Compare commits
1 Commits
main
...
dependabot
| Author | SHA1 | Date | |
|---|---|---|---|
|
0d8a389406 |
@@ -1,68 +0,0 @@
|
||||
# Git
|
||||
.git
|
||||
.gitignore
|
||||
|
||||
# Node modules (rebuilt inside Docker)
|
||||
frontend/node_modules
|
||||
|
||||
# Python cache
|
||||
__pycache__
|
||||
*.pyc
|
||||
*.pyo
|
||||
*.pyd
|
||||
.Python
|
||||
*.so
|
||||
*.egg
|
||||
*.egg-info
|
||||
dist
|
||||
build
|
||||
|
||||
# Virtual envs
|
||||
.venv
|
||||
venv/
|
||||
ENV/
|
||||
|
||||
# IDE
|
||||
.idea/
|
||||
.vscode/
|
||||
*.swp
|
||||
*.swo
|
||||
|
||||
# OS
|
||||
.DS_Store
|
||||
Thumbs.db
|
||||
|
||||
# Docs & markdown (not needed in container)
|
||||
docs/
|
||||
docs-site/
|
||||
*.md
|
||||
|
||||
# GitHub meta
|
||||
.github/
|
||||
|
||||
# Frontend build is copied separately via --from
|
||||
# so exclude the local build dir to keep context small
|
||||
frontend/build/
|
||||
frontend/.env
|
||||
frontend/.env.local
|
||||
frontend/.env.production
|
||||
|
||||
# Backend env
|
||||
.env
|
||||
.env.*
|
||||
!backend/env_template.txt
|
||||
|
||||
# Test files
|
||||
**/test/
|
||||
**/tests/
|
||||
*.test.py
|
||||
*.spec.py
|
||||
|
||||
# Logs
|
||||
*.log
|
||||
logs/
|
||||
|
||||
# Temp
|
||||
tmp/
|
||||
temp/
|
||||
*.tmp
|
||||
23
.github/workflows/lint-forced-user-id.yml
vendored
23
.github/workflows/lint-forced-user-id.yml
vendored
@@ -1,23 +0,0 @@
|
||||
name: Lint Forced User ID Patterns
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
lint-forced-user-id:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.11"
|
||||
|
||||
- name: Check for forced/hardcoded user_id patterns
|
||||
run: python backend/scripts/check_forced_user_id_patterns.py
|
||||
17
.gitignore
vendored
17
.gitignore
vendored
@@ -4,27 +4,15 @@ __pycache__/
|
||||
*.db
|
||||
*.sqlite*
|
||||
|
||||
nul
|
||||
LICENSE
|
||||
CHANGELOG.md
|
||||
|
||||
.planning
|
||||
.planning/
|
||||
|
||||
|
||||
.trae/
|
||||
.trae
|
||||
|
||||
workspace/
|
||||
workspace/*
|
||||
|
||||
.windsurf
|
||||
artifacts
|
||||
|
||||
.opencode
|
||||
|
||||
data/
|
||||
data/*
|
||||
|
||||
.trae/
|
||||
/backend/database/migrations/*
|
||||
@@ -33,7 +21,7 @@ backend/*.db
|
||||
backend\youtube_audio
|
||||
youtube_avatars
|
||||
backend\youtube_images
|
||||
data/media/podcast_videos/AI_Videos
|
||||
|
||||
backend/.trae_*
|
||||
|
||||
# Onboarding progress files
|
||||
@@ -236,9 +224,6 @@ gsc_credentials_template.json
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
docs
|
||||
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
|
||||
0
.windsurf/workflows/c.md
Normal file
0
.windsurf/workflows/c.md
Normal file
72
Dockerfile
72
Dockerfile
@@ -1,72 +0,0 @@
|
||||
# ============================================================
|
||||
# ALwrity Dockerfile — for EasyPanel deployment
|
||||
# ============================================================
|
||||
# Stage 1: Build frontend
|
||||
FROM node:20-alpine AS frontend-builder
|
||||
|
||||
WORKDIR /app/frontend
|
||||
|
||||
# Copy package files
|
||||
COPY frontend/package.json frontend/package-lock.json* ./
|
||||
|
||||
# Install deps (--legacy-peer-deps needed for react-scripts 5)
|
||||
RUN npm install --legacy-peer-deps
|
||||
|
||||
# Copy frontend source
|
||||
COPY frontend/ ./
|
||||
|
||||
# Build static assets
|
||||
RUN npm run build
|
||||
|
||||
# ============================================================
|
||||
# Stage 2: Python backend
|
||||
FROM python:3.11-slim AS backend
|
||||
|
||||
ENV PYTHONDONTWRITEBYTECODE=1
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
ENV PORT=8000
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Install build deps for some Python packages
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
build-essential \
|
||||
libpq-dev \
|
||||
curl \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Copy requirements first (for caching)
|
||||
COPY backend/requirements.txt .
|
||||
|
||||
# Install Python deps
|
||||
RUN pip install --no-cache-dir -r requirements.txt
|
||||
|
||||
# Copy backend source
|
||||
COPY backend/ ./backend/
|
||||
|
||||
# Copy frontend build artifacts from Stage 1
|
||||
COPY --from=frontend-builder /app/frontend/build ./frontend/build
|
||||
|
||||
# Create workspace directories (created by start_alwrity_backend.py but ensure they exist)
|
||||
RUN mkdir -p /app/lib/workspace/alwrity_content \
|
||||
/app/lib/workspace/alwrity_web_research \
|
||||
/app/lib/workspace/alwrity_prompts \
|
||||
/app/lib/workspace/alwrity_config
|
||||
|
||||
# Expose port
|
||||
EXPOSE 8000
|
||||
|
||||
# Health check
|
||||
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
|
||||
CMD curl -f http://localhost:8000/health || exit 1
|
||||
|
||||
# Run with gunicorn + uvicorn workers (recommended for production)
|
||||
# Fallback to plain uvicorn if gunicorn not installed
|
||||
CMD python -m gunicorn backend.app:app \
|
||||
--worker-class uvicorn.workers.UvicornWorker \
|
||||
--bind 0.0.0.0:8000 \
|
||||
--workers 2 \
|
||||
--timeout 120 \
|
||||
--access-logfile - \
|
||||
--error-logfile - \
|
||||
--log-level info
|
||||
215
ToBeMigrated/ai_seo_tools/ENTERPRISE_FEATURES.md
Normal file
215
ToBeMigrated/ai_seo_tools/ENTERPRISE_FEATURES.md
Normal file
@@ -0,0 +1,215 @@
|
||||
# Alwrity Enterprise SEO Features
|
||||
|
||||
## 🚀 Overview
|
||||
|
||||
Alwrity's AI SEO Tools have been enhanced with enterprise-level features that provide comprehensive SEO management, advanced analytics, and AI-powered strategic insights. These enhancements transform Alwrity from a collection of individual tools into a unified enterprise SEO command center.
|
||||
|
||||
## 🏢 Enterprise SEO Suite
|
||||
|
||||
### Unified Command Center (`enterprise_seo_suite.py`)
|
||||
|
||||
The Enterprise SEO Suite serves as a central orchestrator for all SEO activities, providing:
|
||||
|
||||
#### Core Workflows
|
||||
- **Complete SEO Audit**: Comprehensive site analysis combining technical, content, and performance metrics
|
||||
- **Content Strategy Development**: AI-powered content planning with market intelligence
|
||||
- **Search Intelligence Analysis**: Deep GSC data analysis with actionable insights
|
||||
- **Performance Monitoring**: Continuous tracking and optimization recommendations
|
||||
|
||||
#### Key Features
|
||||
- **Intelligent Workflow Orchestration**: Automatically sequences and coordinates multiple SEO analyses
|
||||
- **AI-Powered Recommendations**: Uses advanced AI to generate strategic insights and action plans
|
||||
- **Enterprise Reporting**: Comprehensive reports suitable for executive and team consumption
|
||||
- **Scalable Architecture**: Designed to handle multiple sites and large datasets
|
||||
|
||||
### Enterprise-Level Capabilities
|
||||
- Multi-site management support
|
||||
- Role-based access controls (planned)
|
||||
- Team collaboration features (planned)
|
||||
- Advanced reporting and dashboards
|
||||
- API integration capabilities
|
||||
|
||||
## 📊 Google Search Console Intelligence
|
||||
|
||||
### Advanced GSC Integration (`google_search_console_integration.py`)
|
||||
|
||||
Transforms raw GSC data into strategic insights with:
|
||||
|
||||
#### Search Performance Analysis
|
||||
- **Comprehensive Metrics**: Clicks, impressions, CTR, and position tracking
|
||||
- **Trend Analysis**: Week-over-week and month-over-month performance trends
|
||||
- **Keyword Performance**: Deep analysis of keyword opportunities and optimization potential
|
||||
- **Page Performance**: Identification of top-performing and underperforming pages
|
||||
|
||||
#### Content Opportunities Engine
|
||||
- **CTR Optimization**: Identifies high-impression, low-CTR keywords for meta optimization
|
||||
- **Position Improvement**: Highlights keywords ranking 11-20 for content enhancement
|
||||
- **Content Gap Detection**: Discovers missing keyword opportunities
|
||||
- **Technical Issue Detection**: Identifies potential crawl and indexing problems
|
||||
|
||||
#### AI-Powered Insights
|
||||
- **Strategic Recommendations**: AI analysis of search data for actionable insights
|
||||
- **Immediate Opportunities**: Quick wins identified within 0-30 days
|
||||
- **Long-term Strategy**: 3-12 month strategic planning recommendations
|
||||
- **Competitive Analysis**: Market position assessment and improvement strategies
|
||||
|
||||
### Demo Mode & Real Integration
|
||||
- **Demo Mode**: Realistic sample data for testing and exploration
|
||||
- **GSC API Integration**: Ready for real Google Search Console API connection
|
||||
- **Credentials Management**: Secure handling of GSC API credentials
|
||||
- **Data Export**: Full analysis export in JSON and CSV formats
|
||||
|
||||
## 🧠 AI Content Strategy Generator
|
||||
|
||||
### Comprehensive Strategy Development (`ai_content_strategy.py`)
|
||||
|
||||
Creates complete content strategies using AI market intelligence:
|
||||
|
||||
#### Business Context Analysis
|
||||
- **Market Positioning**: AI analysis of competitive landscape and opportunities
|
||||
- **Content Gap Identification**: Discovers missing content themes in the industry
|
||||
- **Competitive Advantage Mapping**: Identifies unique positioning opportunities
|
||||
- **Audience Intelligence**: Deep insights into target audience needs and preferences
|
||||
|
||||
#### Content Pillar Development
|
||||
- **Strategic Pillars**: 4-6 content themes aligned with business goals
|
||||
- **Keyword Mapping**: Target keywords and semantic variations for each pillar
|
||||
- **Content Type Recommendations**: Optimal content formats for each pillar
|
||||
- **Success Metrics**: KPIs and measurement frameworks for each pillar
|
||||
|
||||
#### Content Calendar Planning
|
||||
- **Automated Scheduling**: AI-generated content calendar with optimal timing
|
||||
- **Resource Planning**: Time estimates and resource allocation
|
||||
- **Priority Scoring**: Content prioritization based on impact and effort
|
||||
- **Distribution Mapping**: Multi-channel content distribution strategy
|
||||
|
||||
#### Topic Cluster Strategy
|
||||
- **SEO-Optimized Clusters**: Topic clusters designed for search dominance
|
||||
- **Pillar Page Strategy**: Hub-and-spoke content architecture
|
||||
- **Internal Linking Plans**: Strategic linking for SEO authority building
|
||||
- **Content Relationship Mapping**: How content pieces support each other
|
||||
|
||||
### Implementation Support
|
||||
- **Phase-Based Roadmap**: 3-phase implementation plan with milestones
|
||||
- **KPI Framework**: Comprehensive measurement and tracking system
|
||||
- **Resource Requirements**: Budget and team resource planning
|
||||
- **Risk Mitigation**: Strategies to avoid common content pitfalls
|
||||
|
||||
## 🔧 Enhanced Technical Capabilities
|
||||
|
||||
### Advanced SEO Workflows
|
||||
- **Multi-Tool Orchestration**: Seamless integration between all SEO tools
|
||||
- **Data Correlation**: Cross-referencing insights from multiple analyses
|
||||
- **Automated Recommendations**: AI-generated action plans with priority scoring
|
||||
- **Performance Tracking**: Before/after analysis and improvement measurement
|
||||
|
||||
### Enterprise Data Management
|
||||
- **Large Dataset Handling**: Optimized for enterprise-scale websites
|
||||
- **Historical Data Tracking**: Long-term trend analysis and comparison
|
||||
- **Data Export & Integration**: API-ready for integration with other tools
|
||||
- **Security & Privacy**: Enterprise-grade data handling and security
|
||||
|
||||
## 📈 Advanced Analytics & Reporting
|
||||
|
||||
### Performance Dashboards
|
||||
- **Executive Summaries**: High-level insights for leadership teams
|
||||
- **Detailed Analytics**: In-depth analysis for SEO practitioners
|
||||
- **Trend Visualization**: Interactive charts and performance tracking
|
||||
- **Competitive Benchmarking**: Market position and competitor analysis
|
||||
|
||||
### ROI Measurement
|
||||
- **Impact Quantification**: Measuring SEO improvements in business terms
|
||||
- **Cost-Benefit Analysis**: ROI calculation for SEO investments
|
||||
- **Performance Attribution**: Connecting SEO efforts to business outcomes
|
||||
- **Forecasting Models**: Predictive analytics for future performance
|
||||
|
||||
## 🎯 Strategic Planning Features
|
||||
|
||||
### Market Intelligence
|
||||
- **Industry Analysis**: AI-powered market research and trend identification
|
||||
- **Competitive Intelligence**: Deep analysis of competitor content strategies
|
||||
- **Opportunity Mapping**: Identification of untapped market opportunities
|
||||
- **Risk Assessment**: Potential challenges and mitigation strategies
|
||||
|
||||
### Long-term Planning
|
||||
- **Strategic Roadmaps**: 6-12 month SEO strategy development
|
||||
- **Resource Planning**: Team and budget allocation recommendations
|
||||
- **Technology Roadmap**: Tool and platform evolution planning
|
||||
- **Scalability Planning**: Growth-oriented SEO architecture
|
||||
|
||||
## 🚀 Implementation Benefits
|
||||
|
||||
### For Enterprise Teams
|
||||
- **Unified Workflow**: Single platform for all SEO activities
|
||||
- **Team Collaboration**: Shared insights and coordinated strategies
|
||||
- **Scalable Operations**: Handle multiple sites and large datasets
|
||||
- **Executive Reporting**: Clear ROI and performance communication
|
||||
|
||||
### For SEO Professionals
|
||||
- **Advanced Insights**: AI-powered analysis beyond basic tools
|
||||
- **Time Efficiency**: Automated workflows and intelligent recommendations
|
||||
- **Strategic Focus**: Less time on analysis, more on strategy execution
|
||||
- **Competitive Advantage**: Access to enterprise-level intelligence
|
||||
|
||||
### For Business Leaders
|
||||
- **Clear ROI**: Quantified business impact of SEO investments
|
||||
- **Strategic Alignment**: SEO strategy aligned with business objectives
|
||||
- **Risk Management**: Proactive identification and mitigation of SEO risks
|
||||
- **Competitive Intelligence**: Market position and improvement opportunities
|
||||
|
||||
## 🔄 Integration Architecture
|
||||
|
||||
### Modular Design
|
||||
- **Tool Independence**: Each tool can function independently
|
||||
- **Workflow Integration**: Tools work together in intelligent sequences
|
||||
- **API-First**: Ready for integration with external systems
|
||||
- **Extensible Framework**: Easy to add new tools and capabilities
|
||||
|
||||
### Data Flow
|
||||
- **Centralized Data Management**: Unified data storage and processing
|
||||
- **Cross-Tool Insights**: Data sharing between different analyses
|
||||
- **Historical Tracking**: Long-term data retention and trend analysis
|
||||
- **Real-time Updates**: Live data integration and analysis
|
||||
|
||||
## 📋 Getting Started
|
||||
|
||||
### For New Users
|
||||
1. Start with the **Enterprise SEO Suite** for comprehensive analysis
|
||||
2. Use **Demo Mode** to explore features with sample data
|
||||
3. Configure **Google Search Console** integration for real data
|
||||
4. Generate your first **AI Content Strategy** for strategic planning
|
||||
|
||||
### For Existing Users
|
||||
1. Explore the new **Enterprise tab** in the SEO dashboard
|
||||
2. Connect your **Google Search Console** for enhanced insights
|
||||
3. Generate comprehensive **content strategies** using AI
|
||||
4. Utilize **workflow orchestration** for multi-tool analysis
|
||||
|
||||
### Implementation Timeline
|
||||
- **Week 1**: Tool exploration and data connection
|
||||
- **Week 2-3**: Initial audits and strategy development
|
||||
- **Month 1**: Content implementation and optimization
|
||||
- **Month 2-3**: Performance tracking and strategy refinement
|
||||
|
||||
## 🔮 Future Enhancements
|
||||
|
||||
### Planned Features
|
||||
- **Multi-site Management**: Centralized management of multiple websites
|
||||
- **Team Collaboration**: Role-based access and collaborative workflows
|
||||
- **Advanced Integrations**: CRM, Analytics, and Marketing Platform connections
|
||||
- **Machine Learning Models**: Custom AI models for specific industries
|
||||
- **Predictive Analytics**: Forecasting SEO performance and opportunities
|
||||
|
||||
### Roadmap
|
||||
- **Q1**: Multi-site support and team collaboration features
|
||||
- **Q2**: Advanced integrations and custom AI models
|
||||
- **Q3**: Predictive analytics and forecasting capabilities
|
||||
- **Q4**: Industry-specific optimization and enterprise scalability
|
||||
|
||||
---
|
||||
|
||||
## 🎯 Conclusion
|
||||
|
||||
These enterprise enhancements transform Alwrity into a comprehensive SEO management platform that rivals expensive enterprise solutions while maintaining ease of use and AI-powered intelligence. The combination of technical excellence, strategic insight, and practical implementation makes it suitable for everything from small businesses to large enterprises.
|
||||
|
||||
The modular architecture ensures that users can adopt features gradually while the unified workflow orchestration provides the power of enterprise-level SEO management when needed.
|
||||
251
ToBeMigrated/ai_seo_tools/README.md
Normal file
251
ToBeMigrated/ai_seo_tools/README.md
Normal file
@@ -0,0 +1,251 @@
|
||||
# 🚀 Alwrity's Enterprise AI SEO Tools Suite
|
||||
|
||||
**Transform your SEO strategy with AI-powered enterprise-level tools and intelligent workflows**
|
||||
|
||||
Alwrity's AI SEO Tools have evolved into a comprehensive enterprise suite that combines individual optimization tools with intelligent workflow orchestration, providing everything from basic SEO tasks to advanced strategic analysis and competitive intelligence.
|
||||
|
||||
---
|
||||
|
||||
## 🌟 **What's New: Enterprise Features**
|
||||
|
||||
### 🎯 **Enterprise SEO Command Center**
|
||||
- **Unified Workflow Orchestration**: Combines all tools into intelligent, automated workflows
|
||||
- **Complete SEO Audits**: Comprehensive analysis covering technical, content, competitive, and performance aspects
|
||||
- **AI-Powered Strategic Recommendations**: Advanced insights with prioritized action plans
|
||||
- **Enterprise-Level Reporting**: Professional dashboards with ROI measurement and executive summaries
|
||||
|
||||
### 📊 **Google Search Console Intelligence**
|
||||
- **Advanced GSC Integration**: Deep analysis of search performance data with AI insights
|
||||
- **Content Opportunities Engine**: Identifies high-impact optimization opportunities
|
||||
- **Search Intelligence Workflows**: Transforms GSC data into actionable content strategies
|
||||
- **Competitive Position Analysis**: Market positioning insights based on search performance
|
||||
|
||||
### 🧠 **AI Content Strategy Generator**
|
||||
- **Comprehensive Strategy Development**: AI-powered content planning with market intelligence
|
||||
- **Content Pillar Architecture**: Topic cluster strategies with keyword mapping
|
||||
- **Implementation Roadmaps**: Phase-based execution plans with resource estimation
|
||||
- **Business Context Analysis**: Industry-specific insights and competitive positioning
|
||||
|
||||
---
|
||||
|
||||
## 🛠️ **Complete Tool Suite**
|
||||
|
||||
### **🏢 Enterprise Suite**
|
||||
| Tool | Description | Key Features |
|
||||
|------|-------------|--------------|
|
||||
| **Enterprise SEO Command Center** | Unified workflow orchestration | Complete audits, AI recommendations, strategic planning |
|
||||
| **Google Search Console Intelligence** | Advanced GSC data analysis | Content opportunities, search intelligence, competitive analysis |
|
||||
| **AI Content Strategy Generator** | Comprehensive content planning | Market intelligence, topic clusters, implementation roadmaps |
|
||||
|
||||
### **📊 Analytics & Intelligence**
|
||||
| Tool | Description | Key Features |
|
||||
|------|-------------|--------------|
|
||||
| **Enhanced Content Gap Analysis** | Advanced competitive content analysis | Advertools integration, AI insights, opportunity identification |
|
||||
| **Technical SEO Crawler** | Site-wide technical analysis | Performance metrics, crawl analysis, AI recommendations |
|
||||
| **Competitive Intelligence** | Market positioning analysis | Competitor benchmarking, strategic insights, market opportunities |
|
||||
|
||||
### **🔧 Technical SEO**
|
||||
| Tool | Description | Key Features |
|
||||
|------|-------------|--------------|
|
||||
| **On-Page SEO Analyzer** | Comprehensive page optimization | Meta analysis, content optimization, readability scoring |
|
||||
| **URL SEO Checker** | Individual URL analysis | Technical factors, optimization recommendations |
|
||||
| **Google PageSpeed Insights** | Performance analysis | Core Web Vitals, speed optimization, mobile performance |
|
||||
|
||||
### **📝 Content & Strategy**
|
||||
| Tool | Description | Key Features |
|
||||
|------|-------------|--------------|
|
||||
| **Content Calendar Planner** | Strategic content planning | Editorial calendars, topic scheduling, resource planning |
|
||||
| **Topic Cluster Generator** | Content architecture planning | Pillar pages, cluster content, internal linking strategies |
|
||||
| **Content Performance Analyzer** | Content effectiveness analysis | Performance metrics, optimization recommendations |
|
||||
|
||||
### **⚡ Quick Optimization Tools**
|
||||
| Tool | Description | Key Features |
|
||||
|------|-------------|--------------|
|
||||
| **Meta Description Generator** | SEO-friendly meta descriptions | Keyword optimization, CTR enhancement, length optimization |
|
||||
| **Content Title Generator** | Attention-grabbing titles | Keyword integration, engagement optimization, SERP visibility |
|
||||
| **OpenGraph Generator** | Social media optimization | Facebook/LinkedIn optimization, visual appeal, click enhancement |
|
||||
| **Image Alt Text Generator** | AI-powered alt text creation | SEO optimization, accessibility compliance, image discoverability |
|
||||
| **Schema Markup Generator** | Structured data creation | Rich snippets, search enhancement, content understanding |
|
||||
| **Twitter Tags Generator** | Twitter optimization | Engagement enhancement, visibility improvement, social sharing |
|
||||
|
||||
---
|
||||
|
||||
## 🎯 **Enterprise Workflows**
|
||||
|
||||
### **🔍 Complete SEO Audit Workflow**
|
||||
1. **Technical SEO Analysis** - Site-wide technical health assessment
|
||||
2. **Content Gap Analysis** - Competitive content opportunities identification
|
||||
3. **On-Page Optimization** - Page-level SEO factor analysis
|
||||
4. **Performance Analysis** - Speed, mobile, and Core Web Vitals assessment
|
||||
5. **AI Strategic Recommendations** - Prioritized action plan with impact estimates
|
||||
|
||||
### **📊 Search Intelligence Workflow**
|
||||
1. **GSC Data Analysis** - Comprehensive search performance review
|
||||
2. **Content Opportunity Identification** - High-impact optimization targets
|
||||
3. **Competitive Position Assessment** - Market positioning analysis
|
||||
4. **Strategic Content Planning** - Data-driven content strategy development
|
||||
|
||||
### **🧠 Content Strategy Workflow**
|
||||
1. **Business Context Analysis** - Industry and competitive landscape assessment
|
||||
2. **Content Pillar Development** - Topic cluster architecture creation
|
||||
3. **Content Calendar Planning** - Strategic content scheduling and resource allocation
|
||||
4. **Implementation Roadmap** - Phase-based execution with timeline and priorities
|
||||
|
||||
---
|
||||
|
||||
## 🚀 **Getting Started**
|
||||
|
||||
### **For New Users**
|
||||
1. **Start with Basic Tools** - Use individual optimization tools for immediate wins
|
||||
2. **Explore Analytics** - Try content gap analysis and technical crawling
|
||||
3. **Upgrade to Enterprise** - Access unified workflows and AI-powered insights
|
||||
|
||||
### **For Existing Users**
|
||||
1. **Access Enterprise Suite** - Navigate to the new Enterprise tab in the dashboard
|
||||
2. **Run Complete Audit** - Execute comprehensive SEO analysis workflows
|
||||
3. **Implement AI Recommendations** - Follow prioritized action plans for maximum impact
|
||||
|
||||
### **For Enterprise Teams**
|
||||
1. **Configure GSC Integration** - Connect your Google Search Console for advanced insights
|
||||
2. **Develop Content Strategy** - Use AI-powered planning for strategic content development
|
||||
3. **Monitor and Optimize** - Leverage continuous monitoring and optimization workflows
|
||||
|
||||
---
|
||||
|
||||
## 📈 **Business Impact**
|
||||
|
||||
### **Immediate Benefits (0-30 days)**
|
||||
- ✅ **Quick Wins Identification** - AI-powered immediate optimization opportunities
|
||||
- ✅ **Technical Issue Resolution** - Critical SEO problems with prioritized fixes
|
||||
- ✅ **Content Optimization** - Existing page improvements for better performance
|
||||
- ✅ **Performance Enhancement** - Speed and mobile optimization recommendations
|
||||
|
||||
### **Strategic Growth (1-6 months)**
|
||||
- 📈 **Content Strategy Execution** - Systematic content development with topic clusters
|
||||
- 📈 **Competitive Positioning** - Market advantage through strategic content gaps
|
||||
- 📈 **Authority Building** - Thought leadership content and link-worthy assets
|
||||
- 📈 **Search Visibility** - Improved rankings through comprehensive optimization
|
||||
|
||||
### **Long-term Success (6-12 months)**
|
||||
- 🏆 **Market Leadership** - Dominant search presence in target markets
|
||||
- 🏆 **Organic Growth** - Sustainable traffic and conversion improvements
|
||||
- 🏆 **Competitive Advantage** - Advanced SEO capabilities beyond competitors
|
||||
- 🏆 **ROI Optimization** - Measurable business impact and revenue growth
|
||||
|
||||
---
|
||||
|
||||
## 🔧 **Technical Architecture**
|
||||
|
||||
### **Modular Design**
|
||||
- **Independent Tools** - Each tool functions standalone for specific tasks
|
||||
- **Workflow Integration** - Tools combine seamlessly in enterprise workflows
|
||||
- **API-Ready Architecture** - External system integration capabilities
|
||||
- **Scalable Infrastructure** - Handles enterprise-level data and analysis
|
||||
|
||||
### **AI Integration**
|
||||
- **Advanced Language Models** - GPT-powered analysis and recommendations
|
||||
- **Contextual Intelligence** - Business-specific insights and strategies
|
||||
- **Continuous Learning** - Improving recommendations based on performance data
|
||||
- **Multi-Modal Analysis** - Text, data, and performance metric integration
|
||||
|
||||
### **Data Management**
|
||||
- **Secure Processing** - Enterprise-grade data security and privacy
|
||||
- **Real-time Analysis** - Live data processing and immediate insights
|
||||
- **Historical Tracking** - Performance monitoring and trend analysis
|
||||
- **Export Capabilities** - Comprehensive reporting and data portability
|
||||
|
||||
---
|
||||
|
||||
## 🎯 **Use Cases by Role**
|
||||
|
||||
### **SEO Professionals**
|
||||
- **Comprehensive Audits** - Complete site analysis with actionable recommendations
|
||||
- **Competitive Intelligence** - Market positioning and opportunity identification
|
||||
- **Strategic Planning** - Long-term SEO roadmaps with business alignment
|
||||
- **Performance Monitoring** - Continuous optimization and improvement tracking
|
||||
|
||||
### **Content Marketers**
|
||||
- **Content Strategy Development** - AI-powered planning with market intelligence
|
||||
- **Topic Research** - Data-driven content ideas and keyword opportunities
|
||||
- **Performance Analysis** - Content effectiveness measurement and optimization
|
||||
- **Editorial Planning** - Strategic content calendars with resource allocation
|
||||
|
||||
### **Business Leaders**
|
||||
- **ROI Measurement** - Clear business impact and performance metrics
|
||||
- **Strategic Insights** - Market opportunities and competitive positioning
|
||||
- **Resource Planning** - Efficient allocation of SEO and content resources
|
||||
- **Executive Reporting** - High-level dashboards and strategic recommendations
|
||||
|
||||
### **Agencies & Consultants**
|
||||
- **Client Audits** - Professional-grade analysis and reporting
|
||||
- **Scalable Solutions** - Multi-client management and optimization
|
||||
- **Competitive Analysis** - Market intelligence and positioning strategies
|
||||
- **Value Demonstration** - Clear ROI and performance improvement tracking
|
||||
|
||||
---
|
||||
|
||||
## 🔮 **Future Roadmap**
|
||||
|
||||
### **Planned Enhancements**
|
||||
- 🔄 **Real-time Monitoring** - Continuous SEO health tracking and alerts
|
||||
- 🤖 **Advanced AI Models** - Enhanced analysis and prediction capabilities
|
||||
- 🌐 **Multi-language Support** - Global SEO optimization and analysis
|
||||
- 📱 **Mobile App** - On-the-go SEO monitoring and management
|
||||
- 🔗 **Enhanced Integrations** - More third-party tool connections and APIs
|
||||
|
||||
### **Advanced Features in Development**
|
||||
- **Predictive SEO Analytics** - Forecast performance and opportunity identification
|
||||
- **Automated Optimization** - AI-driven automatic SEO improvements
|
||||
- **Voice Search Optimization** - Emerging search behavior analysis
|
||||
- **Local SEO Suite** - Location-based optimization and management
|
||||
- **E-commerce SEO** - Specialized tools for online retail optimization
|
||||
|
||||
---
|
||||
|
||||
## 📚 **Resources & Support**
|
||||
|
||||
### **Documentation**
|
||||
- 📖 **Enterprise Features Guide** - Comprehensive feature documentation
|
||||
- 🎥 **Video Tutorials** - Step-by-step workflow demonstrations
|
||||
- 📋 **Best Practices** - Industry-standard SEO optimization guidelines
|
||||
- 🔧 **API Documentation** - Integration guides and technical specifications
|
||||
|
||||
### **Support Channels**
|
||||
- 💬 **Community Forum** - User discussions and knowledge sharing
|
||||
- 📧 **Email Support** - Direct assistance for technical issues
|
||||
- 🎓 **Training Programs** - Advanced SEO strategy and tool mastery
|
||||
- 🤝 **Consulting Services** - Strategic SEO planning and implementation
|
||||
|
||||
---
|
||||
|
||||
## 🏁 **Action Plan: Maximize Your SEO Success**
|
||||
|
||||
### **Phase 1: Foundation (Week 1-2)**
|
||||
1. **Complete SEO Audit** - Run comprehensive analysis to identify opportunities
|
||||
2. **Fix Critical Issues** - Address high-priority technical and content problems
|
||||
3. **Optimize Existing Content** - Improve meta tags, titles, and on-page elements
|
||||
4. **Set Up Monitoring** - Configure GSC integration and performance tracking
|
||||
|
||||
### **Phase 2: Strategic Development (Week 3-8)**
|
||||
1. **Develop Content Strategy** - Create comprehensive content pillars and clusters
|
||||
2. **Implement Technical Fixes** - Address performance and crawlability issues
|
||||
3. **Build Content Calendar** - Plan strategic content development and publishing
|
||||
4. **Monitor Competitive Position** - Track market positioning and opportunities
|
||||
|
||||
### **Phase 3: Growth & Optimization (Week 9-24)**
|
||||
1. **Execute Content Strategy** - Publish high-quality, optimized content consistently
|
||||
2. **Build Authority** - Develop thought leadership and link-worthy content
|
||||
3. **Expand Market Presence** - Target new keywords and market segments
|
||||
4. **Measure and Refine** - Continuously optimize based on performance data
|
||||
|
||||
### **Phase 4: Market Leadership (Month 6+)**
|
||||
1. **Dominate Target Markets** - Achieve top rankings for primary keywords
|
||||
2. **Scale Successful Strategies** - Expand winning approaches to new areas
|
||||
3. **Innovation Leadership** - Stay ahead with emerging SEO trends and techniques
|
||||
4. **Sustainable Growth** - Maintain and improve market position continuously
|
||||
|
||||
---
|
||||
|
||||
**Ready to transform your SEO strategy?** Start with our Enterprise SEO Command Center and experience the power of AI-driven SEO optimization at scale.
|
||||
|
||||
🚀 **[Launch Enterprise SEO Suite](./enterprise_seo_suite.py)** | 📊 **[Explore GSC Intelligence](./google_search_console_integration.py)** | 🧠 **[Generate Content Strategy](./ai_content_strategy.py)**
|
||||
68
ToBeMigrated/ai_seo_tools/TBD
Normal file
68
ToBeMigrated/ai_seo_tools/TBD
Normal file
@@ -0,0 +1,68 @@
|
||||
https://github.com/greghub/website-launch-checklist
|
||||
https://github.com/marcobiedermann/search-engine-optimization
|
||||
https://developers.google.com/speed/docs/insights/v5/get-started
|
||||
https://developers.google.com/search/apis/indexing-api/v3/prereqs
|
||||
https://developer.chrome.com/docs/lighthouse/overview/#cli
|
||||
|
||||
APIs
|
||||
https://docs.ayrshare.com/
|
||||
https://github.com/dataforseo/PythonClient
|
||||
https://mysiteauditor.com/api
|
||||
|
||||
https://github.com/searchsolved/search-solved-public-seo/blob/main/keyword-research/low-competition-keyword-finder-serp-api/low_competition_finder_serp_api.py
|
||||
|
||||
### Structured Data
|
||||
|
||||
- [Facebook Debugger](https://developers.facebook.com/tools/debug) - Enter the URL you want to scrape to see how the page's markup appears to Facebook.
|
||||
- [Pinterest](https://developers.pinterest.com/rich_pins/validator/) - Validate your Rich Pins and apply to get them on Pinterest.
|
||||
- [Structured Data Testing Tool](https://developers.google.com/structured-data/testing-tool/) - Paste in your rich snippets or url to test it.
|
||||
- [Twitter card validator](https://cards-dev.twitter.com/validator) - Enter the URL of the page with the meta tags to validate.
|
||||
|
||||
https://github.com/sethblack/python-seo-analyzer
|
||||
|
||||
https://www.holisticseo.digital/python-seo/analyse-compare-robots-txt/
|
||||
|
||||
https://github.com/Nv7-GitHub/googlesearch
|
||||
https://www.semrush.com/blog/python-for-google-search/
|
||||
|
||||
https://www.kaggle.com/code/eliasdabbas/botpresso-crawl-audit-analysis
|
||||
https://www.kaggle.com/code/eliasdabbas/nike-xml-sitemap-audit-analysis
|
||||
https://www.kaggle.com/code/eliasdabbas/twitter-user-account-analysis-python-sejournal
|
||||
https://www.kaggle.com/code/eliasdabbas/seo-crawl-analysis-template
|
||||
https://www.kaggle.com/code/eliasdabbas/advertools-seo-crawl-analysis-template
|
||||
|
||||
https://www.semrush.com/blog/content-analysis-xml-sitemaps-python/
|
||||
|
||||
|
||||
different configurations that influence your technical SEO and how to optimize them to maximize your organic search visibility.
|
||||
|
||||
ALwrity’ll cover:
|
||||
|
||||
HTTP status
|
||||
|
||||
URL structure
|
||||
|
||||
Website links
|
||||
|
||||
XML sitemaps
|
||||
|
||||
Robots.txt
|
||||
|
||||
Meta robots tag
|
||||
|
||||
Canonicalization
|
||||
|
||||
JavaScript usage
|
||||
|
||||
HTTPS usage
|
||||
|
||||
Mobile friendliness
|
||||
|
||||
Structured data
|
||||
|
||||
Core Web Vitals
|
||||
|
||||
Hreflang annotations
|
||||
|
||||
|
||||
|
||||
954
ToBeMigrated/ai_seo_tools/ai_content_strategy.py
Normal file
954
ToBeMigrated/ai_seo_tools/ai_content_strategy.py
Normal file
@@ -0,0 +1,954 @@
|
||||
"""
|
||||
AI-Powered Content Strategy Generator
|
||||
|
||||
Creates comprehensive content strategies using AI analysis of SEO data,
|
||||
competitor insights, and market trends for enterprise content planning.
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
from datetime import datetime, timedelta
|
||||
import json
|
||||
from loguru import logger
|
||||
import plotly.express as px
|
||||
import plotly.graph_objects as go
|
||||
|
||||
# Import AI modules
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
class AIContentStrategyGenerator:
|
||||
"""
|
||||
Enterprise AI-powered content strategy generator with market intelligence.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the content strategy generator."""
|
||||
logger.info("AI Content Strategy Generator initialized")
|
||||
|
||||
def generate_content_strategy(self, business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Generate comprehensive AI-powered content strategy.
|
||||
|
||||
Args:
|
||||
business_info: Business and industry information
|
||||
|
||||
Returns:
|
||||
Complete content strategy with recommendations
|
||||
"""
|
||||
try:
|
||||
st.info("🧠 Generating AI-powered content strategy...")
|
||||
|
||||
# Analyze business context
|
||||
business_analysis = self._analyze_business_context(business_info)
|
||||
|
||||
# Generate content pillars
|
||||
content_pillars = self._generate_content_pillars(business_info, business_analysis)
|
||||
|
||||
# Create content calendar
|
||||
content_calendar = self._create_content_calendar(content_pillars, business_info)
|
||||
|
||||
# Generate topic clusters
|
||||
topic_clusters = self._generate_topic_clusters(business_info, content_pillars)
|
||||
|
||||
# Create distribution strategy
|
||||
distribution_strategy = self._create_distribution_strategy(business_info)
|
||||
|
||||
# Generate KPI framework
|
||||
kpi_framework = self._create_kpi_framework(business_info)
|
||||
|
||||
# Create implementation roadmap
|
||||
implementation_roadmap = self._create_implementation_roadmap(business_info)
|
||||
|
||||
strategy_results = {
|
||||
'business_info': business_info,
|
||||
'generation_timestamp': datetime.utcnow().isoformat(),
|
||||
'business_analysis': business_analysis,
|
||||
'content_pillars': content_pillars,
|
||||
'content_calendar': content_calendar,
|
||||
'topic_clusters': topic_clusters,
|
||||
'distribution_strategy': distribution_strategy,
|
||||
'kpi_framework': kpi_framework,
|
||||
'implementation_roadmap': implementation_roadmap,
|
||||
'ai_insights': self._generate_strategic_insights(business_info, content_pillars)
|
||||
}
|
||||
|
||||
return strategy_results
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"Error generating content strategy: {str(e)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
return {'error': error_msg}
|
||||
|
||||
def _analyze_business_context(self, business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze business context for strategic insights."""
|
||||
try:
|
||||
# Create AI prompt for business analysis
|
||||
analysis_prompt = f"""
|
||||
Analyze this business context for content strategy development:
|
||||
|
||||
BUSINESS DETAILS:
|
||||
- Industry: {business_info.get('industry', 'Not specified')}
|
||||
- Target Audience: {business_info.get('target_audience', 'Not specified')}
|
||||
- Business Goals: {business_info.get('business_goals', 'Not specified')}
|
||||
- Content Objectives: {business_info.get('content_objectives', 'Not specified')}
|
||||
- Budget: {business_info.get('budget', 'Not specified')}
|
||||
- Timeline: {business_info.get('timeline', 'Not specified')}
|
||||
|
||||
Provide analysis on:
|
||||
1. Market positioning opportunities
|
||||
2. Content gaps in the industry
|
||||
3. Competitive advantages to leverage
|
||||
4. Audience pain points and interests
|
||||
5. Seasonal content opportunities
|
||||
6. Content format preferences for this audience
|
||||
7. Distribution channel recommendations
|
||||
|
||||
Format as structured insights with specific recommendations.
|
||||
"""
|
||||
|
||||
ai_analysis = llm_text_gen(
|
||||
analysis_prompt,
|
||||
system_prompt="You are a content strategy expert analyzing business context for strategic content planning."
|
||||
)
|
||||
|
||||
return {
|
||||
'full_analysis': ai_analysis,
|
||||
'market_position': self._extract_market_position(ai_analysis),
|
||||
'content_gaps': self._extract_content_gaps(ai_analysis),
|
||||
'competitive_advantages': self._extract_competitive_advantages(ai_analysis),
|
||||
'audience_insights': self._extract_audience_insights(ai_analysis)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Business analysis error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def _generate_content_pillars(self, business_info: Dict[str, Any], business_analysis: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""Generate strategic content pillars."""
|
||||
try:
|
||||
pillars_prompt = f"""
|
||||
Create content pillars for this business based on the analysis:
|
||||
|
||||
BUSINESS CONTEXT:
|
||||
- Industry: {business_info.get('industry', 'Not specified')}
|
||||
- Target Audience: {business_info.get('target_audience', 'Not specified')}
|
||||
- Business Goals: {business_info.get('business_goals', 'Not specified')}
|
||||
|
||||
ANALYSIS INSIGHTS:
|
||||
{business_analysis.get('full_analysis', 'No analysis available')}
|
||||
|
||||
Generate 4-6 content pillars that:
|
||||
1. Align with business goals
|
||||
2. Address audience needs
|
||||
3. Differentiate from competitors
|
||||
4. Support SEO objectives
|
||||
5. Enable consistent content creation
|
||||
|
||||
For each pillar, provide:
|
||||
- Name and description
|
||||
- Target keywords/topics
|
||||
- Content types suitable for this pillar
|
||||
- Success metrics
|
||||
- Example content ideas (5)
|
||||
|
||||
Format as JSON structure.
|
||||
"""
|
||||
|
||||
ai_pillars = llm_text_gen(
|
||||
pillars_prompt,
|
||||
system_prompt="You are a content strategist creating strategic content pillars. Return structured data."
|
||||
)
|
||||
|
||||
# Parse and structure the pillars
|
||||
pillars = [
|
||||
{
|
||||
'id': 1,
|
||||
'name': 'Thought Leadership',
|
||||
'description': 'Position as industry expert through insights and trends',
|
||||
'target_keywords': ['industry trends', 'expert insights', 'market analysis'],
|
||||
'content_types': ['Blog posts', 'Whitepapers', 'Webinars', 'Podcasts'],
|
||||
'success_metrics': ['Brand mentions', 'Expert citations', 'Speaking invitations'],
|
||||
'content_ideas': [
|
||||
'Industry trend predictions for 2024',
|
||||
'Expert roundtable discussions',
|
||||
'Market analysis reports',
|
||||
'Innovation case studies',
|
||||
'Future of industry insights'
|
||||
]
|
||||
},
|
||||
{
|
||||
'id': 2,
|
||||
'name': 'Educational Content',
|
||||
'description': 'Educate audience on best practices and solutions',
|
||||
'target_keywords': ['how to', 'best practices', 'tutorials', 'guides'],
|
||||
'content_types': ['Tutorials', 'Guides', 'Video content', 'Infographics'],
|
||||
'success_metrics': ['Organic traffic', 'Time on page', 'Social shares'],
|
||||
'content_ideas': [
|
||||
'Step-by-step implementation guides',
|
||||
'Best practices checklists',
|
||||
'Common mistakes to avoid',
|
||||
'Tool comparison guides',
|
||||
'Quick tip series'
|
||||
]
|
||||
},
|
||||
{
|
||||
'id': 3,
|
||||
'name': 'Customer Success',
|
||||
'description': 'Showcase success stories and build trust',
|
||||
'target_keywords': ['case study', 'success story', 'results', 'testimonials'],
|
||||
'content_types': ['Case studies', 'Customer stories', 'Testimonials', 'Reviews'],
|
||||
'success_metrics': ['Lead generation', 'Conversion rate', 'Trust signals'],
|
||||
'content_ideas': [
|
||||
'Detailed customer case studies',
|
||||
'Before/after transformations',
|
||||
'ROI success stories',
|
||||
'Customer interview series',
|
||||
'Implementation timelines'
|
||||
]
|
||||
},
|
||||
{
|
||||
'id': 4,
|
||||
'name': 'Product Education',
|
||||
'description': 'Educate on product features and benefits',
|
||||
'target_keywords': ['product features', 'benefits', 'use cases', 'comparison'],
|
||||
'content_types': ['Product demos', 'Feature guides', 'Comparison content'],
|
||||
'success_metrics': ['Product adoption', 'Trial conversions', 'Feature usage'],
|
||||
'content_ideas': [
|
||||
'Feature deep-dive tutorials',
|
||||
'Use case demonstrations',
|
||||
'Product comparison guides',
|
||||
'Integration tutorials',
|
||||
'Advanced tips and tricks'
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
return pillars
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Content pillars error: {str(e)}")
|
||||
return []
|
||||
|
||||
def _create_content_calendar(self, content_pillars: List[Dict[str, Any]], business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Create comprehensive content calendar."""
|
||||
timeline = business_info.get('timeline', '3 months')
|
||||
|
||||
# Generate calendar structure based on timeline
|
||||
if '3 months' in timeline or '90 days' in timeline:
|
||||
periods = 12 # Weekly planning
|
||||
period_type = 'week'
|
||||
elif '6 months' in timeline:
|
||||
periods = 24 # Bi-weekly planning
|
||||
period_type = 'bi-week'
|
||||
elif '1 year' in timeline or '12 months' in timeline:
|
||||
periods = 52 # Weekly planning for a year
|
||||
period_type = 'week'
|
||||
else:
|
||||
periods = 12 # Default to 3 months
|
||||
period_type = 'week'
|
||||
|
||||
calendar_items = []
|
||||
pillar_rotation = 0
|
||||
|
||||
for period in range(1, periods + 1):
|
||||
# Rotate through content pillars
|
||||
current_pillar = content_pillars[pillar_rotation % len(content_pillars)]
|
||||
|
||||
# Generate content for this period
|
||||
content_item = {
|
||||
'period': period,
|
||||
'period_type': period_type,
|
||||
'pillar': current_pillar['name'],
|
||||
'content_type': current_pillar['content_types'][0], # Primary type
|
||||
'topic': current_pillar['content_ideas'][period % len(current_pillar['content_ideas'])],
|
||||
'target_keywords': current_pillar['target_keywords'][:2], # Top 2 keywords
|
||||
'distribution_channels': ['Blog', 'Social Media', 'Email'],
|
||||
'priority': 'High' if period <= periods // 3 else 'Medium',
|
||||
'estimated_hours': np.random.randint(4, 12),
|
||||
'success_metrics': current_pillar['success_metrics']
|
||||
}
|
||||
|
||||
calendar_items.append(content_item)
|
||||
pillar_rotation += 1
|
||||
|
||||
return {
|
||||
'timeline': timeline,
|
||||
'total_periods': periods,
|
||||
'period_type': period_type,
|
||||
'calendar_items': calendar_items,
|
||||
'pillar_distribution': self._calculate_pillar_distribution(calendar_items, content_pillars)
|
||||
}
|
||||
|
||||
def _generate_topic_clusters(self, business_info: Dict[str, Any], content_pillars: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
|
||||
"""Generate SEO topic clusters."""
|
||||
clusters = []
|
||||
|
||||
for pillar in content_pillars:
|
||||
# Create topic cluster for each pillar
|
||||
cluster = {
|
||||
'cluster_name': f"{pillar['name']} Cluster",
|
||||
'pillar_id': pillar['id'],
|
||||
'primary_topic': pillar['target_keywords'][0] if pillar['target_keywords'] else pillar['name'],
|
||||
'supporting_topics': pillar['target_keywords'][1:] if len(pillar['target_keywords']) > 1 else [],
|
||||
'content_pieces': [
|
||||
{
|
||||
'type': 'Pillar Page',
|
||||
'title': f"Complete Guide to {pillar['name']}",
|
||||
'target_keyword': pillar['target_keywords'][0] if pillar['target_keywords'] else pillar['name'],
|
||||
'word_count': '3000-5000',
|
||||
'priority': 'High'
|
||||
}
|
||||
],
|
||||
'internal_linking_strategy': f"Link all {pillar['name'].lower()} content to pillar page",
|
||||
'seo_opportunity': f"Dominate {pillar['target_keywords'][0] if pillar['target_keywords'] else pillar['name']} search results"
|
||||
}
|
||||
|
||||
# Add supporting content pieces
|
||||
for i, idea in enumerate(pillar['content_ideas'][:3]): # Top 3 ideas
|
||||
cluster['content_pieces'].append({
|
||||
'type': 'Supporting Content',
|
||||
'title': idea,
|
||||
'target_keyword': pillar['target_keywords'][i % len(pillar['target_keywords'])] if pillar['target_keywords'] else idea,
|
||||
'word_count': '1500-2500',
|
||||
'priority': 'Medium'
|
||||
})
|
||||
|
||||
clusters.append(cluster)
|
||||
|
||||
return clusters
|
||||
|
||||
def _create_distribution_strategy(self, business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Create content distribution strategy."""
|
||||
return {
|
||||
'primary_channels': [
|
||||
{
|
||||
'channel': 'Company Blog',
|
||||
'content_types': ['Long-form articles', 'Guides', 'Case studies'],
|
||||
'frequency': 'Weekly',
|
||||
'audience_reach': 'High',
|
||||
'seo_value': 'High'
|
||||
},
|
||||
{
|
||||
'channel': 'LinkedIn',
|
||||
'content_types': ['Professional insights', 'Industry news', 'Thought leadership'],
|
||||
'frequency': 'Daily',
|
||||
'audience_reach': 'Medium',
|
||||
'seo_value': 'Medium'
|
||||
},
|
||||
{
|
||||
'channel': 'Email Newsletter',
|
||||
'content_types': ['Curated insights', 'Product updates', 'Educational content'],
|
||||
'frequency': 'Bi-weekly',
|
||||
'audience_reach': 'High',
|
||||
'seo_value': 'Low'
|
||||
}
|
||||
],
|
||||
'secondary_channels': [
|
||||
{
|
||||
'channel': 'YouTube',
|
||||
'content_types': ['Tutorial videos', 'Webinars', 'Product demos'],
|
||||
'frequency': 'Bi-weekly',
|
||||
'audience_reach': 'Medium',
|
||||
'seo_value': 'High'
|
||||
},
|
||||
{
|
||||
'channel': 'Industry Publications',
|
||||
'content_types': ['Guest articles', 'Expert quotes', 'Research insights'],
|
||||
'frequency': 'Monthly',
|
||||
'audience_reach': 'Medium',
|
||||
'seo_value': 'High'
|
||||
}
|
||||
],
|
||||
'repurposing_strategy': {
|
||||
'blog_post_to_social': 'Extract key insights for LinkedIn posts',
|
||||
'long_form_to_video': 'Create video summaries of detailed guides',
|
||||
'case_study_to_multiple': 'Create infographics, social posts, and email content',
|
||||
'webinar_to_content': 'Extract blog posts, social content, and email series'
|
||||
}
|
||||
}
|
||||
|
||||
def _create_kpi_framework(self, business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Create KPI measurement framework."""
|
||||
return {
|
||||
'primary_kpis': [
|
||||
{
|
||||
'metric': 'Organic Traffic Growth',
|
||||
'target': '25% increase per quarter',
|
||||
'measurement': 'Google Analytics',
|
||||
'frequency': 'Monthly'
|
||||
},
|
||||
{
|
||||
'metric': 'Lead Generation',
|
||||
'target': '50 qualified leads per month',
|
||||
'measurement': 'CRM tracking',
|
||||
'frequency': 'Weekly'
|
||||
},
|
||||
{
|
||||
'metric': 'Brand Awareness',
|
||||
'target': '15% increase in brand mentions',
|
||||
'measurement': 'Social listening tools',
|
||||
'frequency': 'Monthly'
|
||||
}
|
||||
],
|
||||
'content_kpis': [
|
||||
{
|
||||
'metric': 'Content Engagement',
|
||||
'target': '5% average engagement rate',
|
||||
'measurement': 'Social media analytics',
|
||||
'frequency': 'Weekly'
|
||||
},
|
||||
{
|
||||
'metric': 'Content Shares',
|
||||
'target': '100 shares per piece',
|
||||
'measurement': 'Social sharing tracking',
|
||||
'frequency': 'Per content piece'
|
||||
},
|
||||
{
|
||||
'metric': 'Time on Page',
|
||||
'target': '3+ minutes average',
|
||||
'measurement': 'Google Analytics',
|
||||
'frequency': 'Monthly'
|
||||
}
|
||||
],
|
||||
'seo_kpis': [
|
||||
{
|
||||
'metric': 'Keyword Rankings',
|
||||
'target': 'Top 10 for 20 target keywords',
|
||||
'measurement': 'SEO tools',
|
||||
'frequency': 'Weekly'
|
||||
},
|
||||
{
|
||||
'metric': 'Backlink Growth',
|
||||
'target': '10 quality backlinks per month',
|
||||
'measurement': 'Backlink analysis tools',
|
||||
'frequency': 'Monthly'
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
def _create_implementation_roadmap(self, business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Create implementation roadmap."""
|
||||
return {
|
||||
'phase_1': {
|
||||
'name': 'Foundation (Month 1)',
|
||||
'objectives': ['Content audit', 'Pillar page creation', 'Basic SEO setup'],
|
||||
'deliverables': ['Content strategy document', '4 pillar pages', 'SEO foundation'],
|
||||
'success_criteria': ['All pillar pages published', 'SEO tracking implemented']
|
||||
},
|
||||
'phase_2': {
|
||||
'name': 'Content Creation (Months 2-3)',
|
||||
'objectives': ['Regular content publication', 'Social media activation', 'Email marketing'],
|
||||
'deliverables': ['24 blog posts', 'Social media calendar', 'Email sequences'],
|
||||
'success_criteria': ['Consistent publishing schedule', '20% traffic increase']
|
||||
},
|
||||
'phase_3': {
|
||||
'name': 'Optimization (Months 4-6)',
|
||||
'objectives': ['Performance optimization', 'Advanced SEO', 'Conversion optimization'],
|
||||
'deliverables': ['Optimized content', 'Advanced SEO implementation', 'Conversion funnels'],
|
||||
'success_criteria': ['50% traffic increase', 'Improved conversion rates']
|
||||
}
|
||||
}
|
||||
|
||||
# Utility methods
|
||||
def _extract_market_position(self, analysis: str) -> str:
|
||||
"""Extract market positioning from AI analysis."""
|
||||
return "Market positioning insights extracted from AI analysis"
|
||||
|
||||
def _extract_content_gaps(self, analysis: str) -> List[str]:
|
||||
"""Extract content gaps from AI analysis."""
|
||||
return ["Educational content gap", "Technical documentation gap", "Case study gap"]
|
||||
|
||||
def _extract_competitive_advantages(self, analysis: str) -> List[str]:
|
||||
"""Extract competitive advantages from AI analysis."""
|
||||
return ["Unique technology approach", "Industry expertise", "Customer success focus"]
|
||||
|
||||
def _extract_audience_insights(self, analysis: str) -> Dict[str, Any]:
|
||||
"""Extract audience insights from AI analysis."""
|
||||
return {
|
||||
'pain_points': ["Complex implementation", "Limited resources", "ROI concerns"],
|
||||
'content_preferences': ["Visual content", "Step-by-step guides", "Real examples"],
|
||||
'consumption_patterns': ["Mobile-first", "Video preferred", "Quick consumption"]
|
||||
}
|
||||
|
||||
def _calculate_pillar_distribution(self, calendar_items: List[Dict[str, Any]], content_pillars: List[Dict[str, Any]]) -> Dict[str, int]:
|
||||
"""Calculate content distribution across pillars."""
|
||||
distribution = {}
|
||||
for pillar in content_pillars:
|
||||
count = len([item for item in calendar_items if item['pillar'] == pillar['name']])
|
||||
distribution[pillar['name']] = count
|
||||
return distribution
|
||||
|
||||
def _generate_strategic_insights(self, business_info: Dict[str, Any], content_pillars: List[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""Generate strategic insights and recommendations."""
|
||||
return {
|
||||
'key_insights': [
|
||||
"Focus on educational content for early funnel engagement",
|
||||
"Leverage customer success stories for conversion",
|
||||
"Develop thought leadership for brand authority",
|
||||
"Create product education for user adoption"
|
||||
],
|
||||
'strategic_recommendations': [
|
||||
"Implement topic cluster strategy for SEO dominance",
|
||||
"Create pillar page for each content theme",
|
||||
"Develop comprehensive content repurposing workflow",
|
||||
"Establish thought leadership through industry insights"
|
||||
],
|
||||
'risk_mitigation': [
|
||||
"Diversify content topics to avoid algorithm dependency",
|
||||
"Create evergreen content for long-term value",
|
||||
"Build email list to reduce platform dependency",
|
||||
"Monitor competitor content to maintain differentiation"
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
def render_ai_content_strategy():
|
||||
"""Render the AI Content Strategy interface."""
|
||||
|
||||
st.title("🧠 AI Content Strategy Generator")
|
||||
st.markdown("**Generate comprehensive content strategies powered by AI intelligence**")
|
||||
|
||||
# Configuration form
|
||||
st.header("📋 Business Information")
|
||||
|
||||
with st.form("content_strategy_form"):
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
industry = st.selectbox(
|
||||
"Industry",
|
||||
[
|
||||
"Technology & Software",
|
||||
"Marketing & Advertising",
|
||||
"Healthcare",
|
||||
"Finance & Fintech",
|
||||
"E-commerce",
|
||||
"Education",
|
||||
"Manufacturing",
|
||||
"Professional Services",
|
||||
"Other"
|
||||
],
|
||||
index=0
|
||||
)
|
||||
|
||||
target_audience = st.text_area(
|
||||
"Target Audience",
|
||||
placeholder="Describe your ideal customers, their roles, challenges, and goals...",
|
||||
height=100
|
||||
)
|
||||
|
||||
business_goals = st.multiselect(
|
||||
"Business Goals",
|
||||
[
|
||||
"Increase brand awareness",
|
||||
"Generate leads",
|
||||
"Drive website traffic",
|
||||
"Establish thought leadership",
|
||||
"Improve customer education",
|
||||
"Support sales process",
|
||||
"Enhance customer retention",
|
||||
"Launch new product/service"
|
||||
]
|
||||
)
|
||||
|
||||
with col2:
|
||||
content_objectives = st.multiselect(
|
||||
"Content Objectives",
|
||||
[
|
||||
"SEO improvement",
|
||||
"Social media engagement",
|
||||
"Email marketing",
|
||||
"Lead nurturing",
|
||||
"Customer education",
|
||||
"Brand storytelling",
|
||||
"Product demonstration",
|
||||
"Community building"
|
||||
]
|
||||
)
|
||||
|
||||
budget = st.selectbox(
|
||||
"Monthly Content Budget",
|
||||
[
|
||||
"No budget",
|
||||
"Under $1,000",
|
||||
"$1,000 - $5,000",
|
||||
"$5,000 - $10,000",
|
||||
"$10,000 - $25,000",
|
||||
"$25,000+"
|
||||
]
|
||||
)
|
||||
|
||||
timeline = st.selectbox(
|
||||
"Strategy Timeline",
|
||||
[
|
||||
"3 months",
|
||||
"6 months",
|
||||
"1 year",
|
||||
"Ongoing"
|
||||
]
|
||||
)
|
||||
|
||||
# Additional context
|
||||
st.subheader("Additional Context")
|
||||
|
||||
current_challenges = st.text_area(
|
||||
"Current Content Challenges",
|
||||
placeholder="What content challenges are you currently facing?",
|
||||
height=80
|
||||
)
|
||||
|
||||
competitive_landscape = st.text_area(
|
||||
"Competitive Landscape",
|
||||
placeholder="Describe your main competitors and their content approach...",
|
||||
height=80
|
||||
)
|
||||
|
||||
submit_strategy = st.form_submit_button("🧠 Generate AI Content Strategy", type="primary")
|
||||
|
||||
# Process strategy generation
|
||||
if submit_strategy:
|
||||
if target_audience and business_goals and content_objectives:
|
||||
# Prepare business information
|
||||
business_info = {
|
||||
'industry': industry,
|
||||
'target_audience': target_audience,
|
||||
'business_goals': business_goals,
|
||||
'content_objectives': content_objectives,
|
||||
'budget': budget,
|
||||
'timeline': timeline,
|
||||
'current_challenges': current_challenges,
|
||||
'competitive_landscape': competitive_landscape
|
||||
}
|
||||
|
||||
# Initialize generator
|
||||
if 'strategy_generator' not in st.session_state:
|
||||
st.session_state.strategy_generator = AIContentStrategyGenerator()
|
||||
|
||||
generator = st.session_state.strategy_generator
|
||||
|
||||
with st.spinner("🧠 Generating AI-powered content strategy..."):
|
||||
strategy_results = generator.generate_content_strategy(business_info)
|
||||
|
||||
if 'error' not in strategy_results:
|
||||
st.success("✅ Content strategy generated successfully!")
|
||||
|
||||
# Store results in session state
|
||||
st.session_state.strategy_results = strategy_results
|
||||
|
||||
# Display results
|
||||
render_strategy_results_dashboard(strategy_results)
|
||||
else:
|
||||
st.error(f"❌ Strategy generation failed: {strategy_results['error']}")
|
||||
else:
|
||||
st.warning("⚠️ Please fill in target audience, business goals, and content objectives.")
|
||||
|
||||
# Show previous results if available
|
||||
elif 'strategy_results' in st.session_state:
|
||||
st.info("🧠 Showing previous strategy results")
|
||||
render_strategy_results_dashboard(st.session_state.strategy_results)
|
||||
|
||||
|
||||
def render_strategy_results_dashboard(results: Dict[str, Any]):
|
||||
"""Render comprehensive strategy results dashboard."""
|
||||
|
||||
# Strategy overview
|
||||
st.header("📊 Content Strategy Overview")
|
||||
|
||||
business_analysis = results.get('business_analysis', {})
|
||||
content_pillars = results.get('content_pillars', [])
|
||||
content_calendar = results.get('content_calendar', {})
|
||||
|
||||
# Key metrics overview
|
||||
col1, col2, col3, col4 = st.columns(4)
|
||||
|
||||
with col1:
|
||||
st.metric("Content Pillars", len(content_pillars))
|
||||
|
||||
with col2:
|
||||
calendar_items = content_calendar.get('calendar_items', [])
|
||||
st.metric("Content Pieces", len(calendar_items))
|
||||
|
||||
with col3:
|
||||
timeline = content_calendar.get('timeline', 'Not specified')
|
||||
st.metric("Timeline", timeline)
|
||||
|
||||
with col4:
|
||||
total_hours = sum(item.get('estimated_hours', 0) for item in calendar_items)
|
||||
st.metric("Est. Hours", f"{total_hours}h")
|
||||
|
||||
# Strategy tabs
|
||||
tab1, tab2, tab3, tab4, tab5, tab6 = st.tabs([
|
||||
"🧠 AI Insights",
|
||||
"🏛️ Content Pillars",
|
||||
"📅 Content Calendar",
|
||||
"🎯 Topic Clusters",
|
||||
"📢 Distribution",
|
||||
"📊 Implementation"
|
||||
])
|
||||
|
||||
with tab1:
|
||||
if business_analysis:
|
||||
st.subheader("Business Analysis & Insights")
|
||||
|
||||
# Market positioning
|
||||
market_position = business_analysis.get('market_position', '')
|
||||
if market_position:
|
||||
st.markdown("#### 🎯 Market Positioning")
|
||||
st.info(market_position)
|
||||
|
||||
# Content gaps
|
||||
content_gaps = business_analysis.get('content_gaps', [])
|
||||
if content_gaps:
|
||||
st.markdown("#### 🔍 Content Gaps Identified")
|
||||
for gap in content_gaps:
|
||||
st.warning(f"📌 {gap}")
|
||||
|
||||
# Competitive advantages
|
||||
advantages = business_analysis.get('competitive_advantages', [])
|
||||
if advantages:
|
||||
st.markdown("#### 🏆 Competitive Advantages")
|
||||
for advantage in advantages:
|
||||
st.success(f"✅ {advantage}")
|
||||
|
||||
# AI insights
|
||||
ai_insights = results.get('ai_insights', {})
|
||||
if ai_insights:
|
||||
st.markdown("#### 🧠 Strategic AI Insights")
|
||||
|
||||
insights = ai_insights.get('key_insights', [])
|
||||
for insight in insights:
|
||||
st.info(f"💡 {insight}")
|
||||
|
||||
recommendations = ai_insights.get('strategic_recommendations', [])
|
||||
if recommendations:
|
||||
st.markdown("#### 🎯 Strategic Recommendations")
|
||||
for rec in recommendations:
|
||||
st.success(f"📋 {rec}")
|
||||
|
||||
with tab2:
|
||||
if content_pillars:
|
||||
st.subheader("Content Pillars Strategy")
|
||||
|
||||
# Pillars overview chart
|
||||
pillar_names = [pillar['name'] for pillar in content_pillars]
|
||||
pillar_ideas = [len(pillar['content_ideas']) for pillar in content_pillars]
|
||||
|
||||
fig = px.bar(
|
||||
x=pillar_names,
|
||||
y=pillar_ideas,
|
||||
title="Content Ideas per Pillar",
|
||||
labels={'x': 'Content Pillars', 'y': 'Number of Ideas'}
|
||||
)
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
# Detailed pillar information
|
||||
for pillar in content_pillars:
|
||||
with st.expander(f"🏛️ {pillar['name']}", expanded=False):
|
||||
st.markdown(f"**Description:** {pillar['description']}")
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
st.markdown("**Target Keywords:**")
|
||||
for keyword in pillar['target_keywords']:
|
||||
st.code(keyword)
|
||||
|
||||
st.markdown("**Content Types:**")
|
||||
for content_type in pillar['content_types']:
|
||||
st.write(f"• {content_type}")
|
||||
|
||||
with col2:
|
||||
st.markdown("**Success Metrics:**")
|
||||
for metric in pillar['success_metrics']:
|
||||
st.write(f"📊 {metric}")
|
||||
|
||||
st.markdown("**Content Ideas:**")
|
||||
for idea in pillar['content_ideas']:
|
||||
st.write(f"💡 {idea}")
|
||||
|
||||
with tab3:
|
||||
if content_calendar:
|
||||
st.subheader("Content Calendar & Planning")
|
||||
|
||||
calendar_items = content_calendar.get('calendar_items', [])
|
||||
|
||||
if calendar_items:
|
||||
# Calendar overview
|
||||
df_calendar = pd.DataFrame(calendar_items)
|
||||
|
||||
# Priority distribution
|
||||
priority_counts = df_calendar['priority'].value_counts()
|
||||
fig_priority = px.pie(
|
||||
values=priority_counts.values,
|
||||
names=priority_counts.index,
|
||||
title="Content Priority Distribution"
|
||||
)
|
||||
st.plotly_chart(fig_priority, use_container_width=True)
|
||||
|
||||
# Content calendar table
|
||||
st.markdown("#### 📅 Detailed Content Calendar")
|
||||
|
||||
display_df = df_calendar[[
|
||||
'period', 'pillar', 'content_type', 'topic',
|
||||
'priority', 'estimated_hours'
|
||||
]].copy()
|
||||
|
||||
display_df.columns = [
|
||||
'Period', 'Pillar', 'Content Type', 'Topic',
|
||||
'Priority', 'Est. Hours'
|
||||
]
|
||||
|
||||
st.dataframe(
|
||||
display_df,
|
||||
column_config={
|
||||
"Priority": st.column_config.SelectboxColumn(
|
||||
"Priority",
|
||||
options=["High", "Medium", "Low"]
|
||||
),
|
||||
"Est. Hours": st.column_config.NumberColumn(
|
||||
"Est. Hours",
|
||||
format="%d h"
|
||||
)
|
||||
},
|
||||
hide_index=True,
|
||||
use_container_width=True
|
||||
)
|
||||
|
||||
# Export calendar
|
||||
csv = df_calendar.to_csv(index=False)
|
||||
st.download_button(
|
||||
label="📥 Download Content Calendar",
|
||||
data=csv,
|
||||
file_name=f"content_calendar_{datetime.now().strftime('%Y%m%d')}.csv",
|
||||
mime="text/csv"
|
||||
)
|
||||
|
||||
with tab4:
|
||||
topic_clusters = results.get('topic_clusters', [])
|
||||
if topic_clusters:
|
||||
st.subheader("SEO Topic Clusters")
|
||||
|
||||
for cluster in topic_clusters:
|
||||
with st.expander(f"🎯 {cluster['cluster_name']}", expanded=False):
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
st.markdown(f"**Primary Topic:** {cluster['primary_topic']}")
|
||||
st.markdown(f"**SEO Opportunity:** {cluster['seo_opportunity']}")
|
||||
st.markdown(f"**Linking Strategy:** {cluster['internal_linking_strategy']}")
|
||||
|
||||
with col2:
|
||||
st.markdown("**Supporting Topics:**")
|
||||
for topic in cluster['supporting_topics']:
|
||||
st.code(topic)
|
||||
|
||||
st.markdown("**Content Pieces:**")
|
||||
content_pieces = cluster['content_pieces']
|
||||
df_pieces = pd.DataFrame(content_pieces)
|
||||
st.dataframe(df_pieces, hide_index=True, use_container_width=True)
|
||||
|
||||
with tab5:
|
||||
distribution_strategy = results.get('distribution_strategy', {})
|
||||
if distribution_strategy:
|
||||
st.subheader("Content Distribution Strategy")
|
||||
|
||||
# Primary channels
|
||||
primary_channels = distribution_strategy.get('primary_channels', [])
|
||||
if primary_channels:
|
||||
st.markdown("#### 📢 Primary Distribution Channels")
|
||||
df_primary = pd.DataFrame(primary_channels)
|
||||
st.dataframe(df_primary, hide_index=True, use_container_width=True)
|
||||
|
||||
# Secondary channels
|
||||
secondary_channels = distribution_strategy.get('secondary_channels', [])
|
||||
if secondary_channels:
|
||||
st.markdown("#### 📺 Secondary Distribution Channels")
|
||||
df_secondary = pd.DataFrame(secondary_channels)
|
||||
st.dataframe(df_secondary, hide_index=True, use_container_width=True)
|
||||
|
||||
# Repurposing strategy
|
||||
repurposing = distribution_strategy.get('repurposing_strategy', {})
|
||||
if repurposing:
|
||||
st.markdown("#### ♻️ Content Repurposing Strategy")
|
||||
for strategy, description in repurposing.items():
|
||||
st.write(f"**{strategy.replace('_', ' ').title()}:** {description}")
|
||||
|
||||
with tab6:
|
||||
# Implementation roadmap
|
||||
roadmap = results.get('implementation_roadmap', {})
|
||||
kpi_framework = results.get('kpi_framework', {})
|
||||
|
||||
if roadmap:
|
||||
st.subheader("Implementation Roadmap")
|
||||
|
||||
for phase_key, phase_data in roadmap.items():
|
||||
with st.expander(f"📋 {phase_data['name']}", expanded=False):
|
||||
st.markdown(f"**Objectives:**")
|
||||
for objective in phase_data['objectives']:
|
||||
st.write(f"• {objective}")
|
||||
|
||||
st.markdown(f"**Deliverables:**")
|
||||
for deliverable in phase_data['deliverables']:
|
||||
st.write(f"📦 {deliverable}")
|
||||
|
||||
st.markdown(f"**Success Criteria:**")
|
||||
for criteria in phase_data['success_criteria']:
|
||||
st.write(f"✅ {criteria}")
|
||||
|
||||
if kpi_framework:
|
||||
st.subheader("KPI Framework")
|
||||
|
||||
# Primary KPIs
|
||||
primary_kpis = kpi_framework.get('primary_kpis', [])
|
||||
if primary_kpis:
|
||||
st.markdown("#### 🎯 Primary KPIs")
|
||||
df_primary_kpis = pd.DataFrame(primary_kpis)
|
||||
st.dataframe(df_primary_kpis, hide_index=True, use_container_width=True)
|
||||
|
||||
# Content KPIs
|
||||
content_kpis = kpi_framework.get('content_kpis', [])
|
||||
if content_kpis:
|
||||
st.markdown("#### 📝 Content KPIs")
|
||||
df_content_kpis = pd.DataFrame(content_kpis)
|
||||
st.dataframe(df_content_kpis, hide_index=True, use_container_width=True)
|
||||
|
||||
# Export functionality
|
||||
st.markdown("---")
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
if st.button("📥 Export Full Strategy", use_container_width=True):
|
||||
strategy_json = json.dumps(results, indent=2, default=str)
|
||||
st.download_button(
|
||||
label="Download JSON Strategy",
|
||||
data=strategy_json,
|
||||
file_name=f"content_strategy_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
||||
mime="application/json"
|
||||
)
|
||||
|
||||
with col2:
|
||||
if st.button("📊 Export Calendar", use_container_width=True):
|
||||
calendar_items = content_calendar.get('calendar_items', [])
|
||||
if calendar_items:
|
||||
df_calendar = pd.DataFrame(calendar_items)
|
||||
csv = df_calendar.to_csv(index=False)
|
||||
st.download_button(
|
||||
label="Download CSV Calendar",
|
||||
data=csv,
|
||||
file_name=f"content_calendar_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
|
||||
mime="text/csv"
|
||||
)
|
||||
|
||||
with col3:
|
||||
if st.button("🔄 Generate New Strategy", use_container_width=True):
|
||||
if 'strategy_results' in st.session_state:
|
||||
del st.session_state.strategy_results
|
||||
st.rerun()
|
||||
|
||||
|
||||
# Main execution
|
||||
if __name__ == "__main__":
|
||||
render_ai_content_strategy()
|
||||
919
ToBeMigrated/ai_seo_tools/enterprise_seo_suite.py
Normal file
919
ToBeMigrated/ai_seo_tools/enterprise_seo_suite.py
Normal file
@@ -0,0 +1,919 @@
|
||||
"""
|
||||
Enterprise SEO Command Center
|
||||
|
||||
Unified AI-powered SEO suite that orchestrates all existing tools into
|
||||
intelligent workflows for enterprise-level SEO management.
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import asyncio
|
||||
import pandas as pd
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
from datetime import datetime, timedelta
|
||||
import json
|
||||
from loguru import logger
|
||||
|
||||
# Import existing SEO tools
|
||||
from .on_page_seo_analyzer import fetch_seo_data
|
||||
from .content_gap_analysis.enhanced_analyzer import EnhancedContentGapAnalyzer
|
||||
from .technical_seo_crawler.crawler import TechnicalSEOCrawler
|
||||
from .weburl_seo_checker import url_seo_checker
|
||||
from .google_pagespeed_insights import google_pagespeed_insights
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
# Import the new enterprise tools
|
||||
from .google_search_console_integration import GoogleSearchConsoleAnalyzer, render_gsc_integration
|
||||
from .ai_content_strategy import AIContentStrategyGenerator, render_ai_content_strategy
|
||||
|
||||
class EnterpriseSEOSuite:
|
||||
"""
|
||||
Enterprise-level SEO suite orchestrating all tools into intelligent workflows.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the enterprise SEO suite."""
|
||||
self.gap_analyzer = EnhancedContentGapAnalyzer()
|
||||
self.technical_crawler = TechnicalSEOCrawler()
|
||||
|
||||
# Initialize new enterprise tools
|
||||
self.gsc_analyzer = GoogleSearchConsoleAnalyzer()
|
||||
self.content_strategy_generator = AIContentStrategyGenerator()
|
||||
|
||||
# SEO workflow templates
|
||||
self.workflow_templates = {
|
||||
'complete_audit': 'Complete SEO Audit',
|
||||
'content_strategy': 'Content Strategy Development',
|
||||
'technical_optimization': 'Technical SEO Optimization',
|
||||
'competitor_intelligence': 'Competitive Intelligence',
|
||||
'keyword_domination': 'Keyword Domination Strategy',
|
||||
'local_seo': 'Local SEO Optimization',
|
||||
'enterprise_monitoring': 'Enterprise SEO Monitoring'
|
||||
}
|
||||
|
||||
logger.info("Enterprise SEO Suite initialized")
|
||||
|
||||
async def execute_complete_seo_audit(self, website_url: str, competitors: List[str],
|
||||
target_keywords: List[str]) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute a comprehensive enterprise SEO audit combining all tools.
|
||||
|
||||
Args:
|
||||
website_url: Primary website to audit
|
||||
competitors: List of competitor URLs (max 5)
|
||||
target_keywords: Primary keywords to optimize for
|
||||
|
||||
Returns:
|
||||
Comprehensive audit results with prioritized action plan
|
||||
"""
|
||||
try:
|
||||
st.info("🚀 Initiating Complete Enterprise SEO Audit...")
|
||||
|
||||
audit_results = {
|
||||
'audit_timestamp': datetime.utcnow().isoformat(),
|
||||
'website_url': website_url,
|
||||
'competitors': competitors[:5],
|
||||
'target_keywords': target_keywords,
|
||||
'technical_audit': {},
|
||||
'content_analysis': {},
|
||||
'competitive_intelligence': {},
|
||||
'on_page_analysis': {},
|
||||
'performance_metrics': {},
|
||||
'strategic_recommendations': {},
|
||||
'priority_action_plan': []
|
||||
}
|
||||
|
||||
# Phase 1: Technical SEO Audit
|
||||
with st.expander("🔧 Technical SEO Analysis", expanded=True):
|
||||
st.info("Analyzing technical SEO factors...")
|
||||
technical_results = await self._run_technical_audit(website_url)
|
||||
audit_results['technical_audit'] = technical_results
|
||||
st.success("✅ Technical audit completed")
|
||||
|
||||
# Phase 2: Content Gap Analysis
|
||||
with st.expander("📊 Content Intelligence Analysis", expanded=True):
|
||||
st.info("Analyzing content gaps and opportunities...")
|
||||
content_results = await self._run_content_analysis(
|
||||
website_url, competitors, target_keywords
|
||||
)
|
||||
audit_results['content_analysis'] = content_results
|
||||
st.success("✅ Content analysis completed")
|
||||
|
||||
# Phase 3: On-Page SEO Analysis
|
||||
with st.expander("🔍 On-Page SEO Analysis", expanded=True):
|
||||
st.info("Analyzing on-page SEO factors...")
|
||||
onpage_results = await self._run_onpage_analysis(website_url)
|
||||
audit_results['on_page_analysis'] = onpage_results
|
||||
st.success("✅ On-page analysis completed")
|
||||
|
||||
# Phase 4: Performance Analysis
|
||||
with st.expander("⚡ Performance Analysis", expanded=True):
|
||||
st.info("Analyzing website performance...")
|
||||
performance_results = await self._run_performance_analysis(website_url)
|
||||
audit_results['performance_metrics'] = performance_results
|
||||
st.success("✅ Performance analysis completed")
|
||||
|
||||
# Phase 5: AI-Powered Strategic Recommendations
|
||||
with st.expander("🤖 AI Strategic Analysis", expanded=True):
|
||||
st.info("Generating AI-powered strategic recommendations...")
|
||||
strategic_analysis = await self._generate_strategic_recommendations(audit_results)
|
||||
audit_results['strategic_recommendations'] = strategic_analysis
|
||||
|
||||
# Generate prioritized action plan
|
||||
action_plan = await self._create_priority_action_plan(audit_results)
|
||||
audit_results['priority_action_plan'] = action_plan
|
||||
st.success("✅ Strategic analysis completed")
|
||||
|
||||
return audit_results
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"Error in complete SEO audit: {str(e)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
st.error(error_msg)
|
||||
return {'error': error_msg}
|
||||
|
||||
async def _run_technical_audit(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Run comprehensive technical SEO audit."""
|
||||
try:
|
||||
# Use existing technical crawler
|
||||
technical_results = self.technical_crawler.analyze_website_technical_seo(
|
||||
website_url, crawl_depth=3, max_pages=100
|
||||
)
|
||||
|
||||
# Enhance with additional technical checks
|
||||
enhanced_results = {
|
||||
'crawler_results': technical_results,
|
||||
'critical_issues': self._identify_critical_technical_issues(technical_results),
|
||||
'performance_score': self._calculate_technical_score(technical_results),
|
||||
'priority_fixes': self._prioritize_technical_fixes(technical_results)
|
||||
}
|
||||
|
||||
return enhanced_results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Technical audit error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
async def _run_content_analysis(self, website_url: str, competitors: List[str],
|
||||
keywords: List[str]) -> Dict[str, Any]:
|
||||
"""Run comprehensive content gap analysis."""
|
||||
try:
|
||||
# Use existing content gap analyzer
|
||||
content_results = self.gap_analyzer.analyze_comprehensive_gap(
|
||||
website_url, competitors, keywords, industry="general"
|
||||
)
|
||||
|
||||
# Enhance with content strategy insights
|
||||
enhanced_results = {
|
||||
'gap_analysis': content_results,
|
||||
'content_opportunities': self._identify_content_opportunities(content_results),
|
||||
'keyword_strategy': self._develop_keyword_strategy(content_results),
|
||||
'competitive_advantages': self._find_competitive_advantages(content_results)
|
||||
}
|
||||
|
||||
return enhanced_results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Content analysis error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
async def _run_onpage_analysis(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Run on-page SEO analysis."""
|
||||
try:
|
||||
# Use existing on-page analyzer
|
||||
onpage_data = fetch_seo_data(website_url)
|
||||
|
||||
# Enhanced analysis
|
||||
enhanced_results = {
|
||||
'seo_data': onpage_data,
|
||||
'optimization_score': self._calculate_onpage_score(onpage_data),
|
||||
'meta_optimization': self._analyze_meta_optimization(onpage_data),
|
||||
'content_optimization': self._analyze_content_optimization(onpage_data)
|
||||
}
|
||||
|
||||
return enhanced_results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"On-page analysis error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
async def _run_performance_analysis(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Run website performance analysis."""
|
||||
try:
|
||||
# Comprehensive performance metrics
|
||||
performance_results = {
|
||||
'core_web_vitals': await self._analyze_core_web_vitals(website_url),
|
||||
'loading_performance': await self._analyze_loading_performance(website_url),
|
||||
'mobile_optimization': await self._analyze_mobile_optimization(website_url),
|
||||
'performance_score': 0 # Will be calculated
|
||||
}
|
||||
|
||||
# Calculate overall performance score
|
||||
performance_results['performance_score'] = self._calculate_performance_score(
|
||||
performance_results
|
||||
)
|
||||
|
||||
return performance_results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Performance analysis error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
async def _generate_strategic_recommendations(self, audit_results: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Generate AI-powered strategic recommendations."""
|
||||
try:
|
||||
# Compile audit summary for AI analysis
|
||||
audit_summary = {
|
||||
'technical_score': audit_results.get('technical_audit', {}).get('performance_score', 0),
|
||||
'content_gaps': len(audit_results.get('content_analysis', {}).get('content_opportunities', [])),
|
||||
'onpage_score': audit_results.get('on_page_analysis', {}).get('optimization_score', 0),
|
||||
'performance_score': audit_results.get('performance_metrics', {}).get('performance_score', 0)
|
||||
}
|
||||
|
||||
strategic_prompt = f"""
|
||||
Analyze this comprehensive SEO audit and provide strategic recommendations:
|
||||
|
||||
AUDIT SUMMARY:
|
||||
- Technical SEO Score: {audit_summary['technical_score']}/100
|
||||
- Content Gaps Identified: {audit_summary['content_gaps']}
|
||||
- On-Page SEO Score: {audit_summary['onpage_score']}/100
|
||||
- Performance Score: {audit_summary['performance_score']}/100
|
||||
|
||||
DETAILED FINDINGS:
|
||||
Technical Issues: {json.dumps(audit_results.get('technical_audit', {}), indent=2)[:1000]}
|
||||
Content Opportunities: {json.dumps(audit_results.get('content_analysis', {}), indent=2)[:1000]}
|
||||
|
||||
Provide strategic recommendations in these categories:
|
||||
|
||||
1. IMMEDIATE WINS (0-30 days):
|
||||
- Quick technical fixes with high impact
|
||||
- Content optimizations for existing pages
|
||||
- Critical performance improvements
|
||||
|
||||
2. STRATEGIC INITIATIVES (1-3 months):
|
||||
- Content strategy development
|
||||
- Technical architecture improvements
|
||||
- Competitive positioning strategies
|
||||
|
||||
3. LONG-TERM GROWTH (3-12 months):
|
||||
- Authority building strategies
|
||||
- Market expansion opportunities
|
||||
- Advanced SEO techniques
|
||||
|
||||
4. RISK MITIGATION:
|
||||
- Technical vulnerabilities to address
|
||||
- Content gaps that competitors could exploit
|
||||
- Performance issues affecting user experience
|
||||
|
||||
Provide specific, actionable recommendations with expected impact and effort estimates.
|
||||
"""
|
||||
|
||||
strategic_analysis = llm_text_gen(
|
||||
strategic_prompt,
|
||||
system_prompt="You are an enterprise SEO strategist with 10+ years of experience. Provide detailed, actionable recommendations based on comprehensive audit data."
|
||||
)
|
||||
|
||||
return {
|
||||
'full_analysis': strategic_analysis,
|
||||
'immediate_wins': self._extract_immediate_wins(strategic_analysis),
|
||||
'strategic_initiatives': self._extract_strategic_initiatives(strategic_analysis),
|
||||
'long_term_growth': self._extract_long_term_growth(strategic_analysis),
|
||||
'risk_mitigation': self._extract_risk_mitigation(strategic_analysis)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Strategic analysis error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
async def _create_priority_action_plan(self, audit_results: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""Create prioritized action plan from audit results."""
|
||||
try:
|
||||
action_plan = []
|
||||
|
||||
# Extract recommendations from all analysis phases
|
||||
strategic_recs = audit_results.get('strategic_recommendations', {})
|
||||
|
||||
# Immediate wins (High priority, low effort)
|
||||
immediate_wins = strategic_recs.get('immediate_wins', [])
|
||||
for win in immediate_wins[:5]:
|
||||
action_plan.append({
|
||||
'category': 'Immediate Win',
|
||||
'priority': 'Critical',
|
||||
'effort': 'Low',
|
||||
'timeframe': '0-30 days',
|
||||
'action': win,
|
||||
'expected_impact': 'High',
|
||||
'source': 'Strategic Analysis'
|
||||
})
|
||||
|
||||
# Technical fixes
|
||||
technical_issues = audit_results.get('technical_audit', {}).get('critical_issues', [])
|
||||
for issue in technical_issues[:3]:
|
||||
action_plan.append({
|
||||
'category': 'Technical SEO',
|
||||
'priority': 'High',
|
||||
'effort': 'Medium',
|
||||
'timeframe': '1-4 weeks',
|
||||
'action': issue,
|
||||
'expected_impact': 'High',
|
||||
'source': 'Technical Audit'
|
||||
})
|
||||
|
||||
# Content opportunities
|
||||
content_ops = audit_results.get('content_analysis', {}).get('content_opportunities', [])
|
||||
for opportunity in content_ops[:3]:
|
||||
action_plan.append({
|
||||
'category': 'Content Strategy',
|
||||
'priority': 'Medium',
|
||||
'effort': 'High',
|
||||
'timeframe': '2-8 weeks',
|
||||
'action': opportunity,
|
||||
'expected_impact': 'Medium',
|
||||
'source': 'Content Analysis'
|
||||
})
|
||||
|
||||
# Sort by priority and expected impact
|
||||
priority_order = {'Critical': 0, 'High': 1, 'Medium': 2, 'Low': 3}
|
||||
action_plan.sort(key=lambda x: priority_order.get(x['priority'], 4))
|
||||
|
||||
return action_plan[:15] # Top 15 actions
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Action plan creation error: {str(e)}")
|
||||
return []
|
||||
|
||||
# Utility methods for analysis
|
||||
def _identify_critical_technical_issues(self, technical_results: Dict[str, Any]) -> List[str]:
|
||||
"""Identify critical technical SEO issues."""
|
||||
critical_issues = []
|
||||
|
||||
# Add logic to identify critical technical issues
|
||||
# This would analyze the technical_results and extract critical problems
|
||||
|
||||
return critical_issues
|
||||
|
||||
def _calculate_technical_score(self, technical_results: Dict[str, Any]) -> int:
|
||||
"""Calculate technical SEO score."""
|
||||
# Implement scoring algorithm based on technical audit results
|
||||
return 75 # Placeholder
|
||||
|
||||
def _prioritize_technical_fixes(self, technical_results: Dict[str, Any]) -> List[str]:
|
||||
"""Prioritize technical fixes by impact and effort."""
|
||||
# Implement prioritization logic
|
||||
return ["Fix broken links", "Optimize images", "Improve page speed"]
|
||||
|
||||
def _identify_content_opportunities(self, content_results: Dict[str, Any]) -> List[str]:
|
||||
"""Identify top content opportunities."""
|
||||
# Extract content opportunities from gap analysis
|
||||
return ["Create FAQ content", "Develop comparison guides", "Write how-to articles"]
|
||||
|
||||
def _develop_keyword_strategy(self, content_results: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Develop keyword strategy from content analysis."""
|
||||
return {
|
||||
'primary_keywords': [],
|
||||
'secondary_keywords': [],
|
||||
'long_tail_opportunities': [],
|
||||
'competitor_gaps': []
|
||||
}
|
||||
|
||||
def _find_competitive_advantages(self, content_results: Dict[str, Any]) -> List[str]:
|
||||
"""Find competitive advantages from analysis."""
|
||||
return ["Unique content angles", "Underserved niches", "Technical superiority"]
|
||||
|
||||
def _calculate_onpage_score(self, onpage_data: Dict[str, Any]) -> int:
|
||||
"""Calculate on-page SEO score."""
|
||||
return 80 # Placeholder
|
||||
|
||||
def _analyze_meta_optimization(self, onpage_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze meta tag optimization."""
|
||||
return {'title_optimization': 'good', 'description_optimization': 'needs_work'}
|
||||
|
||||
def _analyze_content_optimization(self, onpage_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze content optimization."""
|
||||
return {'keyword_density': 'optimal', 'content_length': 'adequate'}
|
||||
|
||||
async def _analyze_core_web_vitals(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Analyze Core Web Vitals."""
|
||||
return {'lcp': 2.5, 'fid': 100, 'cls': 0.1}
|
||||
|
||||
async def _analyze_loading_performance(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Analyze loading performance."""
|
||||
return {'ttfb': 200, 'fcp': 1.5, 'speed_index': 3.0}
|
||||
|
||||
async def _analyze_mobile_optimization(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Analyze mobile optimization."""
|
||||
return {'mobile_friendly': True, 'responsive_design': True}
|
||||
|
||||
def _calculate_performance_score(self, performance_results: Dict[str, Any]) -> int:
|
||||
"""Calculate overall performance score."""
|
||||
return 85 # Placeholder
|
||||
|
||||
def _extract_immediate_wins(self, analysis: str) -> List[str]:
|
||||
"""Extract immediate wins from strategic analysis."""
|
||||
# Parse the AI analysis and extract immediate wins
|
||||
lines = analysis.split('\n')
|
||||
wins = []
|
||||
in_immediate_section = False
|
||||
|
||||
for line in lines:
|
||||
if 'IMMEDIATE WINS' in line.upper():
|
||||
in_immediate_section = True
|
||||
continue
|
||||
elif 'STRATEGIC INITIATIVES' in line.upper():
|
||||
in_immediate_section = False
|
||||
continue
|
||||
|
||||
if in_immediate_section and line.strip().startswith('-'):
|
||||
wins.append(line.strip().lstrip('- '))
|
||||
|
||||
return wins[:5]
|
||||
|
||||
def _extract_strategic_initiatives(self, analysis: str) -> List[str]:
|
||||
"""Extract strategic initiatives from analysis."""
|
||||
# Similar extraction logic for strategic initiatives
|
||||
return ["Develop content hub", "Implement schema markup", "Build authority pages"]
|
||||
|
||||
def _extract_long_term_growth(self, analysis: str) -> List[str]:
|
||||
"""Extract long-term growth strategies."""
|
||||
return ["Market expansion", "Authority building", "Advanced technical SEO"]
|
||||
|
||||
def _extract_risk_mitigation(self, analysis: str) -> List[str]:
|
||||
"""Extract risk mitigation strategies."""
|
||||
return ["Fix technical vulnerabilities", "Address content gaps", "Improve performance"]
|
||||
|
||||
def execute_content_strategy_workflow(self, business_info: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute comprehensive content strategy workflow using AI insights.
|
||||
|
||||
Args:
|
||||
business_info: Business context and objectives
|
||||
|
||||
Returns:
|
||||
Complete content strategy with implementation plan
|
||||
"""
|
||||
try:
|
||||
st.info("🧠 Executing AI-powered content strategy workflow...")
|
||||
|
||||
# Generate AI content strategy
|
||||
content_strategy = self.content_strategy_generator.generate_content_strategy(business_info)
|
||||
|
||||
# If GSC data is available, enhance with search insights
|
||||
if business_info.get('gsc_site_url'):
|
||||
gsc_insights = self.gsc_analyzer.analyze_search_performance(
|
||||
business_info['gsc_site_url'],
|
||||
business_info.get('gsc_date_range', 90)
|
||||
)
|
||||
content_strategy['gsc_insights'] = gsc_insights
|
||||
|
||||
# Generate SEO-optimized content recommendations
|
||||
seo_content_recs = self._generate_seo_content_recommendations(content_strategy)
|
||||
content_strategy['seo_recommendations'] = seo_content_recs
|
||||
|
||||
return content_strategy
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Content strategy workflow error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def execute_search_intelligence_workflow(self, site_url: str, date_range: int = 90) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute comprehensive search intelligence workflow using GSC data.
|
||||
|
||||
Args:
|
||||
site_url: Website URL registered in GSC
|
||||
date_range: Analysis period in days
|
||||
|
||||
Returns:
|
||||
Complete search intelligence analysis with actionable insights
|
||||
"""
|
||||
try:
|
||||
st.info("📊 Executing search intelligence workflow...")
|
||||
|
||||
# Analyze GSC performance
|
||||
gsc_analysis = self.gsc_analyzer.analyze_search_performance(site_url, date_range)
|
||||
|
||||
# Enhance with technical SEO analysis
|
||||
technical_analysis = self.technical_crawler.crawl_and_analyze(site_url)
|
||||
gsc_analysis['technical_insights'] = technical_analysis
|
||||
|
||||
# Generate content gap analysis based on GSC keywords
|
||||
if gsc_analysis.get('keyword_analysis'):
|
||||
keywords = [kw['keyword'] for kw in gsc_analysis['keyword_analysis'].get('high_volume_keywords', [])]
|
||||
content_gaps = self.gap_analyzer.analyze_content_gaps(
|
||||
keywords[:10], # Top 10 keywords
|
||||
site_url
|
||||
)
|
||||
gsc_analysis['content_gap_analysis'] = content_gaps
|
||||
|
||||
# Generate comprehensive recommendations
|
||||
search_recommendations = self._generate_search_intelligence_recommendations(gsc_analysis)
|
||||
gsc_analysis['comprehensive_recommendations'] = search_recommendations
|
||||
|
||||
return gsc_analysis
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Search intelligence workflow error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def _generate_seo_content_recommendations(self, content_strategy: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Generate SEO-optimized content recommendations based on strategy."""
|
||||
try:
|
||||
content_pillars = content_strategy.get('content_pillars', [])
|
||||
|
||||
seo_recommendations = {
|
||||
'keyword_optimization': [],
|
||||
'content_structure': [],
|
||||
'internal_linking': [],
|
||||
'technical_seo': []
|
||||
}
|
||||
|
||||
for pillar in content_pillars:
|
||||
# Keyword optimization recommendations
|
||||
for keyword in pillar.get('target_keywords', []):
|
||||
seo_recommendations['keyword_optimization'].append({
|
||||
'pillar': pillar['name'],
|
||||
'keyword': keyword,
|
||||
'recommendation': f"Create comprehensive content targeting '{keyword}' with semantic variations",
|
||||
'priority': 'High' if keyword in pillar['target_keywords'][:2] else 'Medium'
|
||||
})
|
||||
|
||||
# Content structure recommendations
|
||||
seo_recommendations['content_structure'].append({
|
||||
'pillar': pillar['name'],
|
||||
'recommendation': f"Create pillar page for {pillar['name']} with supporting cluster content",
|
||||
'structure': 'Pillar + Cluster model'
|
||||
})
|
||||
|
||||
# Internal linking strategy
|
||||
seo_recommendations['internal_linking'] = [
|
||||
"Link all cluster content to relevant pillar pages",
|
||||
"Create topic-based internal linking structure",
|
||||
"Use contextual anchor text with target keywords",
|
||||
"Implement breadcrumb navigation for topic clusters"
|
||||
]
|
||||
|
||||
# Technical SEO recommendations
|
||||
seo_recommendations['technical_seo'] = [
|
||||
"Optimize page speed for all content pages",
|
||||
"Implement structured data for articles",
|
||||
"Create XML sitemap sections for content categories",
|
||||
"Optimize images with descriptive alt text"
|
||||
]
|
||||
|
||||
return seo_recommendations
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"SEO content recommendations error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def _generate_search_intelligence_recommendations(self, gsc_analysis: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Generate comprehensive recommendations from search intelligence analysis."""
|
||||
try:
|
||||
recommendations = {
|
||||
'immediate_actions': [],
|
||||
'content_opportunities': [],
|
||||
'technical_improvements': [],
|
||||
'strategic_initiatives': []
|
||||
}
|
||||
|
||||
# Extract content opportunities from GSC analysis
|
||||
content_opps = gsc_analysis.get('content_opportunities', [])
|
||||
for opp in content_opps[:5]: # Top 5 opportunities
|
||||
recommendations['content_opportunities'].append({
|
||||
'type': opp['type'],
|
||||
'keyword': opp['keyword'],
|
||||
'action': opp['opportunity'],
|
||||
'priority': opp['priority'],
|
||||
'estimated_impact': opp['potential_impact']
|
||||
})
|
||||
|
||||
# Technical improvements from analysis
|
||||
technical_insights = gsc_analysis.get('technical_insights', {})
|
||||
if technical_insights.get('crawl_issues_indicators'):
|
||||
for issue in technical_insights['crawl_issues_indicators']:
|
||||
recommendations['technical_improvements'].append({
|
||||
'issue': issue,
|
||||
'priority': 'High',
|
||||
'category': 'Crawl & Indexing'
|
||||
})
|
||||
|
||||
# Immediate actions based on performance
|
||||
performance = gsc_analysis.get('performance_overview', {})
|
||||
if performance.get('avg_ctr', 0) < 2:
|
||||
recommendations['immediate_actions'].append({
|
||||
'action': 'Improve meta descriptions and titles for better CTR',
|
||||
'expected_impact': 'Increase CTR by 1-2%',
|
||||
'timeline': '2-4 weeks'
|
||||
})
|
||||
|
||||
if performance.get('avg_position', 0) > 10:
|
||||
recommendations['immediate_actions'].append({
|
||||
'action': 'Focus on improving content quality for top keywords',
|
||||
'expected_impact': 'Improve average position by 2-5 ranks',
|
||||
'timeline': '4-8 weeks'
|
||||
})
|
||||
|
||||
# Strategic initiatives
|
||||
competitive_analysis = gsc_analysis.get('competitive_analysis', {})
|
||||
if competitive_analysis.get('market_position') in ['Challenger', 'Emerging Player']:
|
||||
recommendations['strategic_initiatives'].append({
|
||||
'initiative': 'Develop thought leadership content strategy',
|
||||
'goal': 'Improve market position and brand authority',
|
||||
'timeline': '3-6 months'
|
||||
})
|
||||
|
||||
return recommendations
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Search intelligence recommendations error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def render_enterprise_seo_suite():
|
||||
"""Render the Enterprise SEO Command Center interface."""
|
||||
|
||||
st.set_page_config(
|
||||
page_title="Enterprise SEO Command Center",
|
||||
page_icon="🚀",
|
||||
layout="wide"
|
||||
)
|
||||
|
||||
st.title("🚀 Enterprise SEO Command Center")
|
||||
st.markdown("**Unified AI-powered SEO suite orchestrating all tools into intelligent workflows**")
|
||||
|
||||
# Initialize suite
|
||||
if 'enterprise_seo_suite' not in st.session_state:
|
||||
st.session_state.enterprise_seo_suite = EnterpriseSEOSuite()
|
||||
|
||||
suite = st.session_state.enterprise_seo_suite
|
||||
|
||||
# Workflow selection
|
||||
st.sidebar.header("🎯 SEO Workflow Selection")
|
||||
selected_workflow = st.sidebar.selectbox(
|
||||
"Choose Workflow",
|
||||
list(suite.workflow_templates.keys()),
|
||||
format_func=lambda x: suite.workflow_templates[x]
|
||||
)
|
||||
|
||||
# Main workflow interface
|
||||
if selected_workflow == 'complete_audit':
|
||||
st.header("🔍 Complete Enterprise SEO Audit")
|
||||
render_complete_audit_interface(suite)
|
||||
elif selected_workflow == 'content_strategy':
|
||||
st.header("📊 Content Strategy Development")
|
||||
render_content_strategy_interface(suite)
|
||||
elif selected_workflow == 'technical_optimization':
|
||||
st.header("🔧 Technical SEO Optimization")
|
||||
render_technical_optimization_interface(suite)
|
||||
else:
|
||||
st.info(f"Workflow '{suite.workflow_templates[selected_workflow]}' is being developed.")
|
||||
|
||||
def render_complete_audit_interface(suite: EnterpriseSEOSuite):
|
||||
"""Render the complete audit workflow interface."""
|
||||
|
||||
# Input form
|
||||
with st.form("enterprise_audit_form"):
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
website_url = st.text_input(
|
||||
"Website URL",
|
||||
value="https://example.com",
|
||||
help="Enter your website URL for comprehensive analysis"
|
||||
)
|
||||
|
||||
target_keywords = st.text_area(
|
||||
"Target Keywords (one per line)",
|
||||
value="AI content creation\nSEO tools\ncontent optimization",
|
||||
help="Enter your primary keywords to optimize for"
|
||||
)
|
||||
|
||||
with col2:
|
||||
competitors = st.text_area(
|
||||
"Competitor URLs (one per line)",
|
||||
value="https://jasper.ai\nhttps://copy.ai\nhttps://writesonic.com",
|
||||
help="Enter up to 5 competitor URLs for analysis"
|
||||
)
|
||||
|
||||
submit_audit = st.form_submit_button("🚀 Start Complete SEO Audit", type="primary")
|
||||
|
||||
# Process audit
|
||||
if submit_audit:
|
||||
if website_url and target_keywords:
|
||||
# Parse inputs
|
||||
keywords_list = [k.strip() for k in target_keywords.split('\n') if k.strip()]
|
||||
competitors_list = [c.strip() for c in competitors.split('\n') if c.strip()]
|
||||
|
||||
# Run audit
|
||||
with st.spinner("🔍 Running comprehensive SEO audit..."):
|
||||
audit_results = asyncio.run(
|
||||
suite.execute_complete_seo_audit(
|
||||
website_url, competitors_list, keywords_list
|
||||
)
|
||||
)
|
||||
|
||||
if 'error' not in audit_results:
|
||||
st.success("✅ Enterprise SEO audit completed!")
|
||||
|
||||
# Display results dashboard
|
||||
render_audit_results_dashboard(audit_results)
|
||||
else:
|
||||
st.error(f"❌ Audit failed: {audit_results['error']}")
|
||||
else:
|
||||
st.warning("⚠️ Please enter website URL and target keywords.")
|
||||
|
||||
def render_audit_results_dashboard(results: Dict[str, Any]):
|
||||
"""Render comprehensive audit results dashboard."""
|
||||
|
||||
# Priority Action Plan (Most Important)
|
||||
st.header("📋 Priority Action Plan")
|
||||
action_plan = results.get('priority_action_plan', [])
|
||||
|
||||
if action_plan:
|
||||
# Display as interactive table
|
||||
df_actions = pd.DataFrame(action_plan)
|
||||
|
||||
# Style the dataframe
|
||||
st.dataframe(
|
||||
df_actions,
|
||||
column_config={
|
||||
"category": "Category",
|
||||
"priority": st.column_config.SelectboxColumn(
|
||||
"Priority",
|
||||
options=["Critical", "High", "Medium", "Low"]
|
||||
),
|
||||
"effort": "Effort Level",
|
||||
"timeframe": "Timeline",
|
||||
"action": "Action Required",
|
||||
"expected_impact": "Expected Impact"
|
||||
},
|
||||
hide_index=True,
|
||||
use_container_width=True
|
||||
)
|
||||
|
||||
# Key Metrics Overview
|
||||
st.header("📊 SEO Health Dashboard")
|
||||
|
||||
col1, col2, col3, col4 = st.columns(4)
|
||||
|
||||
with col1:
|
||||
technical_score = results.get('technical_audit', {}).get('performance_score', 0)
|
||||
st.metric("Technical SEO", f"{technical_score}/100", delta=None)
|
||||
|
||||
with col2:
|
||||
onpage_score = results.get('on_page_analysis', {}).get('optimization_score', 0)
|
||||
st.metric("On-Page SEO", f"{onpage_score}/100", delta=None)
|
||||
|
||||
with col3:
|
||||
performance_score = results.get('performance_metrics', {}).get('performance_score', 0)
|
||||
st.metric("Performance", f"{performance_score}/100", delta=None)
|
||||
|
||||
with col4:
|
||||
content_gaps = len(results.get('content_analysis', {}).get('content_opportunities', []))
|
||||
st.metric("Content Opportunities", content_gaps, delta=None)
|
||||
|
||||
# Detailed Analysis Sections
|
||||
tab1, tab2, tab3, tab4, tab5 = st.tabs([
|
||||
"🤖 Strategic Insights",
|
||||
"🔧 Technical Analysis",
|
||||
"📊 Content Intelligence",
|
||||
"🔍 On-Page Analysis",
|
||||
"⚡ Performance Metrics"
|
||||
])
|
||||
|
||||
with tab1:
|
||||
strategic_recs = results.get('strategic_recommendations', {})
|
||||
if strategic_recs:
|
||||
st.subheader("AI-Powered Strategic Recommendations")
|
||||
|
||||
# Immediate wins
|
||||
immediate_wins = strategic_recs.get('immediate_wins', [])
|
||||
if immediate_wins:
|
||||
st.markdown("#### 🚀 Immediate Wins (0-30 days)")
|
||||
for win in immediate_wins[:5]:
|
||||
st.success(f"✅ {win}")
|
||||
|
||||
# Strategic initiatives
|
||||
strategic_initiatives = strategic_recs.get('strategic_initiatives', [])
|
||||
if strategic_initiatives:
|
||||
st.markdown("#### 📈 Strategic Initiatives (1-3 months)")
|
||||
for initiative in strategic_initiatives[:3]:
|
||||
st.info(f"📋 {initiative}")
|
||||
|
||||
# Full analysis
|
||||
full_analysis = strategic_recs.get('full_analysis', '')
|
||||
if full_analysis:
|
||||
with st.expander("🧠 Complete Strategic Analysis"):
|
||||
st.write(full_analysis)
|
||||
|
||||
with tab2:
|
||||
technical_audit = results.get('technical_audit', {})
|
||||
if technical_audit:
|
||||
st.subheader("Technical SEO Analysis")
|
||||
|
||||
critical_issues = technical_audit.get('critical_issues', [])
|
||||
if critical_issues:
|
||||
st.markdown("#### ⚠️ Critical Issues")
|
||||
for issue in critical_issues:
|
||||
st.error(f"🚨 {issue}")
|
||||
|
||||
priority_fixes = technical_audit.get('priority_fixes', [])
|
||||
if priority_fixes:
|
||||
st.markdown("#### 🔧 Priority Fixes")
|
||||
for fix in priority_fixes:
|
||||
st.warning(f"🛠️ {fix}")
|
||||
|
||||
with tab3:
|
||||
content_analysis = results.get('content_analysis', {})
|
||||
if content_analysis:
|
||||
st.subheader("Content Intelligence")
|
||||
|
||||
content_opportunities = content_analysis.get('content_opportunities', [])
|
||||
if content_opportunities:
|
||||
st.markdown("#### 📝 Content Opportunities")
|
||||
for opportunity in content_opportunities[:5]:
|
||||
st.info(f"💡 {opportunity}")
|
||||
|
||||
competitive_advantages = content_analysis.get('competitive_advantages', [])
|
||||
if competitive_advantages:
|
||||
st.markdown("#### 🏆 Competitive Advantages")
|
||||
for advantage in competitive_advantages:
|
||||
st.success(f"⭐ {advantage}")
|
||||
|
||||
with tab4:
|
||||
onpage_analysis = results.get('on_page_analysis', {})
|
||||
if onpage_analysis:
|
||||
st.subheader("On-Page SEO Analysis")
|
||||
|
||||
meta_optimization = onpage_analysis.get('meta_optimization', {})
|
||||
content_optimization = onpage_analysis.get('content_optimization', {})
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
st.markdown("#### 🏷️ Meta Tag Optimization")
|
||||
st.json(meta_optimization)
|
||||
|
||||
with col2:
|
||||
st.markdown("#### 📄 Content Optimization")
|
||||
st.json(content_optimization)
|
||||
|
||||
with tab5:
|
||||
performance_metrics = results.get('performance_metrics', {})
|
||||
if performance_metrics:
|
||||
st.subheader("Performance Analysis")
|
||||
|
||||
core_vitals = performance_metrics.get('core_web_vitals', {})
|
||||
loading_performance = performance_metrics.get('loading_performance', {})
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
st.markdown("#### ⚡ Core Web Vitals")
|
||||
st.json(core_vitals)
|
||||
|
||||
with col2:
|
||||
st.markdown("#### 🚀 Loading Performance")
|
||||
st.json(loading_performance)
|
||||
|
||||
# Export functionality
|
||||
st.markdown("---")
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
if st.button("📥 Export Full Report", use_container_width=True):
|
||||
# Create downloadable report
|
||||
report_json = json.dumps(results, indent=2, default=str)
|
||||
st.download_button(
|
||||
label="Download JSON Report",
|
||||
data=report_json,
|
||||
file_name=f"seo_audit_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
||||
mime="application/json"
|
||||
)
|
||||
|
||||
with col2:
|
||||
if st.button("📊 Export Action Plan", use_container_width=True):
|
||||
# Create CSV of action plan
|
||||
df_actions = pd.DataFrame(action_plan)
|
||||
csv = df_actions.to_csv(index=False)
|
||||
st.download_button(
|
||||
label="Download CSV Action Plan",
|
||||
data=csv,
|
||||
file_name=f"action_plan_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
|
||||
mime="text/csv"
|
||||
)
|
||||
|
||||
with col3:
|
||||
if st.button("🔄 Schedule Follow-up Audit", use_container_width=True):
|
||||
st.info("Follow-up scheduling feature coming soon!")
|
||||
|
||||
def render_content_strategy_interface(suite: EnterpriseSEOSuite):
|
||||
"""Render content strategy development interface."""
|
||||
st.info("🚧 Content Strategy Development workflow coming soon!")
|
||||
|
||||
def render_technical_optimization_interface(suite: EnterpriseSEOSuite):
|
||||
"""Render technical optimization interface."""
|
||||
st.info("🚧 Technical SEO Optimization workflow coming soon!")
|
||||
|
||||
|
||||
# Main execution
|
||||
if __name__ == "__main__":
|
||||
render_enterprise_seo_suite()
|
||||
135
ToBeMigrated/ai_seo_tools/google_pagespeed_insights.py
Normal file
135
ToBeMigrated/ai_seo_tools/google_pagespeed_insights.py
Normal file
@@ -0,0 +1,135 @@
|
||||
import requests
|
||||
import streamlit as st
|
||||
import json
|
||||
import pandas as pd
|
||||
import plotly.express as px
|
||||
from tenacity import retry, stop_after_attempt, wait_random_exponential
|
||||
from datetime import datetime
|
||||
|
||||
def run_pagespeed(url, api_key=None, strategy='DESKTOP', locale='en'):
|
||||
"""Fetches and processes PageSpeed Insights data."""
|
||||
serviceurl = 'https://www.googleapis.com/pagespeedonline/v5/runPagespeed'
|
||||
base_url = f"{serviceurl}?url={url}&strategy={strategy}&locale={locale}&category=performance&category=accessibility&category=best-practices&category=seo"
|
||||
|
||||
if api_key:
|
||||
base_url += f"&key={api_key}"
|
||||
|
||||
try:
|
||||
response = requests.get(base_url)
|
||||
response.raise_for_status() # Raise an exception for bad status codes
|
||||
data = response.json()
|
||||
return data
|
||||
except requests.exceptions.RequestException as e:
|
||||
st.error(f"Error fetching PageSpeed Insights data: {e}")
|
||||
return None
|
||||
|
||||
def display_results(data):
|
||||
"""Presents PageSpeed Insights data in a user-friendly format."""
|
||||
st.subheader("PageSpeed Insights Report")
|
||||
|
||||
# Extract scores from the PageSpeed Insights data
|
||||
scores = {
|
||||
"Performance": data['lighthouseResult']['categories']['performance']['score'] * 100,
|
||||
"Accessibility": data['lighthouseResult']['categories']['accessibility']['score'] * 100,
|
||||
"SEO": data['lighthouseResult']['categories']['seo']['score'] * 100,
|
||||
"Best Practices": data['lighthouseResult']['categories']['best-practices']['score'] * 100
|
||||
}
|
||||
|
||||
descriptions = {
|
||||
"Performance": data['lighthouseResult']['categories']['performance'].get('description', "This score represents Google's assessment of your page's speed. A higher percentage indicates better performance."),
|
||||
"Accessibility": data['lighthouseResult']['categories']['accessibility'].get('description', "This score evaluates how accessible your page is to users with disabilities. A higher percentage means better accessibility."),
|
||||
"SEO": data['lighthouseResult']['categories']['seo'].get('description', "This score measures how well your page is optimized for search engines. A higher percentage indicates better SEO practices."),
|
||||
"Best Practices": data['lighthouseResult']['categories']['best-practices'].get('description', "This score reflects how well your page follows best practices for web development. A higher percentage signifies adherence to best practices.")
|
||||
}
|
||||
|
||||
for category, score in scores.items():
|
||||
st.metric(label=f"Overall {category} Score", value=f"{score:.0f}%", help=descriptions[category])
|
||||
|
||||
# Display additional metrics
|
||||
st.subheader("Additional Metrics")
|
||||
additional_metrics = {
|
||||
"First Contentful Paint (FCP)": data['lighthouseResult']['audits']['first-contentful-paint']['displayValue'],
|
||||
"Largest Contentful Paint (LCP)": data['lighthouseResult']['audits']['largest-contentful-paint']['displayValue'],
|
||||
"Time to Interactive (TTI)": data['lighthouseResult']['audits']['interactive']['displayValue'],
|
||||
"Total Blocking Time (TBT)": data['lighthouseResult']['audits']['total-blocking-time']['displayValue'],
|
||||
"Cumulative Layout Shift (CLS)": data['lighthouseResult']['audits']['cumulative-layout-shift']['displayValue']
|
||||
}
|
||||
|
||||
st.table(pd.DataFrame(additional_metrics.items(), columns=["Metric", "Value"]))
|
||||
|
||||
# Display Network Requests
|
||||
st.subheader("Network Requests")
|
||||
if 'network-requests' in data['lighthouseResult']['audits']:
|
||||
network_requests = [
|
||||
{
|
||||
"End Time": item.get("endTime", "N/A"),
|
||||
"Start Time": item.get("startTime", "N/A"),
|
||||
"Transfer Size (MB)": round(item.get("transferSize", 0) / 1048576, 2),
|
||||
"Resource Size (MB)": round(item.get("resourceSize", 0) / 1048576, 2),
|
||||
"URL": item.get("url", "N/A")
|
||||
}
|
||||
for item in data["lighthouseResult"]["audits"]["network-requests"]["details"]["items"]
|
||||
if item.get("transferSize", 0) > 100000 or item.get("resourceSize", 0) > 100000
|
||||
]
|
||||
if network_requests:
|
||||
st.dataframe(pd.DataFrame(network_requests), use_container_width=True)
|
||||
else:
|
||||
st.write("No significant network requests found.")
|
||||
|
||||
# Display Mainthread Work Breakdown
|
||||
st.subheader("Mainthread Work Breakdown")
|
||||
if 'mainthread-work-breakdown' in data['lighthouseResult']['audits']:
|
||||
mainthread_data = [
|
||||
{"Process": item.get("groupLabel", "N/A"), "Duration (ms)": item.get("duration", "N/A")}
|
||||
for item in data["lighthouseResult"]["audits"]["mainthread-work-breakdown"]["details"]["items"] if item.get("duration", "N/A") != "N/A"
|
||||
]
|
||||
if mainthread_data:
|
||||
fig = px.bar(pd.DataFrame(mainthread_data), x="Process", y="Duration (ms)", title="Mainthread Work Breakdown", labels={"Process": "Process", "Duration (ms)": "Duration (ms)"})
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
else:
|
||||
st.write("No significant main thread work breakdown data found.")
|
||||
|
||||
# Display other metrics
|
||||
metrics = [
|
||||
("Use of Passive Event Listeners", 'uses-passive-event-listeners', ["URL", "Code Line"]),
|
||||
("DOM Size", 'dom-size', ["Score", "DOM Size"]),
|
||||
("Offscreen Images", 'offscreen-images', ["URL", "Total Bytes", "Wasted Bytes", "Wasted Percentage"]),
|
||||
("Critical Request Chains", 'critical-request-chains', ["URL", "Start Time", "End Time", "Transfer Size", "Chain"]),
|
||||
("Total Bytes Weight", 'total-byte-weight', ["URL", "Total Bytes"]),
|
||||
("Render Blocking Resources", 'render-blocking-resources', ["URL", "Total Bytes", "Wasted Milliseconds"]),
|
||||
("Use of Rel Preload", 'uses-rel-preload', ["URL", "Wasted Milliseconds"])
|
||||
]
|
||||
|
||||
for metric_title, audit_key, columns in metrics:
|
||||
st.subheader(metric_title)
|
||||
if audit_key in data['lighthouseResult']['audits']:
|
||||
details = data['lighthouseResult']['audits'][audit_key].get("details", {}).get("items", [])
|
||||
if details:
|
||||
st.table(pd.DataFrame(details, columns=columns))
|
||||
else:
|
||||
st.write(f"No significant {metric_title.lower()} data found.")
|
||||
|
||||
def google_pagespeed_insights():
|
||||
st.markdown("<h1 style='text-align: center; color: #1565C0;'>PageSpeed Insights Analyzer</h1>", unsafe_allow_html=True)
|
||||
st.markdown("<h3 style='text-align: center;'>Get detailed insights into your website's performance! Powered by Google PageSpeed Insights <a href='https://developer.chrome.com/docs/lighthouse/overview/'>[Learn More]</a></h3>", unsafe_allow_html=True)
|
||||
|
||||
# User Input
|
||||
with st.form("pagespeed_form"):
|
||||
url = st.text_input("Enter Website URL", placeholder="https://www.example.com")
|
||||
api_key = st.text_input("Enter Google API Key (Optional)", placeholder="Your API Key", help="Get your API key here: [https://developers.google.com/speed/docs/insights/v5/get-started#key]")
|
||||
device = st.selectbox("Choose Device", ["Mobile", "Desktop"])
|
||||
locale = st.selectbox("Choose Locale", ["en", "fr", "es", "de", "ja"])
|
||||
categories = st.multiselect("Select Categories to Analyze", ['PERFORMANCE', 'ACCESSIBILITY', 'BEST_PRACTICES', 'SEO'], default=['PERFORMANCE', 'ACCESSIBILITY', 'BEST_PRACTICES', 'SEO'])
|
||||
|
||||
submitted = st.form_submit_button("Analyze")
|
||||
|
||||
if submitted:
|
||||
if not url:
|
||||
st.error("Please provide the website URL.")
|
||||
else:
|
||||
strategy = 'mobile' if device == "Mobile" else 'desktop'
|
||||
data = run_pagespeed(url, api_key, strategy=strategy, locale=locale)
|
||||
if data:
|
||||
display_results(data)
|
||||
else:
|
||||
st.error("Failed to retrieve PageSpeed Insights data.")
|
||||
864
ToBeMigrated/ai_seo_tools/google_search_console_integration.py
Normal file
864
ToBeMigrated/ai_seo_tools/google_search_console_integration.py
Normal file
@@ -0,0 +1,864 @@
|
||||
"""
|
||||
Google Search Console Integration for Enterprise SEO
|
||||
|
||||
Connects GSC data with AI-powered content strategy and keyword intelligence.
|
||||
Provides enterprise-level search performance insights and content recommendations.
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
from datetime import datetime, timedelta
|
||||
import json
|
||||
from loguru import logger
|
||||
import plotly.express as px
|
||||
import plotly.graph_objects as go
|
||||
from plotly.subplots import make_subplots
|
||||
|
||||
# Import AI modules
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
class GoogleSearchConsoleAnalyzer:
|
||||
"""
|
||||
Enterprise Google Search Console analyzer with AI-powered insights.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the GSC analyzer."""
|
||||
self.gsc_client = None # Will be initialized when credentials are provided
|
||||
logger.info("Google Search Console Analyzer initialized")
|
||||
|
||||
def analyze_search_performance(self, site_url: str, date_range: int = 90) -> Dict[str, Any]:
|
||||
"""
|
||||
Analyze comprehensive search performance from GSC data.
|
||||
|
||||
Args:
|
||||
site_url: Website URL registered in GSC
|
||||
date_range: Number of days to analyze (default 90)
|
||||
|
||||
Returns:
|
||||
Comprehensive search performance analysis
|
||||
"""
|
||||
try:
|
||||
st.info("📊 Analyzing Google Search Console data...")
|
||||
|
||||
# Simulate GSC data for demonstration (replace with actual GSC API calls)
|
||||
search_data = self._get_mock_gsc_data(site_url, date_range)
|
||||
|
||||
# Perform comprehensive analysis
|
||||
analysis_results = {
|
||||
'site_url': site_url,
|
||||
'analysis_period': f"Last {date_range} days",
|
||||
'analysis_timestamp': datetime.utcnow().isoformat(),
|
||||
'performance_overview': self._analyze_performance_overview(search_data),
|
||||
'keyword_analysis': self._analyze_keyword_performance(search_data),
|
||||
'page_analysis': self._analyze_page_performance(search_data),
|
||||
'content_opportunities': self._identify_content_opportunities(search_data),
|
||||
'technical_insights': self._analyze_technical_seo_signals(search_data),
|
||||
'competitive_analysis': self._analyze_competitive_position(search_data),
|
||||
'ai_recommendations': self._generate_ai_recommendations(search_data)
|
||||
}
|
||||
|
||||
return analysis_results
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"Error analyzing search performance: {str(e)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
return {'error': error_msg}
|
||||
|
||||
def _get_mock_gsc_data(self, site_url: str, days: int) -> Dict[str, pd.DataFrame]:
|
||||
"""
|
||||
Generate mock GSC data for demonstration.
|
||||
In production, this would fetch real data from GSC API.
|
||||
"""
|
||||
# Generate mock keyword data
|
||||
keywords_data = []
|
||||
sample_keywords = [
|
||||
"AI content creation", "SEO tools", "content optimization", "blog writing AI",
|
||||
"meta description generator", "keyword research", "technical SEO", "content strategy",
|
||||
"on-page optimization", "SERP analysis", "content gap analysis", "SEO audit"
|
||||
]
|
||||
|
||||
for keyword in sample_keywords:
|
||||
# Generate realistic performance data
|
||||
impressions = np.random.randint(100, 10000)
|
||||
clicks = int(impressions * np.random.uniform(0.02, 0.15)) # CTR between 2-15%
|
||||
position = np.random.uniform(3, 25)
|
||||
|
||||
keywords_data.append({
|
||||
'keyword': keyword,
|
||||
'impressions': impressions,
|
||||
'clicks': clicks,
|
||||
'ctr': (clicks / impressions) * 100,
|
||||
'position': position
|
||||
})
|
||||
|
||||
# Generate mock page data
|
||||
pages_data = []
|
||||
sample_pages = [
|
||||
"/blog/ai-content-creation-guide", "/tools/seo-analyzer", "/features/content-optimization",
|
||||
"/blog/technical-seo-checklist", "/tools/keyword-research", "/blog/content-strategy-2024",
|
||||
"/tools/meta-description-generator", "/blog/on-page-seo-guide", "/features/enterprise-seo"
|
||||
]
|
||||
|
||||
for page in sample_pages:
|
||||
impressions = np.random.randint(500, 5000)
|
||||
clicks = int(impressions * np.random.uniform(0.03, 0.12))
|
||||
position = np.random.uniform(5, 20)
|
||||
|
||||
pages_data.append({
|
||||
'page': page,
|
||||
'impressions': impressions,
|
||||
'clicks': clicks,
|
||||
'ctr': (clicks / impressions) * 100,
|
||||
'position': position
|
||||
})
|
||||
|
||||
# Generate time series data
|
||||
time_series_data = []
|
||||
for i in range(days):
|
||||
date = datetime.now() - timedelta(days=i)
|
||||
daily_clicks = np.random.randint(50, 500)
|
||||
daily_impressions = np.random.randint(1000, 8000)
|
||||
|
||||
time_series_data.append({
|
||||
'date': date.strftime('%Y-%m-%d'),
|
||||
'clicks': daily_clicks,
|
||||
'impressions': daily_impressions,
|
||||
'ctr': (daily_clicks / daily_impressions) * 100,
|
||||
'position': np.random.uniform(8, 15)
|
||||
})
|
||||
|
||||
return {
|
||||
'keywords': pd.DataFrame(keywords_data),
|
||||
'pages': pd.DataFrame(pages_data),
|
||||
'time_series': pd.DataFrame(time_series_data)
|
||||
}
|
||||
|
||||
def _analyze_performance_overview(self, search_data: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
|
||||
"""Analyze overall search performance metrics."""
|
||||
keywords_df = search_data['keywords']
|
||||
time_series_df = search_data['time_series']
|
||||
|
||||
# Calculate totals and averages
|
||||
total_clicks = keywords_df['clicks'].sum()
|
||||
total_impressions = keywords_df['impressions'].sum()
|
||||
avg_ctr = (total_clicks / total_impressions) * 100 if total_impressions > 0 else 0
|
||||
avg_position = keywords_df['position'].mean()
|
||||
|
||||
# Calculate trends
|
||||
recent_clicks = time_series_df.head(7)['clicks'].mean()
|
||||
previous_clicks = time_series_df.tail(7)['clicks'].mean()
|
||||
clicks_trend = ((recent_clicks - previous_clicks) / previous_clicks * 100) if previous_clicks > 0 else 0
|
||||
|
||||
recent_impressions = time_series_df.head(7)['impressions'].mean()
|
||||
previous_impressions = time_series_df.tail(7)['impressions'].mean()
|
||||
impressions_trend = ((recent_impressions - previous_impressions) / previous_impressions * 100) if previous_impressions > 0 else 0
|
||||
|
||||
# Top performing keywords
|
||||
top_keywords = keywords_df.nlargest(5, 'clicks')[['keyword', 'clicks', 'impressions', 'position']].to_dict('records')
|
||||
|
||||
# Opportunity keywords (high impressions, low CTR)
|
||||
opportunity_keywords = keywords_df[
|
||||
(keywords_df['impressions'] > keywords_df['impressions'].median()) &
|
||||
(keywords_df['ctr'] < 3)
|
||||
].nlargest(5, 'impressions')[['keyword', 'impressions', 'ctr', 'position']].to_dict('records')
|
||||
|
||||
return {
|
||||
'total_clicks': int(total_clicks),
|
||||
'total_impressions': int(total_impressions),
|
||||
'avg_ctr': round(avg_ctr, 2),
|
||||
'avg_position': round(avg_position, 1),
|
||||
'clicks_trend': round(clicks_trend, 1),
|
||||
'impressions_trend': round(impressions_trend, 1),
|
||||
'top_keywords': top_keywords,
|
||||
'opportunity_keywords': opportunity_keywords
|
||||
}
|
||||
|
||||
def _analyze_keyword_performance(self, search_data: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
|
||||
"""Analyze keyword performance and opportunities."""
|
||||
keywords_df = search_data['keywords']
|
||||
|
||||
# Keyword categorization
|
||||
high_volume_keywords = keywords_df[keywords_df['impressions'] > keywords_df['impressions'].quantile(0.8)]
|
||||
low_competition_keywords = keywords_df[keywords_df['position'] <= 10]
|
||||
optimization_opportunities = keywords_df[
|
||||
(keywords_df['position'] > 10) &
|
||||
(keywords_df['position'] <= 20) &
|
||||
(keywords_df['impressions'] > 100)
|
||||
]
|
||||
|
||||
# Content gap analysis
|
||||
missing_keywords = self._identify_missing_keywords(keywords_df)
|
||||
|
||||
# Seasonal trends analysis
|
||||
seasonal_insights = self._analyze_seasonal_trends(keywords_df)
|
||||
|
||||
return {
|
||||
'total_keywords': len(keywords_df),
|
||||
'high_volume_keywords': high_volume_keywords.to_dict('records'),
|
||||
'ranking_keywords': low_competition_keywords.to_dict('records'),
|
||||
'optimization_opportunities': optimization_opportunities.to_dict('records'),
|
||||
'missing_keywords': missing_keywords,
|
||||
'seasonal_insights': seasonal_insights,
|
||||
'keyword_distribution': {
|
||||
'positions_1_3': len(keywords_df[keywords_df['position'] <= 3]),
|
||||
'positions_4_10': len(keywords_df[(keywords_df['position'] > 3) & (keywords_df['position'] <= 10)]),
|
||||
'positions_11_20': len(keywords_df[(keywords_df['position'] > 10) & (keywords_df['position'] <= 20)]),
|
||||
'positions_21_plus': len(keywords_df[keywords_df['position'] > 20])
|
||||
}
|
||||
}
|
||||
|
||||
def _analyze_page_performance(self, search_data: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
|
||||
"""Analyze page-level performance."""
|
||||
pages_df = search_data['pages']
|
||||
|
||||
# Top performing pages
|
||||
top_pages = pages_df.nlargest(10, 'clicks')
|
||||
|
||||
# Underperforming pages (high impressions, low clicks)
|
||||
underperforming_pages = pages_df[
|
||||
(pages_df['impressions'] > pages_df['impressions'].median()) &
|
||||
(pages_df['ctr'] < 2)
|
||||
].nlargest(5, 'impressions')
|
||||
|
||||
# Page type analysis
|
||||
page_types = self._categorize_pages(pages_df)
|
||||
|
||||
return {
|
||||
'top_pages': top_pages.to_dict('records'),
|
||||
'underperforming_pages': underperforming_pages.to_dict('records'),
|
||||
'page_types_performance': page_types,
|
||||
'total_pages': len(pages_df)
|
||||
}
|
||||
|
||||
def _identify_content_opportunities(self, search_data: Dict[str, pd.DataFrame]) -> List[Dict[str, Any]]:
|
||||
"""Identify content creation and optimization opportunities."""
|
||||
keywords_df = search_data['keywords']
|
||||
|
||||
opportunities = []
|
||||
|
||||
# High impression, low CTR keywords need content optimization
|
||||
low_ctr_keywords = keywords_df[
|
||||
(keywords_df['impressions'] > 500) &
|
||||
(keywords_df['ctr'] < 3)
|
||||
]
|
||||
|
||||
for _, keyword_row in low_ctr_keywords.iterrows():
|
||||
opportunities.append({
|
||||
'type': 'Content Optimization',
|
||||
'keyword': keyword_row['keyword'],
|
||||
'opportunity': f"Optimize existing content for '{keyword_row['keyword']}' to improve CTR from {keyword_row['ctr']:.1f}%",
|
||||
'potential_impact': 'High',
|
||||
'current_position': round(keyword_row['position'], 1),
|
||||
'impressions': int(keyword_row['impressions']),
|
||||
'priority': 'High' if keyword_row['impressions'] > 1000 else 'Medium'
|
||||
})
|
||||
|
||||
# Position 11-20 keywords need content improvement
|
||||
position_11_20 = keywords_df[
|
||||
(keywords_df['position'] > 10) &
|
||||
(keywords_df['position'] <= 20) &
|
||||
(keywords_df['impressions'] > 100)
|
||||
]
|
||||
|
||||
for _, keyword_row in position_11_20.iterrows():
|
||||
opportunities.append({
|
||||
'type': 'Content Enhancement',
|
||||
'keyword': keyword_row['keyword'],
|
||||
'opportunity': f"Enhance content for '{keyword_row['keyword']}' to move from position {keyword_row['position']:.1f} to first page",
|
||||
'potential_impact': 'Medium',
|
||||
'current_position': round(keyword_row['position'], 1),
|
||||
'impressions': int(keyword_row['impressions']),
|
||||
'priority': 'Medium'
|
||||
})
|
||||
|
||||
# Sort by potential impact and impressions
|
||||
opportunities = sorted(opportunities, key=lambda x: x['impressions'], reverse=True)
|
||||
|
||||
return opportunities[:10] # Top 10 opportunities
|
||||
|
||||
def _analyze_technical_seo_signals(self, search_data: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
|
||||
"""Analyze technical SEO signals from search data."""
|
||||
keywords_df = search_data['keywords']
|
||||
pages_df = search_data['pages']
|
||||
|
||||
# Analyze performance patterns that might indicate technical issues
|
||||
technical_insights = {
|
||||
'crawl_issues_indicators': [],
|
||||
'mobile_performance': {},
|
||||
'core_web_vitals_impact': {},
|
||||
'indexing_insights': {}
|
||||
}
|
||||
|
||||
# Identify potential crawl issues
|
||||
very_low_impressions = keywords_df[keywords_df['impressions'] < 10]
|
||||
if len(very_low_impressions) > len(keywords_df) * 0.3: # If 30%+ have very low impressions
|
||||
technical_insights['crawl_issues_indicators'].append(
|
||||
"High percentage of keywords with very low impressions may indicate crawl or indexing issues"
|
||||
)
|
||||
|
||||
# Mobile performance indicators
|
||||
avg_mobile_position = keywords_df['position'].mean() # In real implementation, this would be mobile-specific
|
||||
technical_insights['mobile_performance'] = {
|
||||
'avg_mobile_position': round(avg_mobile_position, 1),
|
||||
'mobile_optimization_needed': avg_mobile_position > 15
|
||||
}
|
||||
|
||||
return technical_insights
|
||||
|
||||
def _analyze_competitive_position(self, search_data: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
|
||||
"""Analyze competitive positioning based on search data."""
|
||||
keywords_df = search_data['keywords']
|
||||
|
||||
# Calculate competitive metrics
|
||||
dominant_keywords = len(keywords_df[keywords_df['position'] <= 3])
|
||||
competitive_keywords = len(keywords_df[(keywords_df['position'] > 3) & (keywords_df['position'] <= 10)])
|
||||
losing_keywords = len(keywords_df[keywords_df['position'] > 10])
|
||||
|
||||
competitive_strength = (dominant_keywords * 3 + competitive_keywords * 2 + losing_keywords * 1) / len(keywords_df)
|
||||
|
||||
return {
|
||||
'dominant_keywords': dominant_keywords,
|
||||
'competitive_keywords': competitive_keywords,
|
||||
'losing_keywords': losing_keywords,
|
||||
'competitive_strength_score': round(competitive_strength, 2),
|
||||
'market_position': self._determine_market_position(competitive_strength)
|
||||
}
|
||||
|
||||
def _generate_ai_recommendations(self, search_data: Dict[str, pd.DataFrame]) -> Dict[str, Any]:
|
||||
"""Generate AI-powered recommendations based on search data."""
|
||||
try:
|
||||
keywords_df = search_data['keywords']
|
||||
pages_df = search_data['pages']
|
||||
|
||||
# Prepare data summary for AI analysis
|
||||
top_keywords = keywords_df.nlargest(5, 'impressions')['keyword'].tolist()
|
||||
avg_position = keywords_df['position'].mean()
|
||||
total_impressions = keywords_df['impressions'].sum()
|
||||
total_clicks = keywords_df['clicks'].sum()
|
||||
avg_ctr = (total_clicks / total_impressions * 100) if total_impressions > 0 else 0
|
||||
|
||||
# Create comprehensive prompt for AI analysis
|
||||
ai_prompt = f"""
|
||||
Analyze this Google Search Console data and provide strategic SEO recommendations:
|
||||
|
||||
SEARCH PERFORMANCE SUMMARY:
|
||||
- Total Keywords Tracked: {len(keywords_df)}
|
||||
- Total Impressions: {total_impressions:,}
|
||||
- Total Clicks: {total_clicks:,}
|
||||
- Average CTR: {avg_ctr:.2f}%
|
||||
- Average Position: {avg_position:.1f}
|
||||
|
||||
TOP PERFORMING KEYWORDS:
|
||||
{', '.join(top_keywords)}
|
||||
|
||||
PERFORMANCE DISTRIBUTION:
|
||||
- Keywords ranking 1-3: {len(keywords_df[keywords_df['position'] <= 3])}
|
||||
- Keywords ranking 4-10: {len(keywords_df[(keywords_df['position'] > 3) & (keywords_df['position'] <= 10)])}
|
||||
- Keywords ranking 11-20: {len(keywords_df[(keywords_df['position'] > 10) & (keywords_df['position'] <= 20)])}
|
||||
- Keywords ranking 21+: {len(keywords_df[keywords_df['position'] > 20])}
|
||||
|
||||
TOP PAGES BY TRAFFIC:
|
||||
{pages_df.nlargest(3, 'clicks')['page'].tolist()}
|
||||
|
||||
Based on this data, provide:
|
||||
|
||||
1. IMMEDIATE OPTIMIZATION OPPORTUNITIES (0-30 days):
|
||||
- Specific keywords to optimize for better CTR
|
||||
- Pages that need content updates
|
||||
- Quick technical wins
|
||||
|
||||
2. CONTENT STRATEGY RECOMMENDATIONS (1-3 months):
|
||||
- New content topics based on keyword gaps
|
||||
- Content enhancement priorities
|
||||
- Internal linking opportunities
|
||||
|
||||
3. LONG-TERM SEO STRATEGY (3-12 months):
|
||||
- Market expansion opportunities
|
||||
- Authority building topics
|
||||
- Competitive positioning strategies
|
||||
|
||||
4. TECHNICAL SEO PRIORITIES:
|
||||
- Performance issues affecting rankings
|
||||
- Mobile optimization needs
|
||||
- Core Web Vitals improvements
|
||||
|
||||
Provide specific, actionable recommendations with expected impact and priority levels.
|
||||
"""
|
||||
|
||||
ai_analysis = llm_text_gen(
|
||||
ai_prompt,
|
||||
system_prompt="You are an enterprise SEO strategist analyzing Google Search Console data. Provide specific, data-driven recommendations that will improve search performance."
|
||||
)
|
||||
|
||||
return {
|
||||
'full_analysis': ai_analysis,
|
||||
'immediate_opportunities': self._extract_immediate_opportunities(ai_analysis),
|
||||
'content_strategy': self._extract_content_strategy(ai_analysis),
|
||||
'long_term_strategy': self._extract_long_term_strategy(ai_analysis),
|
||||
'technical_priorities': self._extract_technical_priorities(ai_analysis)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"AI recommendations error: {str(e)}")
|
||||
return {'error': str(e)}
|
||||
|
||||
# Utility methods
|
||||
def _identify_missing_keywords(self, keywords_df: pd.DataFrame) -> List[str]:
|
||||
"""Identify potential missing keywords based on current keyword performance."""
|
||||
# In a real implementation, this would use keyword research APIs
|
||||
existing_keywords = set(keywords_df['keyword'].str.lower())
|
||||
|
||||
potential_keywords = [
|
||||
"AI writing tools", "content automation", "SEO content generator",
|
||||
"blog post optimizer", "meta tag generator", "keyword analyzer"
|
||||
]
|
||||
|
||||
missing = [kw for kw in potential_keywords if kw.lower() not in existing_keywords]
|
||||
return missing[:5]
|
||||
|
||||
def _analyze_seasonal_trends(self, keywords_df: pd.DataFrame) -> Dict[str, Any]:
|
||||
"""Analyze seasonal trends in keyword performance."""
|
||||
# Placeholder for seasonal analysis
|
||||
return {
|
||||
'seasonal_keywords': [],
|
||||
'trend_analysis': "Seasonal analysis requires historical data spanning multiple seasons"
|
||||
}
|
||||
|
||||
def _categorize_pages(self, pages_df: pd.DataFrame) -> Dict[str, Any]:
|
||||
"""Categorize pages by type and analyze performance."""
|
||||
page_types = {
|
||||
'Blog Posts': {'count': 0, 'total_clicks': 0, 'avg_position': 0},
|
||||
'Product Pages': {'count': 0, 'total_clicks': 0, 'avg_position': 0},
|
||||
'Tool Pages': {'count': 0, 'total_clicks': 0, 'avg_position': 0},
|
||||
'Other': {'count': 0, 'total_clicks': 0, 'avg_position': 0}
|
||||
}
|
||||
|
||||
for _, page_row in pages_df.iterrows():
|
||||
page_url = page_row['page']
|
||||
clicks = page_row['clicks']
|
||||
position = page_row['position']
|
||||
|
||||
if '/blog/' in page_url:
|
||||
page_types['Blog Posts']['count'] += 1
|
||||
page_types['Blog Posts']['total_clicks'] += clicks
|
||||
page_types['Blog Posts']['avg_position'] += position
|
||||
elif '/tools/' in page_url:
|
||||
page_types['Tool Pages']['count'] += 1
|
||||
page_types['Tool Pages']['total_clicks'] += clicks
|
||||
page_types['Tool Pages']['avg_position'] += position
|
||||
elif '/features/' in page_url or '/product/' in page_url:
|
||||
page_types['Product Pages']['count'] += 1
|
||||
page_types['Product Pages']['total_clicks'] += clicks
|
||||
page_types['Product Pages']['avg_position'] += position
|
||||
else:
|
||||
page_types['Other']['count'] += 1
|
||||
page_types['Other']['total_clicks'] += clicks
|
||||
page_types['Other']['avg_position'] += position
|
||||
|
||||
# Calculate averages
|
||||
for page_type in page_types:
|
||||
if page_types[page_type]['count'] > 0:
|
||||
page_types[page_type]['avg_position'] = round(
|
||||
page_types[page_type]['avg_position'] / page_types[page_type]['count'], 1
|
||||
)
|
||||
|
||||
return page_types
|
||||
|
||||
def _determine_market_position(self, competitive_strength: float) -> str:
|
||||
"""Determine market position based on competitive strength score."""
|
||||
if competitive_strength >= 2.5:
|
||||
return "Market Leader"
|
||||
elif competitive_strength >= 2.0:
|
||||
return "Strong Competitor"
|
||||
elif competitive_strength >= 1.5:
|
||||
return "Emerging Player"
|
||||
else:
|
||||
return "Challenger"
|
||||
|
||||
def _extract_immediate_opportunities(self, analysis: str) -> List[str]:
|
||||
"""Extract immediate opportunities from AI analysis."""
|
||||
lines = analysis.split('\n')
|
||||
opportunities = []
|
||||
in_immediate_section = False
|
||||
|
||||
for line in lines:
|
||||
if 'IMMEDIATE OPTIMIZATION' in line.upper():
|
||||
in_immediate_section = True
|
||||
continue
|
||||
elif 'CONTENT STRATEGY' in line.upper():
|
||||
in_immediate_section = False
|
||||
continue
|
||||
|
||||
if in_immediate_section and line.strip().startswith('-'):
|
||||
opportunities.append(line.strip().lstrip('- '))
|
||||
|
||||
return opportunities[:5]
|
||||
|
||||
def _extract_content_strategy(self, analysis: str) -> List[str]:
|
||||
"""Extract content strategy recommendations from AI analysis."""
|
||||
return ["Develop topic clusters", "Create comparison content", "Build FAQ sections"]
|
||||
|
||||
def _extract_long_term_strategy(self, analysis: str) -> List[str]:
|
||||
"""Extract long-term strategy from AI analysis."""
|
||||
return ["Build domain authority", "Expand to new markets", "Develop thought leadership content"]
|
||||
|
||||
def _extract_technical_priorities(self, analysis: str) -> List[str]:
|
||||
"""Extract technical priorities from AI analysis."""
|
||||
return ["Improve page speed", "Optimize mobile experience", "Fix crawl errors"]
|
||||
|
||||
|
||||
def render_gsc_integration():
|
||||
"""Render the Google Search Console integration interface."""
|
||||
|
||||
st.title("📊 Google Search Console Intelligence")
|
||||
st.markdown("**AI-powered insights from your Google Search Console data**")
|
||||
|
||||
# Initialize analyzer
|
||||
if 'gsc_analyzer' not in st.session_state:
|
||||
st.session_state.gsc_analyzer = GoogleSearchConsoleAnalyzer()
|
||||
|
||||
analyzer = st.session_state.gsc_analyzer
|
||||
|
||||
# Configuration section
|
||||
st.header("🔧 Configuration")
|
||||
|
||||
with st.expander("📋 Setup Instructions", expanded=False):
|
||||
st.markdown("""
|
||||
### Setting up Google Search Console Integration
|
||||
|
||||
1. **Verify your website** in Google Search Console
|
||||
2. **Enable the Search Console API** in Google Cloud Console
|
||||
3. **Create service account credentials** and download the JSON file
|
||||
4. **Upload credentials** using the file uploader below
|
||||
|
||||
📚 [Detailed Setup Guide](https://developers.google.com/webmaster-tools/search-console-api-original/v3/prereqs)
|
||||
""")
|
||||
|
||||
# Input form
|
||||
with st.form("gsc_analysis_form"):
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
site_url = st.text_input(
|
||||
"Site URL",
|
||||
value="https://example.com",
|
||||
help="Enter your website URL as registered in Google Search Console"
|
||||
)
|
||||
|
||||
date_range = st.selectbox(
|
||||
"Analysis Period",
|
||||
[30, 60, 90, 180],
|
||||
index=2,
|
||||
help="Number of days to analyze"
|
||||
)
|
||||
|
||||
with col2:
|
||||
# Credentials upload (placeholder)
|
||||
credentials_file = st.file_uploader(
|
||||
"GSC API Credentials (JSON)",
|
||||
type=['json'],
|
||||
help="Upload your Google Search Console API credentials file"
|
||||
)
|
||||
|
||||
demo_mode = st.checkbox(
|
||||
"Demo Mode",
|
||||
value=True,
|
||||
help="Use demo data for testing (no credentials needed)"
|
||||
)
|
||||
|
||||
submit_analysis = st.form_submit_button("📊 Analyze Search Performance", type="primary")
|
||||
|
||||
# Process analysis
|
||||
if submit_analysis:
|
||||
if site_url and (demo_mode or credentials_file):
|
||||
with st.spinner("📊 Analyzing Google Search Console data..."):
|
||||
analysis_results = analyzer.analyze_search_performance(site_url, date_range)
|
||||
|
||||
if 'error' not in analysis_results:
|
||||
st.success("✅ Search Console analysis completed!")
|
||||
|
||||
# Store results in session state
|
||||
st.session_state.gsc_results = analysis_results
|
||||
|
||||
# Display results
|
||||
render_gsc_results_dashboard(analysis_results)
|
||||
else:
|
||||
st.error(f"❌ Analysis failed: {analysis_results['error']}")
|
||||
else:
|
||||
st.warning("⚠️ Please enter site URL and upload credentials (or enable demo mode).")
|
||||
|
||||
# Show previous results if available
|
||||
elif 'gsc_results' in st.session_state:
|
||||
st.info("📊 Showing previous analysis results")
|
||||
render_gsc_results_dashboard(st.session_state.gsc_results)
|
||||
|
||||
|
||||
def render_gsc_results_dashboard(results: Dict[str, Any]):
|
||||
"""Render comprehensive GSC analysis results."""
|
||||
|
||||
# Performance overview
|
||||
st.header("📊 Search Performance Overview")
|
||||
|
||||
overview = results['performance_overview']
|
||||
|
||||
col1, col2, col3, col4 = st.columns(4)
|
||||
|
||||
with col1:
|
||||
st.metric(
|
||||
"Total Clicks",
|
||||
f"{overview['total_clicks']:,}",
|
||||
delta=f"{overview['clicks_trend']:+.1f}%" if overview['clicks_trend'] != 0 else None
|
||||
)
|
||||
|
||||
with col2:
|
||||
st.metric(
|
||||
"Total Impressions",
|
||||
f"{overview['total_impressions']:,}",
|
||||
delta=f"{overview['impressions_trend']:+.1f}%" if overview['impressions_trend'] != 0 else None
|
||||
)
|
||||
|
||||
with col3:
|
||||
st.metric(
|
||||
"Average CTR",
|
||||
f"{overview['avg_ctr']:.2f}%"
|
||||
)
|
||||
|
||||
with col4:
|
||||
st.metric(
|
||||
"Average Position",
|
||||
f"{overview['avg_position']:.1f}"
|
||||
)
|
||||
|
||||
# Content opportunities (Most important section)
|
||||
st.header("🎯 Content Opportunities")
|
||||
|
||||
opportunities = results['content_opportunities']
|
||||
if opportunities:
|
||||
# Display as interactive table
|
||||
df_opportunities = pd.DataFrame(opportunities)
|
||||
|
||||
st.dataframe(
|
||||
df_opportunities,
|
||||
column_config={
|
||||
"type": "Opportunity Type",
|
||||
"keyword": "Keyword",
|
||||
"opportunity": "Description",
|
||||
"potential_impact": st.column_config.SelectboxColumn(
|
||||
"Impact",
|
||||
options=["High", "Medium", "Low"]
|
||||
),
|
||||
"current_position": st.column_config.NumberColumn(
|
||||
"Current Position",
|
||||
format="%.1f"
|
||||
),
|
||||
"impressions": st.column_config.NumberColumn(
|
||||
"Impressions",
|
||||
format="%d"
|
||||
),
|
||||
"priority": st.column_config.SelectboxColumn(
|
||||
"Priority",
|
||||
options=["High", "Medium", "Low"]
|
||||
)
|
||||
},
|
||||
hide_index=True,
|
||||
use_container_width=True
|
||||
)
|
||||
|
||||
# Detailed analysis tabs
|
||||
tab1, tab2, tab3, tab4, tab5 = st.tabs([
|
||||
"🤖 AI Insights",
|
||||
"🎯 Keyword Analysis",
|
||||
"📄 Page Performance",
|
||||
"🏆 Competitive Position",
|
||||
"🔧 Technical Signals"
|
||||
])
|
||||
|
||||
with tab1:
|
||||
ai_recs = results.get('ai_recommendations', {})
|
||||
if ai_recs and 'error' not in ai_recs:
|
||||
st.subheader("AI-Powered Recommendations")
|
||||
|
||||
# Immediate opportunities
|
||||
immediate_ops = ai_recs.get('immediate_opportunities', [])
|
||||
if immediate_ops:
|
||||
st.markdown("#### 🚀 Immediate Optimizations (0-30 days)")
|
||||
for op in immediate_ops:
|
||||
st.success(f"✅ {op}")
|
||||
|
||||
# Content strategy
|
||||
content_strategy = ai_recs.get('content_strategy', [])
|
||||
if content_strategy:
|
||||
st.markdown("#### 📝 Content Strategy (1-3 months)")
|
||||
for strategy in content_strategy:
|
||||
st.info(f"📋 {strategy}")
|
||||
|
||||
# Full analysis
|
||||
full_analysis = ai_recs.get('full_analysis', '')
|
||||
if full_analysis:
|
||||
with st.expander("🧠 Complete AI Analysis"):
|
||||
st.write(full_analysis)
|
||||
|
||||
with tab2:
|
||||
keyword_analysis = results.get('keyword_analysis', {})
|
||||
if keyword_analysis:
|
||||
st.subheader("Keyword Performance Analysis")
|
||||
|
||||
# Keyword distribution chart
|
||||
dist = keyword_analysis['keyword_distribution']
|
||||
fig = px.pie(
|
||||
values=[dist['positions_1_3'], dist['positions_4_10'], dist['positions_11_20'], dist['positions_21_plus']],
|
||||
names=['Positions 1-3', 'Positions 4-10', 'Positions 11-20', 'Positions 21+'],
|
||||
title="Keyword Position Distribution"
|
||||
)
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
# High volume keywords
|
||||
high_volume = keyword_analysis.get('high_volume_keywords', [])
|
||||
if high_volume:
|
||||
st.markdown("#### 📈 High Volume Keywords")
|
||||
st.dataframe(pd.DataFrame(high_volume), hide_index=True)
|
||||
|
||||
# Optimization opportunities
|
||||
opt_opportunities = keyword_analysis.get('optimization_opportunities', [])
|
||||
if opt_opportunities:
|
||||
st.markdown("#### 🎯 Optimization Opportunities (Positions 11-20)")
|
||||
st.dataframe(pd.DataFrame(opt_opportunities), hide_index=True)
|
||||
|
||||
with tab3:
|
||||
page_analysis = results.get('page_analysis', {})
|
||||
if page_analysis:
|
||||
st.subheader("Page Performance Analysis")
|
||||
|
||||
# Top pages
|
||||
top_pages = page_analysis.get('top_pages', [])
|
||||
if top_pages:
|
||||
st.markdown("#### 🏆 Top Performing Pages")
|
||||
st.dataframe(pd.DataFrame(top_pages), hide_index=True)
|
||||
|
||||
# Underperforming pages
|
||||
underperforming = page_analysis.get('underperforming_pages', [])
|
||||
if underperforming:
|
||||
st.markdown("#### ⚠️ Underperforming Pages (High Impressions, Low CTR)")
|
||||
st.dataframe(pd.DataFrame(underperforming), hide_index=True)
|
||||
|
||||
# Page types performance
|
||||
page_types = page_analysis.get('page_types_performance', {})
|
||||
if page_types:
|
||||
st.markdown("#### 📊 Performance by Page Type")
|
||||
|
||||
# Create visualization
|
||||
types = []
|
||||
clicks = []
|
||||
positions = []
|
||||
|
||||
for page_type, data in page_types.items():
|
||||
if data['count'] > 0:
|
||||
types.append(page_type)
|
||||
clicks.append(data['total_clicks'])
|
||||
positions.append(data['avg_position'])
|
||||
|
||||
if types:
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
fig_clicks = px.bar(x=types, y=clicks, title="Total Clicks by Page Type")
|
||||
st.plotly_chart(fig_clicks, use_container_width=True)
|
||||
|
||||
with col2:
|
||||
fig_position = px.bar(x=types, y=positions, title="Average Position by Page Type")
|
||||
st.plotly_chart(fig_position, use_container_width=True)
|
||||
|
||||
with tab4:
|
||||
competitive_analysis = results.get('competitive_analysis', {})
|
||||
if competitive_analysis:
|
||||
st.subheader("Competitive Position Analysis")
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
st.metric("Market Position", competitive_analysis['market_position'])
|
||||
st.metric("Competitive Strength", f"{competitive_analysis['competitive_strength_score']}/3.0")
|
||||
|
||||
with col2:
|
||||
# Competitive distribution
|
||||
comp_data = {
|
||||
'Dominant (1-3)': competitive_analysis['dominant_keywords'],
|
||||
'Competitive (4-10)': competitive_analysis['competitive_keywords'],
|
||||
'Losing (11+)': competitive_analysis['losing_keywords']
|
||||
}
|
||||
|
||||
fig = px.bar(
|
||||
x=list(comp_data.keys()),
|
||||
y=list(comp_data.values()),
|
||||
title="Keyword Competitive Position"
|
||||
)
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
with tab5:
|
||||
technical_insights = results.get('technical_insights', {})
|
||||
if technical_insights:
|
||||
st.subheader("Technical SEO Signals")
|
||||
|
||||
# Crawl issues indicators
|
||||
crawl_issues = technical_insights.get('crawl_issues_indicators', [])
|
||||
if crawl_issues:
|
||||
st.markdown("#### ⚠️ Potential Issues")
|
||||
for issue in crawl_issues:
|
||||
st.warning(f"🚨 {issue}")
|
||||
|
||||
# Mobile performance
|
||||
mobile_perf = technical_insights.get('mobile_performance', {})
|
||||
if mobile_perf:
|
||||
st.markdown("#### 📱 Mobile Performance")
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
st.metric("Avg Mobile Position", f"{mobile_perf.get('avg_mobile_position', 0):.1f}")
|
||||
|
||||
with col2:
|
||||
if mobile_perf.get('mobile_optimization_needed', False):
|
||||
st.warning("📱 Mobile optimization needed")
|
||||
else:
|
||||
st.success("📱 Mobile performance good")
|
||||
|
||||
# Export functionality
|
||||
st.markdown("---")
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
if st.button("📥 Export Full Report", use_container_width=True):
|
||||
report_json = json.dumps(results, indent=2, default=str)
|
||||
st.download_button(
|
||||
label="Download JSON Report",
|
||||
data=report_json,
|
||||
file_name=f"gsc_analysis_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
||||
mime="application/json"
|
||||
)
|
||||
|
||||
with col2:
|
||||
if st.button("📊 Export Opportunities", use_container_width=True):
|
||||
if opportunities:
|
||||
df_opportunities = pd.DataFrame(opportunities)
|
||||
csv = df_opportunities.to_csv(index=False)
|
||||
st.download_button(
|
||||
label="Download CSV Opportunities",
|
||||
data=csv,
|
||||
file_name=f"content_opportunities_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
|
||||
mime="text/csv"
|
||||
)
|
||||
|
||||
with col3:
|
||||
if st.button("🔄 Refresh Analysis", use_container_width=True):
|
||||
# Clear cached results to force refresh
|
||||
if 'gsc_results' in st.session_state:
|
||||
del st.session_state.gsc_results
|
||||
st.rerun()
|
||||
|
||||
|
||||
# Main execution
|
||||
if __name__ == "__main__":
|
||||
render_gsc_integration()
|
||||
112
ToBeMigrated/ai_seo_tools/image_alt_text_generator.py
Normal file
112
ToBeMigrated/ai_seo_tools/image_alt_text_generator.py
Normal file
@@ -0,0 +1,112 @@
|
||||
import streamlit as st
|
||||
import base64
|
||||
import requests
|
||||
from PIL import Image
|
||||
import os
|
||||
|
||||
|
||||
def encode_image(image_path):
|
||||
"""
|
||||
Encodes an image to base64 format.
|
||||
|
||||
Args:
|
||||
image_path (str): Path to the image file.
|
||||
|
||||
Returns:
|
||||
str: Base64 encoded string of the image.
|
||||
|
||||
Raises:
|
||||
ValueError: If the image path is invalid.
|
||||
"""
|
||||
safe_root = os.getenv('SAFE_ROOT_DIRECTORY', '/safe/root/directory') # Use an environment variable for the safe root directory
|
||||
normalized_path = os.path.normpath(image_path)
|
||||
if not normalized_path.startswith(safe_root):
|
||||
raise ValueError("Invalid image path")
|
||||
with open(normalized_path, "rb") as image_file:
|
||||
return base64.b64encode(image_file.read()).decode('utf-8')
|
||||
|
||||
|
||||
def get_image_description(image_path):
|
||||
"""
|
||||
Generates a description for the given image using an external API.
|
||||
|
||||
Args:
|
||||
image_path (str): Path to the image file.
|
||||
|
||||
Returns:
|
||||
str: Description of the image.
|
||||
|
||||
Raises:
|
||||
ValueError: If the image path is invalid.
|
||||
"""
|
||||
safe_root = os.getenv('SAFE_ROOT_DIRECTORY', '/safe/root/directory') # Use an environment variable for the safe root directory
|
||||
normalized_path = os.path.normpath(image_path)
|
||||
if not normalized_path.startswith(safe_root):
|
||||
raise ValueError("Invalid image path")
|
||||
base64_image = encode_image(normalized_path)
|
||||
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {os.getenv('OPENAI_API_KEY')}"
|
||||
}
|
||||
|
||||
payload = {
|
||||
"model": "gpt-4o-mini",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": """You are an SEO expert specializing in writing optimized Alt text for images.
|
||||
Your goal is to create clear, descriptive, and concise Alt text that accurately represents
|
||||
the content and context of the given image. Make sure your response is optimized for search engines and accessibility."""
|
||||
},
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url": {
|
||||
"url": f"data:image/jpeg;base64,{base64_image}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"max_tokens": 300
|
||||
}
|
||||
|
||||
response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
|
||||
response_data = response.json()
|
||||
|
||||
# Extract the content field from the response
|
||||
content = response_data['choices'][0]['message']['content']
|
||||
return content
|
||||
|
||||
|
||||
def alt_text_gen():
|
||||
"""
|
||||
Streamlit app function to generate Alt text for an uploaded image.
|
||||
"""
|
||||
st.title("Image Description Generator")
|
||||
|
||||
image_path = st.text_input("Enter the full path of the image file", help="Provide the full path to a .jpg, .jpeg, or .png image file")
|
||||
|
||||
if image_path:
|
||||
if os.path.exists(image_path) and image_path.lower().endswith(('jpg', 'jpeg', 'png')):
|
||||
try:
|
||||
image = Image.open(image_path)
|
||||
st.image(image, caption='Uploaded Image', use_column_width=True)
|
||||
|
||||
if st.button("Get Image Alt Text"):
|
||||
with st.spinner("Generating Alt Text..."):
|
||||
try:
|
||||
description = get_image_description(image_path)
|
||||
st.success("Alt Text generated successfully!")
|
||||
st.write("Alt Text:", description)
|
||||
except Exception as e:
|
||||
st.error(f"Error generating description: {e}")
|
||||
except Exception as e:
|
||||
st.error(f"Error processing image: {e}")
|
||||
else:
|
||||
st.error("Please enter a valid image file path ending with .jpg, .jpeg, or .png")
|
||||
else:
|
||||
st.info("Please enter the full path of an image file.")
|
||||
110
ToBeMigrated/ai_seo_tools/meta_desc_generator.py
Normal file
110
ToBeMigrated/ai_seo_tools/meta_desc_generator.py
Normal file
@@ -0,0 +1,110 @@
|
||||
import os
|
||||
import json
|
||||
import streamlit as st
|
||||
from tenacity import retry, stop_after_attempt, wait_random_exponential
|
||||
from loguru import logger
|
||||
import sys
|
||||
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
def metadesc_generator_main():
|
||||
"""
|
||||
Streamlit app for generating SEO-optimized blog meta descriptions.
|
||||
"""
|
||||
st.title("✍️ Alwrity - AI Blog Meta Description Generator")
|
||||
st.markdown(
|
||||
"Create compelling, SEO-optimized meta descriptions in just a few clicks. Perfect for enhancing your blog's click-through rates!"
|
||||
)
|
||||
|
||||
# Input section
|
||||
with st.expander("**PRO-TIP** - Read the instructions below. 🚀", expanded=True):
|
||||
col1, col2, _ = st.columns([5, 5, 0.5])
|
||||
|
||||
# Column 1: Keywords and Tone
|
||||
with col1:
|
||||
keywords = st.text_input(
|
||||
"🔑 Target Keywords (comma-separated):",
|
||||
placeholder="e.g., content marketing, SEO, social media, online business",
|
||||
help="Enter your target keywords, separated by commas. 📝",
|
||||
)
|
||||
|
||||
tone_options = ["General", "Informative", "Engaging", "Humorous", "Intriguing", "Playful"]
|
||||
tone = st.selectbox(
|
||||
"🎨 Desired Tone (optional):",
|
||||
options=tone_options,
|
||||
help="Choose the overall tone you want for your meta description. 🎭",
|
||||
)
|
||||
|
||||
# Column 2: Search Intent and Language
|
||||
with col2:
|
||||
search_type = st.selectbox(
|
||||
"🔍 Search Intent:",
|
||||
("Informational Intent", "Commercial Intent", "Transactional Intent", "Navigational Intent"),
|
||||
index=0,
|
||||
)
|
||||
|
||||
language_options = ["English", "Spanish", "French", "German", "Other"]
|
||||
language_choice = st.selectbox(
|
||||
"🌐 Preferred Language:",
|
||||
options=language_options,
|
||||
help="Select the language for your meta description. 🗣️",
|
||||
)
|
||||
|
||||
language = (
|
||||
st.text_input(
|
||||
"Specify Other Language:",
|
||||
placeholder="e.g., Italian, Chinese",
|
||||
help="Enter your preferred language. 🌍",
|
||||
)
|
||||
if language_choice == "Other"
|
||||
else language_choice
|
||||
)
|
||||
|
||||
# Generate Meta Description button
|
||||
if st.button("**✨ Generate Meta Description ✨**"):
|
||||
if not keywords.strip():
|
||||
st.error("**🫣 Target Keywords are required! Please provide at least one keyword.**")
|
||||
return
|
||||
|
||||
with st.spinner("Crafting your Meta descriptions... ⏳"):
|
||||
blog_metadesc = generate_blog_metadesc(keywords, tone, search_type, language)
|
||||
if blog_metadesc:
|
||||
st.success("**🎉 Meta Descriptions Generated Successfully! 🚀**")
|
||||
with st.expander("**Your SEO-Boosting Blog Meta Descriptions 🎆🎇**", expanded=True):
|
||||
st.markdown(blog_metadesc)
|
||||
else:
|
||||
st.error("💥 **Failed to generate blog meta description. Please try again!**")
|
||||
|
||||
|
||||
def generate_blog_metadesc(keywords, tone, search_type, language):
|
||||
"""
|
||||
Generate blog meta descriptions using LLM.
|
||||
|
||||
Args:
|
||||
keywords (str): Comma-separated target keywords.
|
||||
tone (str): Desired tone for the meta description.
|
||||
search_type (str): Search intent type.
|
||||
language (str): Preferred language for the description.
|
||||
|
||||
Returns:
|
||||
str: Generated meta descriptions or error message.
|
||||
"""
|
||||
prompt = f"""
|
||||
Craft 3 engaging and SEO-friendly meta descriptions for a blog post based on the following details:
|
||||
|
||||
Blog Post Keywords: {keywords}
|
||||
Search Intent Type: {search_type}
|
||||
Desired Tone: {tone}
|
||||
Preferred Language: {language}
|
||||
|
||||
Output Format:
|
||||
|
||||
Respond with 3 compelling and concise meta descriptions, approximately 155-160 characters long, that incorporate the target keywords, reflect the blog post content, resonate with the target audience, and entice users to click through to read the full article.
|
||||
"""
|
||||
try:
|
||||
return llm_text_gen(prompt)
|
||||
except Exception as err:
|
||||
logger.error(f"Error generating meta description: {err}")
|
||||
st.error(f"💥 Error: Failed to generate response from LLM: {err}")
|
||||
return None
|
||||
1070
ToBeMigrated/ai_seo_tools/on_page_seo_analyzer.py
Normal file
1070
ToBeMigrated/ai_seo_tools/on_page_seo_analyzer.py
Normal file
File diff suppressed because it is too large
Load Diff
129
ToBeMigrated/ai_seo_tools/opengraph_generator.py
Normal file
129
ToBeMigrated/ai_seo_tools/opengraph_generator.py
Normal file
@@ -0,0 +1,129 @@
|
||||
import streamlit as st
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
def generate_og_tags(url, title_hint, description_hint, platform="General"):
|
||||
"""
|
||||
Generate Open Graph tags based on the provided URL, title hint, description hint, and platform.
|
||||
|
||||
Args:
|
||||
url (str): The URL of the webpage.
|
||||
title_hint (str): A hint for the title.
|
||||
description_hint (str): A hint for the description.
|
||||
platform (str): The platform for which to generate the tags (General, Facebook, or Twitter).
|
||||
|
||||
Returns:
|
||||
str: The generated Open Graph tags or an error message.
|
||||
"""
|
||||
# Create a prompt for the text generation model
|
||||
prompt = (
|
||||
f"Generate Open Graph tags for the following page:\nURL: {url}\n"
|
||||
f"Title hint: {title_hint}\nDescription hint: {description_hint}"
|
||||
)
|
||||
if platform == "Facebook":
|
||||
prompt += "\nSpecifically for Facebook"
|
||||
elif platform == "Twitter":
|
||||
prompt += "\nSpecifically for Twitter"
|
||||
|
||||
try:
|
||||
# Generate Open Graph tags using the text generation model
|
||||
response = llm_text_gen(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
st.error(f"Failed to generate Open Graph tags: {err}")
|
||||
return None
|
||||
|
||||
|
||||
def extract_default_og_tags(url):
|
||||
"""
|
||||
Extract default Open Graph tags from the provided URL.
|
||||
|
||||
Args:
|
||||
url (str): The URL of the webpage.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing the title, description, and image URL, or None in case of an error.
|
||||
"""
|
||||
try:
|
||||
# Fetch the HTML content of the URL
|
||||
response = requests.get(url)
|
||||
response.raise_for_status()
|
||||
|
||||
# Parse the HTML content using BeautifulSoup
|
||||
soup = BeautifulSoup(response.content, 'html.parser')
|
||||
|
||||
# Extract the title, description, and image URL
|
||||
title = soup.find('title').text if soup.find('title') else None
|
||||
description = soup.find('meta', attrs={'name': 'description'})['content'] if soup.find('meta', attrs={'name': 'description'}) else None
|
||||
image_url = soup.find('meta', attrs={'property': 'og:image'})['content'] if soup.find('meta', attrs={'property': 'og:image'}) else None
|
||||
|
||||
return title, description, image_url
|
||||
|
||||
except requests.exceptions.RequestException as req_err:
|
||||
st.error(f"Error fetching the URL: {req_err}")
|
||||
return None, None, None
|
||||
|
||||
except Exception as err:
|
||||
st.error(f"Error parsing the HTML content: {err}")
|
||||
return None, None, None
|
||||
|
||||
|
||||
def og_tag_generator():
|
||||
"""Main function to run the Streamlit app."""
|
||||
st.title("AI Open Graph Tag Generator")
|
||||
|
||||
# Platform selection
|
||||
platform = st.selectbox(
|
||||
"**Select the platform**",
|
||||
["General", "Facebook", "Twitter"],
|
||||
help="Choose the platform for which you want to generate Open Graph tags."
|
||||
)
|
||||
|
||||
# URL input
|
||||
url = st.text_input(
|
||||
"**Enter the URL of the page to generate Open Graph tags for:**",
|
||||
placeholder="e.g., https://example.com",
|
||||
help="Provide the URL of the page you want to generate Open Graph tags for."
|
||||
)
|
||||
|
||||
if url:
|
||||
# Extract default Open Graph tags
|
||||
title, description, image_url = extract_default_og_tags(url)
|
||||
|
||||
# Title hint input
|
||||
title_hint = st.text_input(
|
||||
"**Modify existing title or suggest a new one (optional):**",
|
||||
value=title if title else "",
|
||||
placeholder="e.g., Amazing Blog Post Title"
|
||||
)
|
||||
|
||||
# Description hint input
|
||||
description_hint = st.text_area(
|
||||
"**Modify existing description or suggest a new one (optional):**",
|
||||
value=description if description else "",
|
||||
placeholder="e.g., This is a detailed description of the content."
|
||||
)
|
||||
|
||||
# Image URL hint input
|
||||
image_hint = st.text_input(
|
||||
"**Use this image or suggest a new URL (optional):**",
|
||||
value=image_url if image_url else "",
|
||||
placeholder="e.g., https://example.com/image.jpg"
|
||||
)
|
||||
|
||||
# Generate Open Graph tags
|
||||
if st.button("Generate Open Graph Tags"):
|
||||
with st.spinner("Generating Open Graph tags..."):
|
||||
try:
|
||||
og_tags = generate_og_tags(url, title_hint, description_hint, platform)
|
||||
if og_tags:
|
||||
st.success("Open Graph tags generated successfully!")
|
||||
st.markdown(og_tags)
|
||||
else:
|
||||
st.error("Failed to generate Open Graph tags.")
|
||||
except Exception as e:
|
||||
st.error(f"Failed to generate Open Graph tags: {e}")
|
||||
else:
|
||||
st.info("Please enter a URL to generate Open Graph tags.")
|
||||
2
ToBeMigrated/ai_seo_tools/opengraph_image_generate.py
Normal file
2
ToBeMigrated/ai_seo_tools/opengraph_image_generate.py
Normal file
@@ -0,0 +1,2 @@
|
||||
|
||||
ogImage TBD
|
||||
187
ToBeMigrated/ai_seo_tools/optimize_images_for_upload.py
Normal file
187
ToBeMigrated/ai_seo_tools/optimize_images_for_upload.py
Normal file
@@ -0,0 +1,187 @@
|
||||
import os
|
||||
import sys
|
||||
import tinify
|
||||
from PIL import Image
|
||||
from loguru import logger
|
||||
from dotenv import load_dotenv
|
||||
import streamlit as st
|
||||
from tempfile import NamedTemporaryFile
|
||||
|
||||
# Load environment variables
|
||||
load_dotenv()
|
||||
|
||||
# Set Tinyfy API key from environment variable
|
||||
TINIFY_API_KEY = os.getenv('TINIFY_API_KEY')
|
||||
if TINIFY_API_KEY:
|
||||
tinify.key = TINIFY_API_KEY
|
||||
|
||||
def setup_logger() -> None:
|
||||
"""Configure the logger."""
|
||||
logger.remove()
|
||||
logger.add(
|
||||
sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
setup_logger()
|
||||
|
||||
def compress_image(image: Image.Image, quality: int = 45, resize: tuple = None, preserve_exif: bool = False) -> Image.Image:
|
||||
"""
|
||||
Compress and optionally resize an image.
|
||||
|
||||
Args:
|
||||
image (PIL.Image): Image object to compress.
|
||||
quality (int): Quality of the output image (1-100).
|
||||
resize (tuple): Tuple (width, height) to resize the image.
|
||||
preserve_exif (bool): Preserve EXIF data if True.
|
||||
|
||||
Returns:
|
||||
PIL.Image: The compressed and resized image object.
|
||||
"""
|
||||
try:
|
||||
if image.mode == 'RGBA':
|
||||
logger.info("Converting RGBA image to RGB.")
|
||||
image = image.convert('RGB')
|
||||
|
||||
exif = image.info.get('exif') if preserve_exif and 'exif' in image.info else None
|
||||
|
||||
if resize:
|
||||
image = image.resize(resize, Image.LANCZOS)
|
||||
logger.info(f"Resized image to {resize}")
|
||||
|
||||
with NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
|
||||
temp_path = temp_file.name
|
||||
try:
|
||||
image.save(temp_path, optimize=True, quality=quality, exif=exif)
|
||||
except Exception as exif_error:
|
||||
logger.warning(f"Error saving image with EXIF: {exif_error}. Saving without EXIF.")
|
||||
image.save(temp_path, optimize=True, quality=quality)
|
||||
|
||||
logger.info("Image compression successful.")
|
||||
return Image.open(temp_path)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error compressing image: {e}")
|
||||
st.error("Failed to compress the image. Please try again.")
|
||||
return None
|
||||
|
||||
def convert_to_webp(image: Image.Image, image_path: str) -> str:
|
||||
"""
|
||||
Convert an image to WebP format.
|
||||
|
||||
Args:
|
||||
image (PIL.Image): Image object to convert.
|
||||
image_path (str): Path to save the WebP image.
|
||||
|
||||
Returns:
|
||||
str: Path to the WebP image.
|
||||
"""
|
||||
try:
|
||||
webp_path = os.path.splitext(image_path)[0] + '.webp'
|
||||
image.save(webp_path, 'WEBP', quality=80, method=6)
|
||||
return webp_path
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting image to WebP: {e}")
|
||||
st.error("Failed to convert the image to WebP format. Please try again.")
|
||||
return None
|
||||
|
||||
def compress_image_tinyfy(image_path: str) -> None:
|
||||
"""
|
||||
Compress an image using Tinyfy API.
|
||||
|
||||
Args:
|
||||
image_path (str): Path to the image to be compressed.
|
||||
|
||||
Returns:
|
||||
None
|
||||
"""
|
||||
try:
|
||||
if not tinify.key:
|
||||
logger.warning("Tinyfy API key is not set. Skipping Tinyfy compression.")
|
||||
return
|
||||
|
||||
source = tinify.from_file(image_path)
|
||||
source.to_file(image_path)
|
||||
logger.info("Tinyfy compression successful.")
|
||||
except tinify.errors.AccountError:
|
||||
logger.error("Verify your Tinyfy API key and account limit.")
|
||||
st.warning("Tinyfy compression failed. Check your API key and account limit.")
|
||||
except Exception as e:
|
||||
logger.error(f"Error during Tinyfy compression: {e}")
|
||||
st.warning("Tinyfy compression failed. Ensure the API key is set.")
|
||||
|
||||
def optimize_image(image: Image.Image, image_path: str, quality: int, resize: tuple, preserve_exif: bool) -> str:
|
||||
"""
|
||||
Optimize the image by compressing and converting it to WebP, with optional Tinyfy compression.
|
||||
|
||||
Args:
|
||||
image (PIL.Image): The original image.
|
||||
image_path (str): The path to the image file.
|
||||
quality (int): Quality level for compression.
|
||||
resize (tuple): Dimensions to resize the image.
|
||||
preserve_exif (bool): Whether to preserve EXIF data.
|
||||
|
||||
Returns:
|
||||
str: Path to the optimized WebP image, or None if failed.
|
||||
"""
|
||||
logger.info("Starting image optimization process...")
|
||||
|
||||
compressed_image = compress_image(image, quality, resize, preserve_exif)
|
||||
if compressed_image is None:
|
||||
return None
|
||||
|
||||
webp_path = convert_to_webp(compressed_image, image_path)
|
||||
if webp_path is None:
|
||||
return None
|
||||
|
||||
if tinify.key:
|
||||
compress_image_tinyfy(webp_path)
|
||||
else:
|
||||
logger.info("Tinyfy key not provided, skipping Tinyfy compression.")
|
||||
|
||||
return webp_path
|
||||
|
||||
def main_img_optimizer() -> None:
|
||||
st.title("ALwrity Image Optimizer")
|
||||
st.markdown("## Upload an image to optimize its size and format.")
|
||||
|
||||
input_tinify_key = st.text_input("Optional: Enter your Tinyfy API Key")
|
||||
if input_tinify_key:
|
||||
tinify.key = input_tinify_key
|
||||
|
||||
uploaded_file = st.file_uploader("Upload an image", type=['jpg', 'jpeg', 'png', 'gif', 'bmp', 'webp'])
|
||||
|
||||
if uploaded_file:
|
||||
image = Image.open(uploaded_file)
|
||||
st.image(image, caption="Original Image", use_column_width=True)
|
||||
|
||||
quality = st.slider("Compression Quality", 1, 100, 45)
|
||||
preserve_exif = st.checkbox("Preserve EXIF Data", value=False)
|
||||
resize = st.checkbox("Resize Image")
|
||||
|
||||
if resize:
|
||||
width = st.number_input("Width", value=image.width)
|
||||
height = st.number_input("Height", value=image.height)
|
||||
resize_dims = (width, height)
|
||||
else:
|
||||
resize_dims = None
|
||||
|
||||
if st.button("Optimize Image"):
|
||||
with st.spinner("Optimizing..."):
|
||||
if tinify.key:
|
||||
st.info("Tinyfy compression will be applied.")
|
||||
|
||||
webp_path = optimize_image(image, uploaded_file.name, quality, resize_dims, preserve_exif)
|
||||
|
||||
if webp_path:
|
||||
st.image(webp_path, caption="Optimized Image (WebP)", use_column_width=True)
|
||||
st.success("Image optimization completed!")
|
||||
|
||||
with open(webp_path, "rb") as file:
|
||||
st.download_button(
|
||||
label="Download Optimized Image",
|
||||
data=file,
|
||||
file_name=os.path.basename(webp_path),
|
||||
mime="image/webp"
|
||||
)
|
||||
340
ToBeMigrated/ai_seo_tools/seo_analyzer_api.py
Normal file
340
ToBeMigrated/ai_seo_tools/seo_analyzer_api.py
Normal file
@@ -0,0 +1,340 @@
|
||||
"""
|
||||
FastAPI endpoint for the Comprehensive SEO Analyzer
|
||||
Provides data for the React SEO Dashboard
|
||||
"""
|
||||
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from pydantic import BaseModel, HttpUrl
|
||||
from typing import List, Optional, Dict, Any
|
||||
from datetime import datetime
|
||||
import json
|
||||
|
||||
from .comprehensive_seo_analyzer import ComprehensiveSEOAnalyzer, SEOAnalysisResult
|
||||
|
||||
app = FastAPI(
|
||||
title="Comprehensive SEO Analyzer API",
|
||||
description="API for analyzing website SEO performance with actionable insights",
|
||||
version="1.0.0"
|
||||
)
|
||||
|
||||
# Initialize the analyzer
|
||||
seo_analyzer = ComprehensiveSEOAnalyzer()
|
||||
|
||||
class SEOAnalysisRequest(BaseModel):
|
||||
url: HttpUrl
|
||||
target_keywords: Optional[List[str]] = None
|
||||
|
||||
class SEOAnalysisResponse(BaseModel):
|
||||
url: str
|
||||
timestamp: datetime
|
||||
overall_score: int
|
||||
health_status: str
|
||||
critical_issues: List[str]
|
||||
warnings: List[str]
|
||||
recommendations: List[str]
|
||||
data: Dict[str, Any]
|
||||
success: bool
|
||||
message: str
|
||||
|
||||
@app.post("/analyze-seo", response_model=SEOAnalysisResponse)
|
||||
async def analyze_seo(request: SEOAnalysisRequest):
|
||||
"""
|
||||
Analyze a URL for comprehensive SEO performance
|
||||
|
||||
Args:
|
||||
request: SEOAnalysisRequest containing URL and optional target keywords
|
||||
|
||||
Returns:
|
||||
SEOAnalysisResponse with detailed analysis results
|
||||
"""
|
||||
try:
|
||||
# Convert URL to string
|
||||
url_str = str(request.url)
|
||||
|
||||
# Perform analysis
|
||||
result = seo_analyzer.analyze_url(url_str, request.target_keywords)
|
||||
|
||||
# Convert to response format
|
||||
response_data = {
|
||||
'url': result.url,
|
||||
'timestamp': result.timestamp,
|
||||
'overall_score': result.overall_score,
|
||||
'health_status': result.health_status,
|
||||
'critical_issues': result.critical_issues,
|
||||
'warnings': result.warnings,
|
||||
'recommendations': result.recommendations,
|
||||
'data': result.data,
|
||||
'success': True,
|
||||
'message': f"SEO analysis completed successfully for {result.url}"
|
||||
}
|
||||
|
||||
return SEOAnalysisResponse(**response_data)
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=f"Error analyzing SEO: {str(e)}"
|
||||
)
|
||||
|
||||
@app.get("/health")
|
||||
async def health_check():
|
||||
"""Health check endpoint"""
|
||||
return {
|
||||
"status": "healthy",
|
||||
"timestamp": datetime.now(),
|
||||
"service": "Comprehensive SEO Analyzer API"
|
||||
}
|
||||
|
||||
@app.get("/analysis-summary/{url:path}")
|
||||
async def get_analysis_summary(url: str):
|
||||
"""
|
||||
Get a quick summary of SEO analysis for a URL
|
||||
|
||||
Args:
|
||||
url: The URL to analyze
|
||||
|
||||
Returns:
|
||||
Summary of SEO analysis
|
||||
"""
|
||||
try:
|
||||
# Ensure URL has protocol
|
||||
if not url.startswith(('http://', 'https://')):
|
||||
url = f"https://{url}"
|
||||
|
||||
# Perform analysis
|
||||
result = seo_analyzer.analyze_url(url)
|
||||
|
||||
# Create summary
|
||||
summary = {
|
||||
"url": result.url,
|
||||
"overall_score": result.overall_score,
|
||||
"health_status": result.health_status,
|
||||
"critical_issues_count": len(result.critical_issues),
|
||||
"warnings_count": len(result.warnings),
|
||||
"recommendations_count": len(result.recommendations),
|
||||
"top_issues": result.critical_issues[:3],
|
||||
"top_recommendations": result.recommendations[:3],
|
||||
"analysis_timestamp": result.timestamp.isoformat()
|
||||
}
|
||||
|
||||
return summary
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=f"Error getting analysis summary: {str(e)}"
|
||||
)
|
||||
|
||||
@app.get("/seo-metrics/{url:path}")
|
||||
async def get_seo_metrics(url: str):
|
||||
"""
|
||||
Get detailed SEO metrics for dashboard display
|
||||
|
||||
Args:
|
||||
url: The URL to analyze
|
||||
|
||||
Returns:
|
||||
Detailed SEO metrics for React dashboard
|
||||
"""
|
||||
try:
|
||||
# Ensure URL has protocol
|
||||
if not url.startswith(('http://', 'https://')):
|
||||
url = f"https://{url}"
|
||||
|
||||
# Perform analysis
|
||||
result = seo_analyzer.analyze_url(url)
|
||||
|
||||
# Extract metrics for dashboard
|
||||
metrics = {
|
||||
"overall_score": result.overall_score,
|
||||
"health_status": result.health_status,
|
||||
"url_structure_score": result.data.get('url_structure', {}).get('score', 0),
|
||||
"meta_data_score": result.data.get('meta_data', {}).get('score', 0),
|
||||
"content_score": result.data.get('content_analysis', {}).get('score', 0),
|
||||
"technical_score": result.data.get('technical_seo', {}).get('score', 0),
|
||||
"performance_score": result.data.get('performance', {}).get('score', 0),
|
||||
"accessibility_score": result.data.get('accessibility', {}).get('score', 0),
|
||||
"user_experience_score": result.data.get('user_experience', {}).get('score', 0),
|
||||
"security_score": result.data.get('security_headers', {}).get('score', 0)
|
||||
}
|
||||
|
||||
# Add detailed data for each category
|
||||
dashboard_data = {
|
||||
"metrics": metrics,
|
||||
"critical_issues": result.critical_issues,
|
||||
"warnings": result.warnings,
|
||||
"recommendations": result.recommendations,
|
||||
"detailed_analysis": {
|
||||
"url_structure": result.data.get('url_structure', {}),
|
||||
"meta_data": result.data.get('meta_data', {}),
|
||||
"content_analysis": result.data.get('content_analysis', {}),
|
||||
"technical_seo": result.data.get('technical_seo', {}),
|
||||
"performance": result.data.get('performance', {}),
|
||||
"accessibility": result.data.get('accessibility', {}),
|
||||
"user_experience": result.data.get('user_experience', {}),
|
||||
"security_headers": result.data.get('security_headers', {}),
|
||||
"keyword_analysis": result.data.get('keyword_analysis', {})
|
||||
},
|
||||
"timestamp": result.timestamp.isoformat(),
|
||||
"url": result.url
|
||||
}
|
||||
|
||||
return dashboard_data
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=f"Error getting SEO metrics: {str(e)}"
|
||||
)
|
||||
|
||||
@app.post("/batch-analyze")
|
||||
async def batch_analyze(urls: List[str]):
|
||||
"""
|
||||
Analyze multiple URLs in batch
|
||||
|
||||
Args:
|
||||
urls: List of URLs to analyze
|
||||
|
||||
Returns:
|
||||
Batch analysis results
|
||||
"""
|
||||
try:
|
||||
results = []
|
||||
|
||||
for url in urls:
|
||||
try:
|
||||
# Ensure URL has protocol
|
||||
if not url.startswith(('http://', 'https://')):
|
||||
url = f"https://{url}"
|
||||
|
||||
# Perform analysis
|
||||
result = seo_analyzer.analyze_url(url)
|
||||
|
||||
# Add to results
|
||||
results.append({
|
||||
"url": result.url,
|
||||
"overall_score": result.overall_score,
|
||||
"health_status": result.health_status,
|
||||
"critical_issues_count": len(result.critical_issues),
|
||||
"warnings_count": len(result.warnings),
|
||||
"success": True
|
||||
})
|
||||
|
||||
except Exception as e:
|
||||
# Add error result
|
||||
results.append({
|
||||
"url": url,
|
||||
"overall_score": 0,
|
||||
"health_status": "error",
|
||||
"critical_issues_count": 0,
|
||||
"warnings_count": 0,
|
||||
"success": False,
|
||||
"error": str(e)
|
||||
})
|
||||
|
||||
return {
|
||||
"total_urls": len(urls),
|
||||
"successful_analyses": len([r for r in results if r['success']]),
|
||||
"failed_analyses": len([r for r in results if not r['success']]),
|
||||
"results": results
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=f"Error in batch analysis: {str(e)}"
|
||||
)
|
||||
|
||||
# Enhanced prompts for better results
|
||||
ENHANCED_PROMPTS = {
|
||||
"critical_issue": "🚨 CRITICAL: This issue is severely impacting your SEO performance and must be fixed immediately.",
|
||||
"warning": "⚠️ WARNING: This could be improved to boost your search rankings.",
|
||||
"recommendation": "💡 RECOMMENDATION: Implement this to improve your SEO score.",
|
||||
"excellent": "🎉 EXCELLENT: Your SEO is performing very well in this area!",
|
||||
"good": "✅ GOOD: Your SEO is performing well, with room for minor improvements.",
|
||||
"needs_improvement": "🔧 NEEDS IMPROVEMENT: Several areas need attention to boost your SEO.",
|
||||
"poor": "❌ POOR: Significant improvements needed across multiple areas."
|
||||
}
|
||||
|
||||
def enhance_analysis_result(result: SEOAnalysisResult) -> SEOAnalysisResult:
|
||||
"""
|
||||
Enhance analysis results with better prompts and user-friendly language
|
||||
"""
|
||||
# Enhance critical issues
|
||||
enhanced_critical_issues = []
|
||||
for issue in result.critical_issues:
|
||||
enhanced_issue = f"{ENHANCED_PROMPTS['critical_issue']} {issue}"
|
||||
enhanced_critical_issues.append(enhanced_issue)
|
||||
|
||||
# Enhance warnings
|
||||
enhanced_warnings = []
|
||||
for warning in result.warnings:
|
||||
enhanced_warning = f"{ENHANCED_PROMPTS['warning']} {warning}"
|
||||
enhanced_warnings.append(enhanced_warning)
|
||||
|
||||
# Enhance recommendations
|
||||
enhanced_recommendations = []
|
||||
for rec in result.recommendations:
|
||||
enhanced_rec = f"{ENHANCED_PROMPTS['recommendation']} {rec}"
|
||||
enhanced_recommendations.append(enhanced_rec)
|
||||
|
||||
# Create enhanced result
|
||||
enhanced_result = SEOAnalysisResult(
|
||||
url=result.url,
|
||||
timestamp=result.timestamp,
|
||||
overall_score=result.overall_score,
|
||||
health_status=result.health_status,
|
||||
critical_issues=enhanced_critical_issues,
|
||||
warnings=enhanced_warnings,
|
||||
recommendations=enhanced_recommendations,
|
||||
data=result.data
|
||||
)
|
||||
|
||||
return enhanced_result
|
||||
|
||||
@app.post("/analyze-seo-enhanced", response_model=SEOAnalysisResponse)
|
||||
async def analyze_seo_enhanced(request: SEOAnalysisRequest):
|
||||
"""
|
||||
Analyze a URL with enhanced, user-friendly prompts
|
||||
|
||||
Args:
|
||||
request: SEOAnalysisRequest containing URL and optional target keywords
|
||||
|
||||
Returns:
|
||||
SEOAnalysisResponse with enhanced, user-friendly analysis results
|
||||
"""
|
||||
try:
|
||||
# Convert URL to string
|
||||
url_str = str(request.url)
|
||||
|
||||
# Perform analysis
|
||||
result = seo_analyzer.analyze_url(url_str, request.target_keywords)
|
||||
|
||||
# Enhance results
|
||||
enhanced_result = enhance_analysis_result(result)
|
||||
|
||||
# Convert to response format
|
||||
response_data = {
|
||||
'url': enhanced_result.url,
|
||||
'timestamp': enhanced_result.timestamp,
|
||||
'overall_score': enhanced_result.overall_score,
|
||||
'health_status': enhanced_result.health_status,
|
||||
'critical_issues': enhanced_result.critical_issues,
|
||||
'warnings': enhanced_result.warnings,
|
||||
'recommendations': enhanced_result.recommendations,
|
||||
'data': enhanced_result.data,
|
||||
'success': True,
|
||||
'message': f"Enhanced SEO analysis completed successfully for {enhanced_result.url}"
|
||||
}
|
||||
|
||||
return SEOAnalysisResponse(**response_data)
|
||||
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=f"Error analyzing SEO: {str(e)}"
|
||||
)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
uvicorn.run(app, host="0.0.0.0", port=8000)
|
||||
130
ToBeMigrated/ai_seo_tools/seo_structured_data.py
Normal file
130
ToBeMigrated/ai_seo_tools/seo_structured_data.py
Normal file
@@ -0,0 +1,130 @@
|
||||
import streamlit as st
|
||||
import json
|
||||
from datetime import date
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from ..ai_web_researcher.firecrawl_web_crawler import scrape_url
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
# Load environment variables
|
||||
load_dotenv()
|
||||
|
||||
# Define a dictionary for schema types
|
||||
schema_types = {
|
||||
"Article": {
|
||||
"fields": ["Headline", "Author", "Date Published", "Keywords"],
|
||||
"schema_type": "Article",
|
||||
},
|
||||
"Product": {
|
||||
"fields": ["Name", "Description", "Price", "Brand", "Image URL"],
|
||||
"schema_type": "Product",
|
||||
},
|
||||
"Recipe": {
|
||||
"fields": ["Name", "Ingredients", "Cooking Time", "Serving Size", "Image URL"],
|
||||
"schema_type": "Recipe",
|
||||
},
|
||||
"Event": {
|
||||
"fields": ["Name", "Start Date", "End Date", "Location", "Description"],
|
||||
"schema_type": "Event",
|
||||
},
|
||||
"LocalBusiness": {
|
||||
"fields": ["Name", "Address", "Phone Number", "Opening Hours", "Image URL"],
|
||||
"schema_type": "LocalBusiness",
|
||||
},
|
||||
# ... (add more schema types as needed)
|
||||
}
|
||||
|
||||
def generate_json_data(content_type, details, url):
|
||||
"""Generates structured data (JSON-LD) based on user input."""
|
||||
try:
|
||||
scraped_text = scrape_url(url)
|
||||
except Exception as err:
|
||||
st.error(f"Failed to scrape web page from URL: {url} - Error: {err}")
|
||||
return
|
||||
|
||||
schema = schema_types.get(content_type)
|
||||
if not schema:
|
||||
st.error(f"Invalid content type: {content_type}")
|
||||
return
|
||||
|
||||
data = {
|
||||
"@context": "https://schema.org",
|
||||
"@type": schema["schema_type"],
|
||||
}
|
||||
for field in schema["fields"]:
|
||||
value = details.get(field)
|
||||
if isinstance(value, date):
|
||||
value = value.isoformat()
|
||||
data[field] = value if value else "N/A" # Use placeholder values if input is missing
|
||||
|
||||
if url:
|
||||
data['url'] = url
|
||||
|
||||
llm_structured_data = get_llm_structured_data(content_type, data, scraped_text)
|
||||
return llm_structured_data
|
||||
|
||||
def get_llm_structured_data(content_type, data, scraped_text):
|
||||
"""Function to get structured data from LLM."""
|
||||
prompt = f"""Given the following information:
|
||||
|
||||
HTML Content: <<<HTML>>> {scraped_text} <<<END_HTML>>>
|
||||
Content Type: <<<CONTENT_TYPE>>> {content_type} <<<END_CONTENT_TYPE>>>
|
||||
Additional Relevant Data: <<<ADDITIONAL_DATA>>> {data} <<<END_ADDITIONAL_DATA>>>
|
||||
|
||||
Create a detailed structured data (JSON-LD) script for SEO purposes.
|
||||
The structured data should help search engines understand the content and features of the webpage, enhancing its visibility and potential for rich snippets in search results.
|
||||
|
||||
Detailed Steps:
|
||||
Parse the HTML content to extract relevant information like the title, main heading, and body content.
|
||||
Use the contentType to determine the structured data type (e.g., Article, Product, Recipe).
|
||||
Integrate the additional relevant data (e.g., author, datePublished, keywords) into the structured data.
|
||||
Ensure all URLs, images, and other attributes are correctly formatted and included.
|
||||
Validate the generated JSON-LD to ensure it meets schema.org standards and is free of errors.
|
||||
|
||||
Expected Output:
|
||||
Generate a JSON-LD structured data snippet based on the provided inputs."""
|
||||
|
||||
try:
|
||||
response = llm_text_gen(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
st.error(f"Failed to get response from LLM: {err}")
|
||||
return
|
||||
|
||||
def ai_structured_data():
|
||||
st.title("📝 Generate Structured Data for SEO 🚀")
|
||||
st.markdown("**Make your content more discoverable with rich snippets.**")
|
||||
|
||||
content_type = st.selectbox("**Select Content Type**", list(schema_types.keys()))
|
||||
|
||||
details = {}
|
||||
schema_fields = schema_types[content_type]["fields"]
|
||||
num_fields = len(schema_fields)
|
||||
|
||||
url = st.text_input("**URL :**", placeholder="Enter the URL of your webpage")
|
||||
for i in range(0, num_fields, 2):
|
||||
cols = st.columns(2)
|
||||
for j in range(2):
|
||||
if i + j < num_fields:
|
||||
field = schema_fields[i + j]
|
||||
if "Date" in field:
|
||||
details[field] = cols[j].date_input(field)
|
||||
else:
|
||||
details[field] = cols[j].text_input(field, placeholder=f"Enter {field.lower()}")
|
||||
|
||||
if st.button("Generate Structured Data"):
|
||||
if not url:
|
||||
st.error("URL is required to generate structured data.")
|
||||
return
|
||||
|
||||
structured_data = generate_json_data(content_type, details, url)
|
||||
if structured_data:
|
||||
st.subheader("Generated Structured Data (JSON-LD):")
|
||||
st.markdown(structured_data)
|
||||
|
||||
st.download_button(
|
||||
label="Download JSON-LD",
|
||||
data=structured_data,
|
||||
file_name=f"{content_type}_structured_data.json",
|
||||
mime="application/json",
|
||||
)
|
||||
340
ToBeMigrated/ai_seo_tools/sitemap_analysis.py
Normal file
340
ToBeMigrated/ai_seo_tools/sitemap_analysis.py
Normal file
@@ -0,0 +1,340 @@
|
||||
import streamlit as st
|
||||
import advertools as adv
|
||||
import pandas as pd
|
||||
import plotly.graph_objects as go
|
||||
from urllib.error import URLError
|
||||
import xml.etree.ElementTree as ET
|
||||
import requests
|
||||
|
||||
|
||||
def main():
|
||||
"""
|
||||
Main function to run the Sitemap Analyzer Streamlit app.
|
||||
"""
|
||||
st.title("📊 Sitemap Analyzer")
|
||||
st.write("""
|
||||
This tool analyzes a website's sitemap to understand its content structure and publishing trends.
|
||||
Enter a sitemap URL to start your analysis.
|
||||
""")
|
||||
|
||||
sitemap_url = st.text_input(
|
||||
"Please enter the sitemap URL:",
|
||||
"https://www.example.com/sitemap.xml"
|
||||
)
|
||||
|
||||
if st.button("Analyze Sitemap"):
|
||||
try:
|
||||
sitemap_df = fetch_all_sitemaps(sitemap_url)
|
||||
if sitemap_df is not None and not sitemap_df.empty:
|
||||
sitemap_df = process_lastmod_column(sitemap_df)
|
||||
ppmonth = analyze_content_trends(sitemap_df)
|
||||
sitemap_df = categorize_and_shorten_sitemaps(sitemap_df)
|
||||
|
||||
display_key_metrics(sitemap_df, ppmonth)
|
||||
plot_sitemap_content_distribution(sitemap_df)
|
||||
plot_content_trends(ppmonth)
|
||||
plot_content_type_breakdown(sitemap_df)
|
||||
plot_publishing_frequency(sitemap_df)
|
||||
|
||||
st.success("🎉 Analysis complete!")
|
||||
else:
|
||||
st.error("No valid URLs found in the sitemap.")
|
||||
except URLError as e:
|
||||
st.error(f"Error fetching the sitemap: {e}")
|
||||
except Exception as e:
|
||||
st.error(f"An unexpected error occurred: {e}")
|
||||
|
||||
|
||||
def fetch_all_sitemaps(sitemap_url):
|
||||
"""
|
||||
Fetches all sitemaps from the provided sitemap URL and concatenates their URLs into a DataFrame.
|
||||
|
||||
Parameters:
|
||||
sitemap_url (str): The URL of the sitemap.
|
||||
|
||||
Returns:
|
||||
DataFrame: A DataFrame containing all URLs from the sitemaps.
|
||||
"""
|
||||
st.write(f"🚀 Fetching and analyzing the sitemap: {sitemap_url}...")
|
||||
|
||||
try:
|
||||
sitemap_df = fetch_sitemap(sitemap_url)
|
||||
|
||||
if sitemap_df is not None:
|
||||
all_sitemaps = sitemap_df.loc[
|
||||
sitemap_df['loc'].str.contains('sitemap'),
|
||||
'loc'
|
||||
].tolist()
|
||||
|
||||
if all_sitemaps:
|
||||
st.write(
|
||||
f"🔄 Found {len(all_sitemaps)} additional sitemaps. Fetching data from them..."
|
||||
)
|
||||
all_urls_df = pd.DataFrame()
|
||||
|
||||
for sitemap in all_sitemaps:
|
||||
try:
|
||||
st.write(f"Fetching URLs from {sitemap}...")
|
||||
temp_df = fetch_sitemap(sitemap)
|
||||
if temp_df is not None:
|
||||
all_urls_df = pd.concat(
|
||||
[all_urls_df, temp_df], ignore_index=True
|
||||
)
|
||||
except Exception as e:
|
||||
st.error(f"Error fetching {sitemap}: {e}")
|
||||
|
||||
st.write(
|
||||
f"✅ Successfully fetched {len(all_urls_df)} URLs from all sitemaps."
|
||||
)
|
||||
return all_urls_df
|
||||
|
||||
else:
|
||||
st.write(f"✅ Successfully fetched {len(sitemap_df)} URLs from the main sitemap.")
|
||||
return sitemap_df
|
||||
else:
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error fetching the sitemap: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def fetch_sitemap(url):
|
||||
"""
|
||||
Fetches and parses the sitemap from the provided URL.
|
||||
|
||||
Parameters:
|
||||
url (str): The URL of the sitemap.
|
||||
|
||||
Returns:
|
||||
DataFrame: A DataFrame containing the URLs from the sitemap.
|
||||
"""
|
||||
try:
|
||||
response = requests.get(url)
|
||||
response.raise_for_status()
|
||||
|
||||
ET.fromstring(response.content)
|
||||
|
||||
sitemap_df = adv.sitemap_to_df(url)
|
||||
return sitemap_df
|
||||
|
||||
except requests.RequestException as e:
|
||||
st.error(f"⚠️ Request error: {e}")
|
||||
return None
|
||||
except ET.ParseError as e:
|
||||
st.error(f"⚠️ XML parsing error: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def process_lastmod_column(sitemap_df):
|
||||
"""
|
||||
Processes the 'lastmod' column in the sitemap DataFrame by converting it to DateTime format and setting it as the index.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
|
||||
Returns:
|
||||
DataFrame: The processed sitemap DataFrame with 'lastmod' as the index.
|
||||
"""
|
||||
st.write("📅 Converting 'lastmod' column to DateTime format and setting it as the index...")
|
||||
|
||||
try:
|
||||
sitemap_df = sitemap_df.dropna(subset=['lastmod'])
|
||||
sitemap_df['lastmod'] = pd.to_datetime(sitemap_df['lastmod'])
|
||||
sitemap_df.set_index('lastmod', inplace=True)
|
||||
|
||||
st.write("✅ 'lastmod' column successfully converted to DateTime format and set as the index.")
|
||||
return sitemap_df
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error processing the 'lastmod' column: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def categorize_and_shorten_sitemaps(sitemap_df):
|
||||
"""
|
||||
Categorizes and shortens the sitemap names in the sitemap DataFrame.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
|
||||
Returns:
|
||||
DataFrame: The sitemap DataFrame with categorized and shortened sitemap names.
|
||||
"""
|
||||
st.write("🔍 Categorizing and shortening sitemap names...")
|
||||
|
||||
try:
|
||||
sitemap_df['sitemap_name'] = sitemap_df['sitemap'].str.split('/').str[4]
|
||||
sitemap_df['sitemap_name'] = sitemap_df['sitemap_name'].replace({
|
||||
'sitemap-site-kasko-fiyatlari.xml': 'Kasko',
|
||||
'sitemap-site-bireysel.xml': 'Personal',
|
||||
'sitemap-site-kurumsal.xml': 'Cooperate',
|
||||
'sitemap-site-arac-sigortasi.xml': 'Car',
|
||||
'sitemap-site.xml': 'Others'
|
||||
})
|
||||
|
||||
st.write("✅ Sitemap names categorized and shortened.")
|
||||
return sitemap_df
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error categorizing sitemap names: {e}")
|
||||
return sitemap_df
|
||||
|
||||
|
||||
def analyze_content_trends(sitemap_df):
|
||||
"""
|
||||
Analyzes content publishing trends in the sitemap DataFrame.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
|
||||
Returns:
|
||||
Series: A Series representing the number of contents published each month.
|
||||
"""
|
||||
st.write("📅 Analyzing content publishing trends...")
|
||||
|
||||
try:
|
||||
ppmonth = sitemap_df.resample('M').size()
|
||||
sitemap_df['monthly_count'] = sitemap_df.index.to_period('M').value_counts().sort_index()
|
||||
|
||||
st.write("✅ Content trends analysis completed.")
|
||||
return ppmonth
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error during content trends analysis: {e}")
|
||||
return pd.Series()
|
||||
|
||||
|
||||
def display_key_metrics(sitemap_df, ppmonth):
|
||||
"""
|
||||
Displays key metrics of the sitemap analysis.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
ppmonth (Series): The Series representing the number of contents published each month.
|
||||
"""
|
||||
st.write("### Key Metrics")
|
||||
|
||||
total_urls = len(sitemap_df)
|
||||
total_articles = ppmonth.sum()
|
||||
average_frequency = ppmonth.mean()
|
||||
|
||||
st.write(f"**Total URLs Found:** {total_urls:,}")
|
||||
st.write(f"**Total Articles Published:** {total_articles:,}")
|
||||
st.write(f"**Average Monthly Publishing Frequency:** {average_frequency:.2f} articles/month")
|
||||
|
||||
|
||||
def plot_sitemap_content_distribution(sitemap_df):
|
||||
"""
|
||||
Plots the content distribution by sitemap categories.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
"""
|
||||
st.write("📊 Visualizing content amount by sitemap categories...")
|
||||
|
||||
try:
|
||||
if 'sitemap_name' in sitemap_df.columns:
|
||||
stmc = sitemap_df.groupby('sitemap_name').size()
|
||||
fig = go.Figure()
|
||||
fig.add_bar(x=stmc.index, y=stmc.values, name='Sitemap Categories')
|
||||
fig.update_layout(
|
||||
title='Content Amount by Sitemap Categories',
|
||||
xaxis_title='Sitemap Categories',
|
||||
yaxis_title='Number of Articles',
|
||||
paper_bgcolor='#E5ECF6'
|
||||
)
|
||||
st.plotly_chart(fig)
|
||||
else:
|
||||
st.warning("⚠️ The 'sitemap_name' column is missing in the data.")
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error during sitemap content distribution plotting: {e}")
|
||||
|
||||
|
||||
def plot_content_trends(ppmonth):
|
||||
"""
|
||||
Plots the content publishing trends over time.
|
||||
|
||||
Parameters:
|
||||
ppmonth (Series): The Series representing the number of contents published each month.
|
||||
"""
|
||||
st.write("📈 Plotting content publishing trends over time...")
|
||||
|
||||
try:
|
||||
fig = go.Figure()
|
||||
fig.add_scatter(x=ppmonth.index, y=ppmonth.values, mode='lines+markers', name='Publishing Trends')
|
||||
fig.update_layout(
|
||||
title='Content Publishing Trends Over Time',
|
||||
xaxis_title='Month',
|
||||
yaxis_title='Number of Articles',
|
||||
paper_bgcolor='#E5ECF6'
|
||||
)
|
||||
st.plotly_chart(fig)
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error during content trends plotting: {e}")
|
||||
|
||||
|
||||
def plot_content_type_breakdown(sitemap_df):
|
||||
"""
|
||||
Plots the content type breakdown.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
"""
|
||||
st.write("🔍 Plotting content type breakdown...")
|
||||
|
||||
try:
|
||||
if 'sitemap_name' in sitemap_df.columns and not sitemap_df['sitemap_name'].empty:
|
||||
content_type_counts = sitemap_df['sitemap_name'].value_counts()
|
||||
st.write("Content Type Counts:", content_type_counts)
|
||||
|
||||
if not content_type_counts.empty:
|
||||
fig = go.Figure(data=[go.Pie(labels=content_type_counts.index, values=content_type_counts.values)])
|
||||
fig.update_layout(
|
||||
title='Content Type Breakdown',
|
||||
paper_bgcolor='#E5ECF6'
|
||||
)
|
||||
st.plotly_chart(fig)
|
||||
else:
|
||||
st.warning("⚠️ No content types to display.")
|
||||
else:
|
||||
st.warning("⚠️ The 'sitemap_name' column is missing or empty.")
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error during content type breakdown plotting: {e}")
|
||||
|
||||
|
||||
def plot_publishing_frequency(sitemap_df):
|
||||
"""
|
||||
Plots the publishing frequency by month.
|
||||
|
||||
Parameters:
|
||||
sitemap_df (DataFrame): The sitemap DataFrame.
|
||||
"""
|
||||
st.write("📆 Plotting publishing frequency by month...")
|
||||
|
||||
try:
|
||||
if not sitemap_df.empty:
|
||||
frequency_by_month = sitemap_df.index.to_period('M').value_counts().sort_index()
|
||||
frequency_by_month.index = frequency_by_month.index.astype(str)
|
||||
|
||||
fig = go.Figure()
|
||||
fig.add_bar(x=frequency_by_month.index, y=frequency_by_month.values, name='Publishing Frequency')
|
||||
fig.update_layout(
|
||||
title='Publishing Frequency by Month',
|
||||
xaxis_title='Month',
|
||||
yaxis_title='Number of Articles',
|
||||
paper_bgcolor='#E5ECF6'
|
||||
)
|
||||
st.plotly_chart(fig)
|
||||
else:
|
||||
st.warning("⚠️ No data available to plot publishing frequency.")
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"⚠️ Error during publishing frequency plotting: {e}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
22
ToBeMigrated/ai_seo_tools/technical_seo_crawler/__init__.py
Normal file
22
ToBeMigrated/ai_seo_tools/technical_seo_crawler/__init__.py
Normal file
@@ -0,0 +1,22 @@
|
||||
"""
|
||||
Technical SEO Crawler Package.
|
||||
|
||||
This package provides comprehensive technical SEO analysis capabilities
|
||||
with advertools integration and AI-powered recommendations.
|
||||
|
||||
Components:
|
||||
- TechnicalSEOCrawler: Core crawler with technical analysis
|
||||
- TechnicalSEOCrawlerUI: Streamlit interface for the crawler
|
||||
"""
|
||||
|
||||
from .crawler import TechnicalSEOCrawler
|
||||
from .ui import TechnicalSEOCrawlerUI, render_technical_seo_crawler
|
||||
|
||||
__version__ = "1.0.0"
|
||||
__author__ = "ALwrity"
|
||||
|
||||
__all__ = [
|
||||
'TechnicalSEOCrawler',
|
||||
'TechnicalSEOCrawlerUI',
|
||||
'render_technical_seo_crawler'
|
||||
]
|
||||
709
ToBeMigrated/ai_seo_tools/technical_seo_crawler/crawler.py
Normal file
709
ToBeMigrated/ai_seo_tools/technical_seo_crawler/crawler.py
Normal file
@@ -0,0 +1,709 @@
|
||||
"""
|
||||
Comprehensive Technical SEO Crawler using Advertools Integration.
|
||||
|
||||
This module provides advanced site-wide technical SEO analysis using:
|
||||
- adv.crawl: Complete website crawling and analysis
|
||||
- adv.crawl_headers: HTTP headers and server analysis
|
||||
- adv.crawl_images: Image optimization analysis
|
||||
- adv.url_to_df: URL structure optimization
|
||||
- AI-powered technical recommendations
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import pandas as pd
|
||||
import advertools as adv
|
||||
from typing import Dict, Any, List, Optional, Tuple
|
||||
from urllib.parse import urlparse, urljoin
|
||||
import tempfile
|
||||
import os
|
||||
from datetime import datetime
|
||||
import json
|
||||
from collections import Counter, defaultdict
|
||||
from loguru import logger
|
||||
import numpy as np
|
||||
|
||||
# Import existing modules
|
||||
from lib.gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
from lib.utils.website_analyzer.analyzer import WebsiteAnalyzer
|
||||
|
||||
class TechnicalSEOCrawler:
|
||||
"""Comprehensive technical SEO crawler with advertools integration."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the technical SEO crawler."""
|
||||
self.temp_dir = tempfile.mkdtemp()
|
||||
logger.info("TechnicalSEOCrawler initialized")
|
||||
|
||||
def analyze_website_technical_seo(self, website_url: str, crawl_depth: int = 3,
|
||||
max_pages: int = 500) -> Dict[str, Any]:
|
||||
"""
|
||||
Perform comprehensive technical SEO analysis.
|
||||
|
||||
Args:
|
||||
website_url: Website URL to analyze
|
||||
crawl_depth: How deep to crawl (1-5)
|
||||
max_pages: Maximum pages to crawl (50-1000)
|
||||
|
||||
Returns:
|
||||
Comprehensive technical SEO analysis results
|
||||
"""
|
||||
try:
|
||||
st.info("🚀 Starting Comprehensive Technical SEO Crawl...")
|
||||
|
||||
# Initialize results structure
|
||||
results = {
|
||||
'analysis_timestamp': datetime.utcnow().isoformat(),
|
||||
'website_url': website_url,
|
||||
'crawl_settings': {
|
||||
'depth': crawl_depth,
|
||||
'max_pages': max_pages
|
||||
},
|
||||
'crawl_overview': {},
|
||||
'technical_issues': {},
|
||||
'performance_analysis': {},
|
||||
'content_analysis': {},
|
||||
'url_structure': {},
|
||||
'image_optimization': {},
|
||||
'security_headers': {},
|
||||
'mobile_seo': {},
|
||||
'structured_data': {},
|
||||
'ai_recommendations': {}
|
||||
}
|
||||
|
||||
# Phase 1: Core Website Crawl
|
||||
with st.expander("🕷️ Website Crawling Progress", expanded=True):
|
||||
crawl_data = self._perform_comprehensive_crawl(website_url, crawl_depth, max_pages)
|
||||
results['crawl_overview'] = crawl_data
|
||||
st.success(f"✅ Crawled {crawl_data.get('pages_crawled', 0)} pages")
|
||||
|
||||
# Phase 2: Technical Issues Detection
|
||||
with st.expander("🔍 Technical Issues Analysis", expanded=True):
|
||||
technical_issues = self._analyze_technical_issues(crawl_data)
|
||||
results['technical_issues'] = technical_issues
|
||||
st.success("✅ Identified technical SEO issues")
|
||||
|
||||
# Phase 3: Performance Analysis
|
||||
with st.expander("⚡ Performance Analysis", expanded=True):
|
||||
performance = self._analyze_performance_metrics(crawl_data)
|
||||
results['performance_analysis'] = performance
|
||||
st.success("✅ Analyzed website performance metrics")
|
||||
|
||||
# Phase 4: Content & Structure Analysis
|
||||
with st.expander("📊 Content Structure Analysis", expanded=True):
|
||||
content_analysis = self._analyze_content_structure(crawl_data)
|
||||
results['content_analysis'] = content_analysis
|
||||
st.success("✅ Analyzed content structure and optimization")
|
||||
|
||||
# Phase 5: URL Structure Optimization
|
||||
with st.expander("🔗 URL Structure Analysis", expanded=True):
|
||||
url_analysis = self._analyze_url_structure(crawl_data)
|
||||
results['url_structure'] = url_analysis
|
||||
st.success("✅ Analyzed URL structure and patterns")
|
||||
|
||||
# Phase 6: Image SEO Analysis
|
||||
with st.expander("🖼️ Image SEO Analysis", expanded=True):
|
||||
image_analysis = self._analyze_image_seo(website_url)
|
||||
results['image_optimization'] = image_analysis
|
||||
st.success("✅ Analyzed image optimization")
|
||||
|
||||
# Phase 7: Security & Headers Analysis
|
||||
with st.expander("🛡️ Security Headers Analysis", expanded=True):
|
||||
security_analysis = self._analyze_security_headers(website_url)
|
||||
results['security_headers'] = security_analysis
|
||||
st.success("✅ Analyzed security headers")
|
||||
|
||||
# Phase 8: Mobile SEO Analysis
|
||||
with st.expander("📱 Mobile SEO Analysis", expanded=True):
|
||||
mobile_analysis = self._analyze_mobile_seo(crawl_data)
|
||||
results['mobile_seo'] = mobile_analysis
|
||||
st.success("✅ Analyzed mobile SEO factors")
|
||||
|
||||
# Phase 9: AI-Powered Recommendations
|
||||
with st.expander("🤖 AI Technical Recommendations", expanded=True):
|
||||
ai_recommendations = self._generate_technical_recommendations(results)
|
||||
results['ai_recommendations'] = ai_recommendations
|
||||
st.success("✅ Generated AI-powered technical recommendations")
|
||||
|
||||
return results
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"Error in technical SEO analysis: {str(e)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
st.error(error_msg)
|
||||
return {'error': error_msg}
|
||||
|
||||
def _perform_comprehensive_crawl(self, website_url: str, depth: int, max_pages: int) -> Dict[str, Any]:
|
||||
"""Perform comprehensive website crawl using adv.crawl."""
|
||||
try:
|
||||
st.info("🕷️ Crawling website for comprehensive analysis...")
|
||||
|
||||
# Create crawl output file
|
||||
crawl_file = os.path.join(self.temp_dir, "technical_crawl.jl")
|
||||
|
||||
# Configure crawl settings for technical SEO
|
||||
custom_settings = {
|
||||
'DEPTH_LIMIT': depth,
|
||||
'CLOSESPIDER_PAGECOUNT': max_pages,
|
||||
'DOWNLOAD_DELAY': 0.5, # Be respectful
|
||||
'CONCURRENT_REQUESTS': 8,
|
||||
'ROBOTSTXT_OBEY': True,
|
||||
'USER_AGENT': 'ALwrity-TechnicalSEO-Crawler/1.0',
|
||||
'COOKIES_ENABLED': False,
|
||||
'TELNETCONSOLE_ENABLED': False,
|
||||
'LOG_LEVEL': 'WARNING'
|
||||
}
|
||||
|
||||
# Start crawl
|
||||
adv.crawl(
|
||||
url_list=[website_url],
|
||||
output_file=crawl_file,
|
||||
follow_links=True,
|
||||
custom_settings=custom_settings
|
||||
)
|
||||
|
||||
# Read and process crawl results
|
||||
if os.path.exists(crawl_file):
|
||||
crawl_df = pd.read_json(crawl_file, lines=True)
|
||||
|
||||
# Basic crawl statistics
|
||||
crawl_overview = {
|
||||
'pages_crawled': len(crawl_df),
|
||||
'status_codes': crawl_df['status'].value_counts().to_dict(),
|
||||
'crawl_file_path': crawl_file,
|
||||
'crawl_dataframe': crawl_df,
|
||||
'domains_found': crawl_df['url'].apply(lambda x: urlparse(x).netloc).nunique(),
|
||||
'avg_response_time': crawl_df.get('download_latency', pd.Series()).mean(),
|
||||
'total_content_size': crawl_df.get('size', pd.Series()).sum()
|
||||
}
|
||||
|
||||
return crawl_overview
|
||||
else:
|
||||
st.error("Crawl file not created")
|
||||
return {}
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error in website crawl: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_technical_issues(self, crawl_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze technical SEO issues from crawl data."""
|
||||
try:
|
||||
st.info("🔍 Detecting technical SEO issues...")
|
||||
|
||||
if 'crawl_dataframe' not in crawl_data:
|
||||
return {}
|
||||
|
||||
df = crawl_data['crawl_dataframe']
|
||||
|
||||
technical_issues = {
|
||||
'http_errors': {},
|
||||
'redirect_issues': {},
|
||||
'duplicate_content': {},
|
||||
'missing_elements': {},
|
||||
'page_speed_issues': {},
|
||||
'crawlability_issues': {}
|
||||
}
|
||||
|
||||
# HTTP Status Code Issues
|
||||
error_codes = df[df['status'] >= 400]['status'].value_counts().to_dict()
|
||||
technical_issues['http_errors'] = {
|
||||
'total_errors': len(df[df['status'] >= 400]),
|
||||
'error_breakdown': error_codes,
|
||||
'error_pages': df[df['status'] >= 400][['url', 'status']].to_dict('records')[:50]
|
||||
}
|
||||
|
||||
# Redirect Analysis
|
||||
redirects = df[df['status'].isin([301, 302, 303, 307, 308])]
|
||||
technical_issues['redirect_issues'] = {
|
||||
'total_redirects': len(redirects),
|
||||
'redirect_chains': self._find_redirect_chains(redirects),
|
||||
'redirect_types': redirects['status'].value_counts().to_dict()
|
||||
}
|
||||
|
||||
# Duplicate Content Detection
|
||||
if 'title' in df.columns:
|
||||
duplicate_titles = df['title'].value_counts()
|
||||
duplicate_titles = duplicate_titles[duplicate_titles > 1]
|
||||
|
||||
technical_issues['duplicate_content'] = {
|
||||
'duplicate_titles': len(duplicate_titles),
|
||||
'duplicate_title_groups': duplicate_titles.to_dict(),
|
||||
'pages_with_duplicate_titles': df[df['title'].isin(duplicate_titles.index)][['url', 'title']].to_dict('records')[:20]
|
||||
}
|
||||
|
||||
# Missing Elements Analysis
|
||||
missing_elements = {
|
||||
'missing_titles': len(df[(df['title'].isna()) | (df['title'] == '')]) if 'title' in df.columns else 0,
|
||||
'missing_meta_desc': len(df[(df['meta_desc'].isna()) | (df['meta_desc'] == '')]) if 'meta_desc' in df.columns else 0,
|
||||
'missing_h1': len(df[(df['h1'].isna()) | (df['h1'] == '')]) if 'h1' in df.columns else 0
|
||||
}
|
||||
technical_issues['missing_elements'] = missing_elements
|
||||
|
||||
# Page Speed Issues
|
||||
if 'download_latency' in df.columns:
|
||||
slow_pages = df[df['download_latency'] > 3.0] # Pages taking >3s
|
||||
technical_issues['page_speed_issues'] = {
|
||||
'slow_pages_count': len(slow_pages),
|
||||
'avg_load_time': df['download_latency'].mean(),
|
||||
'slowest_pages': slow_pages.nlargest(10, 'download_latency')[['url', 'download_latency']].to_dict('records')
|
||||
}
|
||||
|
||||
return technical_issues
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing technical issues: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_performance_metrics(self, crawl_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze website performance metrics."""
|
||||
try:
|
||||
st.info("⚡ Analyzing performance metrics...")
|
||||
|
||||
if 'crawl_dataframe' not in crawl_data:
|
||||
return {}
|
||||
|
||||
df = crawl_data['crawl_dataframe']
|
||||
|
||||
performance = {
|
||||
'load_time_analysis': {},
|
||||
'content_size_analysis': {},
|
||||
'server_performance': {},
|
||||
'optimization_opportunities': []
|
||||
}
|
||||
|
||||
# Load Time Analysis
|
||||
if 'download_latency' in df.columns:
|
||||
load_times = df['download_latency'].dropna()
|
||||
performance['load_time_analysis'] = {
|
||||
'avg_load_time': load_times.mean(),
|
||||
'median_load_time': load_times.median(),
|
||||
'p95_load_time': load_times.quantile(0.95),
|
||||
'fastest_page': load_times.min(),
|
||||
'slowest_page': load_times.max(),
|
||||
'pages_over_3s': len(load_times[load_times > 3]),
|
||||
'performance_distribution': {
|
||||
'fast_pages': len(load_times[load_times <= 1]),
|
||||
'moderate_pages': len(load_times[(load_times > 1) & (load_times <= 3)]),
|
||||
'slow_pages': len(load_times[load_times > 3])
|
||||
}
|
||||
}
|
||||
|
||||
# Content Size Analysis
|
||||
if 'size' in df.columns:
|
||||
sizes = df['size'].dropna()
|
||||
performance['content_size_analysis'] = {
|
||||
'avg_page_size': sizes.mean(),
|
||||
'median_page_size': sizes.median(),
|
||||
'largest_page': sizes.max(),
|
||||
'smallest_page': sizes.min(),
|
||||
'pages_over_1mb': len(sizes[sizes > 1048576]), # 1MB
|
||||
'total_content_size': sizes.sum()
|
||||
}
|
||||
|
||||
# Server Performance
|
||||
status_codes = df['status'].value_counts()
|
||||
total_pages = len(df)
|
||||
performance['server_performance'] = {
|
||||
'success_rate': status_codes.get(200, 0) / total_pages * 100,
|
||||
'error_rate': sum(status_codes.get(code, 0) for code in range(400, 600)) / total_pages * 100,
|
||||
'redirect_rate': sum(status_codes.get(code, 0) for code in [301, 302, 303, 307, 308]) / total_pages * 100
|
||||
}
|
||||
|
||||
return performance
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing performance: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_content_structure(self, crawl_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze content structure and SEO elements."""
|
||||
try:
|
||||
st.info("📊 Analyzing content structure...")
|
||||
|
||||
if 'crawl_dataframe' not in crawl_data:
|
||||
return {}
|
||||
|
||||
df = crawl_data['crawl_dataframe']
|
||||
|
||||
content_analysis = {
|
||||
'title_analysis': {},
|
||||
'meta_description_analysis': {},
|
||||
'heading_structure': {},
|
||||
'internal_linking': {},
|
||||
'content_optimization': {}
|
||||
}
|
||||
|
||||
# Title Analysis
|
||||
if 'title' in df.columns:
|
||||
titles = df['title'].dropna()
|
||||
title_lengths = titles.str.len()
|
||||
|
||||
content_analysis['title_analysis'] = {
|
||||
'avg_title_length': title_lengths.mean(),
|
||||
'title_length_distribution': {
|
||||
'too_short': len(title_lengths[title_lengths < 30]),
|
||||
'optimal': len(title_lengths[(title_lengths >= 30) & (title_lengths <= 60)]),
|
||||
'too_long': len(title_lengths[title_lengths > 60])
|
||||
},
|
||||
'duplicate_titles': len(titles.value_counts()[titles.value_counts() > 1]),
|
||||
'missing_titles': len(df) - len(titles)
|
||||
}
|
||||
|
||||
# Meta Description Analysis
|
||||
if 'meta_desc' in df.columns:
|
||||
meta_descs = df['meta_desc'].dropna()
|
||||
meta_lengths = meta_descs.str.len()
|
||||
|
||||
content_analysis['meta_description_analysis'] = {
|
||||
'avg_meta_length': meta_lengths.mean(),
|
||||
'meta_length_distribution': {
|
||||
'too_short': len(meta_lengths[meta_lengths < 120]),
|
||||
'optimal': len(meta_lengths[(meta_lengths >= 120) & (meta_lengths <= 160)]),
|
||||
'too_long': len(meta_lengths[meta_lengths > 160])
|
||||
},
|
||||
'missing_meta_descriptions': len(df) - len(meta_descs)
|
||||
}
|
||||
|
||||
# Heading Structure Analysis
|
||||
heading_cols = [col for col in df.columns if col.startswith('h') and col[1:].isdigit()]
|
||||
if heading_cols:
|
||||
heading_analysis = {}
|
||||
for col in heading_cols:
|
||||
headings = df[col].dropna()
|
||||
heading_analysis[f'{col}_usage'] = {
|
||||
'pages_with_heading': len(headings),
|
||||
'usage_rate': len(headings) / len(df) * 100,
|
||||
'avg_length': headings.str.len().mean() if len(headings) > 0 else 0
|
||||
}
|
||||
content_analysis['heading_structure'] = heading_analysis
|
||||
|
||||
# Internal Linking Analysis
|
||||
if 'links_internal' in df.columns:
|
||||
internal_links = df['links_internal'].apply(lambda x: len(x) if isinstance(x, list) else 0)
|
||||
content_analysis['internal_linking'] = {
|
||||
'avg_internal_links': internal_links.mean(),
|
||||
'pages_with_no_internal_links': len(internal_links[internal_links == 0]),
|
||||
'max_internal_links': internal_links.max(),
|
||||
'internal_link_distribution': internal_links.describe().to_dict()
|
||||
}
|
||||
|
||||
return content_analysis
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing content structure: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_url_structure(self, crawl_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze URL structure and optimization using adv.url_to_df."""
|
||||
try:
|
||||
st.info("🔗 Analyzing URL structure...")
|
||||
|
||||
if 'crawl_dataframe' not in crawl_data:
|
||||
return {}
|
||||
|
||||
df = crawl_data['crawl_dataframe']
|
||||
urls = df['url'].tolist()
|
||||
|
||||
# Use advertools to analyze URL structure
|
||||
url_df = adv.url_to_df(urls)
|
||||
|
||||
url_analysis = {
|
||||
'url_length_analysis': {},
|
||||
'url_structure_patterns': {},
|
||||
'url_optimization': {},
|
||||
'path_analysis': {}
|
||||
}
|
||||
|
||||
# URL Length Analysis
|
||||
url_lengths = url_df['url'].str.len()
|
||||
url_analysis['url_length_analysis'] = {
|
||||
'avg_url_length': url_lengths.mean(),
|
||||
'max_url_length': url_lengths.max(),
|
||||
'long_urls_count': len(url_lengths[url_lengths > 100]),
|
||||
'url_length_distribution': url_lengths.describe().to_dict()
|
||||
}
|
||||
|
||||
# Path Depth Analysis
|
||||
if 'dir_1' in url_df.columns:
|
||||
path_depths = url_df.apply(lambda row: sum(1 for i in range(1, 10) if f'dir_{i}' in row and pd.notna(row[f'dir_{i}'])), axis=1)
|
||||
url_analysis['path_analysis'] = {
|
||||
'avg_path_depth': path_depths.mean(),
|
||||
'max_path_depth': path_depths.max(),
|
||||
'deep_paths_count': len(path_depths[path_depths > 4]),
|
||||
'path_depth_distribution': path_depths.value_counts().to_dict()
|
||||
}
|
||||
|
||||
# URL Structure Patterns
|
||||
domains = url_df['netloc'].value_counts()
|
||||
schemes = url_df['scheme'].value_counts()
|
||||
|
||||
url_analysis['url_structure_patterns'] = {
|
||||
'domains_found': domains.to_dict(),
|
||||
'schemes_used': schemes.to_dict(),
|
||||
'subdomain_usage': len(url_df[url_df['netloc'].str.contains('\.', regex=True)]),
|
||||
'https_usage': schemes.get('https', 0) / len(url_df) * 100
|
||||
}
|
||||
|
||||
# URL Optimization Issues
|
||||
optimization_issues = []
|
||||
|
||||
# Check for non-HTTPS URLs
|
||||
if schemes.get('http', 0) > 0:
|
||||
optimization_issues.append(f"{schemes.get('http', 0)} pages not using HTTPS")
|
||||
|
||||
# Check for long URLs
|
||||
long_urls = len(url_lengths[url_lengths > 100])
|
||||
if long_urls > 0:
|
||||
optimization_issues.append(f"{long_urls} URLs are too long (>100 characters)")
|
||||
|
||||
# Check for deep paths
|
||||
if 'path_analysis' in url_analysis:
|
||||
deep_paths = url_analysis['path_analysis']['deep_paths_count']
|
||||
if deep_paths > 0:
|
||||
optimization_issues.append(f"{deep_paths} URLs have deep path structures (>4 levels)")
|
||||
|
||||
url_analysis['url_optimization'] = {
|
||||
'issues_found': len(optimization_issues),
|
||||
'optimization_recommendations': optimization_issues
|
||||
}
|
||||
|
||||
return url_analysis
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing URL structure: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_image_seo(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Analyze image SEO using adv.crawl_images."""
|
||||
try:
|
||||
st.info("🖼️ Analyzing image SEO...")
|
||||
|
||||
# Create image crawl output file
|
||||
image_file = os.path.join(self.temp_dir, "image_crawl.jl")
|
||||
|
||||
# Crawl images
|
||||
adv.crawl_images(
|
||||
url_list=[website_url],
|
||||
output_file=image_file,
|
||||
custom_settings={
|
||||
'DEPTH_LIMIT': 2,
|
||||
'CLOSESPIDER_PAGECOUNT': 100,
|
||||
'DOWNLOAD_DELAY': 1
|
||||
}
|
||||
)
|
||||
|
||||
image_analysis = {
|
||||
'image_count': 0,
|
||||
'alt_text_analysis': {},
|
||||
'image_format_analysis': {},
|
||||
'image_size_analysis': {},
|
||||
'optimization_opportunities': []
|
||||
}
|
||||
|
||||
if os.path.exists(image_file):
|
||||
image_df = pd.read_json(image_file, lines=True)
|
||||
|
||||
image_analysis['image_count'] = len(image_df)
|
||||
|
||||
# Alt text analysis
|
||||
if 'img_alt' in image_df.columns:
|
||||
alt_texts = image_df['img_alt'].dropna()
|
||||
missing_alt = len(image_df) - len(alt_texts)
|
||||
|
||||
image_analysis['alt_text_analysis'] = {
|
||||
'images_with_alt': len(alt_texts),
|
||||
'images_missing_alt': missing_alt,
|
||||
'alt_text_coverage': len(alt_texts) / len(image_df) * 100,
|
||||
'avg_alt_length': alt_texts.str.len().mean() if len(alt_texts) > 0 else 0
|
||||
}
|
||||
|
||||
# Image format analysis
|
||||
if 'img_src' in image_df.columns:
|
||||
# Extract file extensions
|
||||
extensions = image_df['img_src'].str.extract(r'\.([a-zA-Z]{2,4})(?:\?|$)')
|
||||
format_counts = extensions[0].value_counts()
|
||||
|
||||
image_analysis['image_format_analysis'] = {
|
||||
'format_distribution': format_counts.to_dict(),
|
||||
'modern_format_usage': format_counts.get('webp', 0) + format_counts.get('avif', 0)
|
||||
}
|
||||
|
||||
return image_analysis
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing images: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_security_headers(self, website_url: str) -> Dict[str, Any]:
|
||||
"""Analyze security headers using adv.crawl_headers."""
|
||||
try:
|
||||
st.info("🛡️ Analyzing security headers...")
|
||||
|
||||
# Create headers output file
|
||||
headers_file = os.path.join(self.temp_dir, "security_headers.jl")
|
||||
|
||||
# Crawl headers
|
||||
adv.crawl_headers([website_url], output_file=headers_file)
|
||||
|
||||
security_analysis = {
|
||||
'security_headers_present': {},
|
||||
'security_score': 0,
|
||||
'security_recommendations': []
|
||||
}
|
||||
|
||||
if os.path.exists(headers_file):
|
||||
headers_df = pd.read_json(headers_file, lines=True)
|
||||
|
||||
# Check for important security headers
|
||||
security_headers = {
|
||||
'X-Frame-Options': 'resp_headers_X-Frame-Options',
|
||||
'X-Content-Type-Options': 'resp_headers_X-Content-Type-Options',
|
||||
'X-XSS-Protection': 'resp_headers_X-XSS-Protection',
|
||||
'Strict-Transport-Security': 'resp_headers_Strict-Transport-Security',
|
||||
'Content-Security-Policy': 'resp_headers_Content-Security-Policy',
|
||||
'Referrer-Policy': 'resp_headers_Referrer-Policy'
|
||||
}
|
||||
|
||||
headers_present = {}
|
||||
for header_name, column_name in security_headers.items():
|
||||
is_present = column_name in headers_df.columns and headers_df[column_name].notna().any()
|
||||
headers_present[header_name] = is_present
|
||||
|
||||
security_analysis['security_headers_present'] = headers_present
|
||||
|
||||
# Calculate security score
|
||||
present_count = sum(headers_present.values())
|
||||
security_analysis['security_score'] = (present_count / len(security_headers)) * 100
|
||||
|
||||
# Generate recommendations
|
||||
recommendations = []
|
||||
for header_name, is_present in headers_present.items():
|
||||
if not is_present:
|
||||
recommendations.append(f"Add {header_name} header for improved security")
|
||||
|
||||
security_analysis['security_recommendations'] = recommendations
|
||||
|
||||
return security_analysis
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing security headers: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _analyze_mobile_seo(self, crawl_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze mobile SEO factors."""
|
||||
try:
|
||||
st.info("📱 Analyzing mobile SEO factors...")
|
||||
|
||||
if 'crawl_dataframe' not in crawl_data:
|
||||
return {}
|
||||
|
||||
df = crawl_data['crawl_dataframe']
|
||||
|
||||
mobile_analysis = {
|
||||
'viewport_analysis': {},
|
||||
'mobile_optimization': {},
|
||||
'responsive_design_indicators': {}
|
||||
}
|
||||
|
||||
# Viewport meta tag analysis
|
||||
if 'viewport' in df.columns:
|
||||
viewport_present = df['viewport'].notna().sum()
|
||||
mobile_analysis['viewport_analysis'] = {
|
||||
'pages_with_viewport': viewport_present,
|
||||
'viewport_coverage': viewport_present / len(df) * 100,
|
||||
'pages_missing_viewport': len(df) - viewport_present
|
||||
}
|
||||
|
||||
# Check for mobile-specific meta tags and indicators
|
||||
mobile_indicators = []
|
||||
|
||||
# Check for touch icons
|
||||
if any('touch-icon' in col for col in df.columns):
|
||||
mobile_indicators.append("Touch icons configured")
|
||||
|
||||
# Check for responsive design indicators in content
|
||||
# This is a simplified check - in practice, you'd analyze CSS and page structure
|
||||
mobile_analysis['mobile_optimization'] = {
|
||||
'mobile_indicators_found': len(mobile_indicators),
|
||||
'mobile_indicators': mobile_indicators
|
||||
}
|
||||
|
||||
return mobile_analysis
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error analyzing mobile SEO: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _generate_technical_recommendations(self, results: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Generate AI-powered technical SEO recommendations."""
|
||||
try:
|
||||
st.info("🤖 Generating technical recommendations...")
|
||||
|
||||
# Prepare technical analysis summary for AI
|
||||
technical_summary = {
|
||||
'website_url': results.get('website_url', ''),
|
||||
'pages_crawled': results.get('crawl_overview', {}).get('pages_crawled', 0),
|
||||
'error_count': results.get('technical_issues', {}).get('http_errors', {}).get('total_errors', 0),
|
||||
'avg_load_time': results.get('performance_analysis', {}).get('load_time_analysis', {}).get('avg_load_time', 0),
|
||||
'security_score': results.get('security_headers', {}).get('security_score', 0),
|
||||
'missing_titles': results.get('content_analysis', {}).get('title_analysis', {}).get('missing_titles', 0),
|
||||
'missing_meta_desc': results.get('content_analysis', {}).get('meta_description_analysis', {}).get('missing_meta_descriptions', 0)
|
||||
}
|
||||
|
||||
# Generate AI recommendations
|
||||
prompt = f"""
|
||||
As a technical SEO expert, analyze this comprehensive website audit and provide prioritized recommendations:
|
||||
|
||||
WEBSITE: {technical_summary['website_url']}
|
||||
PAGES ANALYZED: {technical_summary['pages_crawled']}
|
||||
|
||||
TECHNICAL ISSUES:
|
||||
- HTTP Errors: {technical_summary['error_count']}
|
||||
- Average Load Time: {technical_summary['avg_load_time']:.2f}s
|
||||
- Security Score: {technical_summary['security_score']:.1f}%
|
||||
- Missing Titles: {technical_summary['missing_titles']}
|
||||
- Missing Meta Descriptions: {technical_summary['missing_meta_desc']}
|
||||
|
||||
PROVIDE:
|
||||
1. Critical Issues (Fix Immediately)
|
||||
2. High Priority Optimizations
|
||||
3. Medium Priority Improvements
|
||||
4. Long-term Technical Strategy
|
||||
5. Specific Implementation Steps
|
||||
6. Expected Impact Assessment
|
||||
|
||||
Format as JSON with clear priorities and actionable recommendations.
|
||||
"""
|
||||
|
||||
ai_response = llm_text_gen(
|
||||
prompt=prompt,
|
||||
system_prompt="You are a senior technical SEO specialist with expertise in website optimization, Core Web Vitals, and search engine best practices.",
|
||||
response_format="json_object"
|
||||
)
|
||||
|
||||
if ai_response:
|
||||
return ai_response
|
||||
else:
|
||||
return {'recommendations': ['AI recommendations temporarily unavailable']}
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"Error generating recommendations: {str(e)}")
|
||||
return {}
|
||||
|
||||
def _find_redirect_chains(self, redirects_df: pd.DataFrame) -> List[Dict[str, Any]]:
|
||||
"""Find redirect chains in the crawled data."""
|
||||
# Simplified redirect chain detection
|
||||
# In a full implementation, you'd trace the redirect paths
|
||||
redirect_chains = []
|
||||
|
||||
if len(redirects_df) > 0:
|
||||
# Group redirects by status code
|
||||
for status_code in redirects_df['status'].unique():
|
||||
status_redirects = redirects_df[redirects_df['status'] == status_code]
|
||||
redirect_chains.append({
|
||||
'status_code': int(status_code),
|
||||
'count': len(status_redirects),
|
||||
'examples': status_redirects['url'].head(5).tolist()
|
||||
})
|
||||
|
||||
return redirect_chains
|
||||
968
ToBeMigrated/ai_seo_tools/technical_seo_crawler/ui.py
Normal file
968
ToBeMigrated/ai_seo_tools/technical_seo_crawler/ui.py
Normal file
@@ -0,0 +1,968 @@
|
||||
"""
|
||||
Technical SEO Crawler UI with Comprehensive Analysis Dashboard.
|
||||
|
||||
This module provides a professional Streamlit interface for the Technical SEO Crawler
|
||||
with detailed analysis results, visualization, and export capabilities.
|
||||
"""
|
||||
|
||||
import streamlit as st
|
||||
import pandas as pd
|
||||
from typing import Dict, Any, List
|
||||
import json
|
||||
from datetime import datetime
|
||||
import io
|
||||
import base64
|
||||
import plotly.express as px
|
||||
import plotly.graph_objects as go
|
||||
from plotly.subplots import make_subplots
|
||||
|
||||
from .crawler import TechnicalSEOCrawler
|
||||
from lib.alwrity_ui.dashboard_styles import apply_dashboard_style, render_dashboard_header
|
||||
|
||||
class TechnicalSEOCrawlerUI:
|
||||
"""Professional UI for Technical SEO Crawler."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the Technical SEO Crawler UI."""
|
||||
self.crawler = TechnicalSEOCrawler()
|
||||
|
||||
# Apply dashboard styling
|
||||
apply_dashboard_style()
|
||||
|
||||
def render(self):
|
||||
"""Render the Technical SEO Crawler interface."""
|
||||
|
||||
# Enhanced dashboard header
|
||||
render_dashboard_header(
|
||||
"🔧 Technical SEO Crawler",
|
||||
"Comprehensive site-wide technical SEO analysis with AI-powered recommendations. Identify and fix technical issues that impact your search rankings."
|
||||
)
|
||||
|
||||
# Main content area
|
||||
with st.container():
|
||||
# Analysis input form
|
||||
self._render_crawler_form()
|
||||
|
||||
# Session state for results
|
||||
if 'technical_seo_results' in st.session_state and st.session_state.technical_seo_results:
|
||||
st.markdown("---")
|
||||
self._render_results_dashboard(st.session_state.technical_seo_results)
|
||||
|
||||
def _render_crawler_form(self):
|
||||
"""Render the crawler configuration form."""
|
||||
st.markdown("## 🚀 Configure Technical SEO Audit")
|
||||
|
||||
with st.form("technical_seo_crawler_form"):
|
||||
# Website URL input
|
||||
col1, col2 = st.columns([3, 1])
|
||||
|
||||
with col1:
|
||||
website_url = st.text_input(
|
||||
"🌐 Website URL to Audit",
|
||||
placeholder="https://yourwebsite.com",
|
||||
help="Enter the website URL for comprehensive technical SEO analysis"
|
||||
)
|
||||
|
||||
with col2:
|
||||
audit_type = st.selectbox(
|
||||
"🎯 Audit Type",
|
||||
options=["Standard", "Deep", "Quick"],
|
||||
help="Choose the depth of analysis"
|
||||
)
|
||||
|
||||
# Crawl configuration
|
||||
st.markdown("### ⚙️ Crawl Configuration")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
if audit_type == "Quick":
|
||||
crawl_depth = st.slider("Crawl Depth", 1, 2, 1)
|
||||
max_pages = st.slider("Max Pages", 10, 100, 50)
|
||||
elif audit_type == "Deep":
|
||||
crawl_depth = st.slider("Crawl Depth", 1, 5, 4)
|
||||
max_pages = st.slider("Max Pages", 100, 1000, 500)
|
||||
else: # Standard
|
||||
crawl_depth = st.slider("Crawl Depth", 1, 4, 3)
|
||||
max_pages = st.slider("Max Pages", 50, 500, 200)
|
||||
|
||||
with col2:
|
||||
analyze_images = st.checkbox(
|
||||
"🖼️ Analyze Images",
|
||||
value=True,
|
||||
help="Include image SEO analysis"
|
||||
)
|
||||
|
||||
analyze_security = st.checkbox(
|
||||
"🛡️ Security Headers",
|
||||
value=True,
|
||||
help="Analyze security headers"
|
||||
)
|
||||
|
||||
with col3:
|
||||
analyze_mobile = st.checkbox(
|
||||
"📱 Mobile SEO",
|
||||
value=True,
|
||||
help="Include mobile SEO analysis"
|
||||
)
|
||||
|
||||
ai_recommendations = st.checkbox(
|
||||
"🤖 AI Recommendations",
|
||||
value=True,
|
||||
help="Generate AI-powered recommendations"
|
||||
)
|
||||
|
||||
# Analysis scope
|
||||
st.markdown("### 🎯 Analysis Scope")
|
||||
|
||||
analysis_options = st.multiselect(
|
||||
"Select Analysis Components",
|
||||
options=[
|
||||
"Technical Issues Detection",
|
||||
"Performance Analysis",
|
||||
"Content Structure Analysis",
|
||||
"URL Structure Optimization",
|
||||
"Internal Linking Analysis",
|
||||
"Duplicate Content Detection"
|
||||
],
|
||||
default=[
|
||||
"Technical Issues Detection",
|
||||
"Performance Analysis",
|
||||
"Content Structure Analysis"
|
||||
],
|
||||
help="Choose which analysis components to include"
|
||||
)
|
||||
|
||||
# Submit button
|
||||
submitted = st.form_submit_button(
|
||||
"🚀 Start Technical SEO Audit",
|
||||
use_container_width=True,
|
||||
type="primary"
|
||||
)
|
||||
|
||||
if submitted:
|
||||
# Validate inputs
|
||||
if not website_url or not website_url.startswith(('http://', 'https://')):
|
||||
st.error("❌ Please enter a valid website URL starting with http:// or https://")
|
||||
return
|
||||
|
||||
# Run technical SEO analysis
|
||||
self._run_technical_analysis(
|
||||
website_url=website_url,
|
||||
crawl_depth=crawl_depth,
|
||||
max_pages=max_pages,
|
||||
options={
|
||||
'analyze_images': analyze_images,
|
||||
'analyze_security': analyze_security,
|
||||
'analyze_mobile': analyze_mobile,
|
||||
'ai_recommendations': ai_recommendations,
|
||||
'analysis_scope': analysis_options
|
||||
}
|
||||
)
|
||||
|
||||
def _run_technical_analysis(self, website_url: str, crawl_depth: int,
|
||||
max_pages: int, options: Dict[str, Any]):
|
||||
"""Run the technical SEO analysis."""
|
||||
|
||||
try:
|
||||
with st.spinner("🔄 Running Comprehensive Technical SEO Audit..."):
|
||||
|
||||
# Initialize progress tracking
|
||||
progress_bar = st.progress(0)
|
||||
status_text = st.empty()
|
||||
|
||||
# Update progress
|
||||
progress_bar.progress(10)
|
||||
status_text.text("🚀 Initializing technical SEO crawler...")
|
||||
|
||||
# Run comprehensive analysis
|
||||
results = self.crawler.analyze_website_technical_seo(
|
||||
website_url=website_url,
|
||||
crawl_depth=crawl_depth,
|
||||
max_pages=max_pages
|
||||
)
|
||||
|
||||
progress_bar.progress(100)
|
||||
status_text.text("✅ Technical SEO audit complete!")
|
||||
|
||||
# Store results in session state
|
||||
st.session_state.technical_seo_results = results
|
||||
|
||||
# Clear progress indicators
|
||||
progress_bar.empty()
|
||||
status_text.empty()
|
||||
|
||||
if 'error' in results:
|
||||
st.error(f"❌ Analysis failed: {results['error']}")
|
||||
else:
|
||||
st.success("🎉 Technical SEO Audit completed successfully!")
|
||||
st.balloons()
|
||||
|
||||
# Rerun to show results
|
||||
st.rerun()
|
||||
|
||||
except Exception as e:
|
||||
st.error(f"❌ Error running technical analysis: {str(e)}")
|
||||
|
||||
def _render_results_dashboard(self, results: Dict[str, Any]):
|
||||
"""Render the comprehensive results dashboard."""
|
||||
|
||||
if 'error' in results:
|
||||
st.error(f"❌ Analysis Error: {results['error']}")
|
||||
return
|
||||
|
||||
# Results header
|
||||
st.markdown("## 📊 Technical SEO Audit Results")
|
||||
|
||||
# Key metrics overview
|
||||
self._render_metrics_overview(results)
|
||||
|
||||
# Detailed analysis tabs
|
||||
self._render_detailed_analysis(results)
|
||||
|
||||
# Export functionality
|
||||
self._render_export_options(results)
|
||||
|
||||
def _render_metrics_overview(self, results: Dict[str, Any]):
|
||||
"""Render key metrics overview."""
|
||||
|
||||
st.markdown("### 📈 Audit Overview")
|
||||
|
||||
# Create metrics columns
|
||||
col1, col2, col3, col4, col5, col6 = st.columns(6)
|
||||
|
||||
with col1:
|
||||
pages_crawled = results.get('crawl_overview', {}).get('pages_crawled', 0)
|
||||
st.metric(
|
||||
"🕷️ Pages Crawled",
|
||||
pages_crawled,
|
||||
help="Total pages analyzed"
|
||||
)
|
||||
|
||||
with col2:
|
||||
error_count = results.get('technical_issues', {}).get('http_errors', {}).get('total_errors', 0)
|
||||
st.metric(
|
||||
"❌ HTTP Errors",
|
||||
error_count,
|
||||
delta=f"-{error_count}" if error_count > 0 else None,
|
||||
help="Pages with HTTP errors (4xx, 5xx)"
|
||||
)
|
||||
|
||||
with col3:
|
||||
avg_load_time = results.get('performance_analysis', {}).get('load_time_analysis', {}).get('avg_load_time', 0)
|
||||
st.metric(
|
||||
"⚡ Avg Load Time",
|
||||
f"{avg_load_time:.2f}s",
|
||||
delta=f"+{avg_load_time:.2f}s" if avg_load_time > 3 else None,
|
||||
help="Average page load time"
|
||||
)
|
||||
|
||||
with col4:
|
||||
security_score = results.get('security_headers', {}).get('security_score', 0)
|
||||
st.metric(
|
||||
"🛡️ Security Score",
|
||||
f"{security_score:.0f}%",
|
||||
delta=f"{security_score:.0f}%" if security_score < 100 else None,
|
||||
help="Security headers implementation score"
|
||||
)
|
||||
|
||||
with col5:
|
||||
missing_titles = results.get('content_analysis', {}).get('title_analysis', {}).get('missing_titles', 0)
|
||||
st.metric(
|
||||
"📝 Missing Titles",
|
||||
missing_titles,
|
||||
delta=f"-{missing_titles}" if missing_titles > 0 else None,
|
||||
help="Pages without title tags"
|
||||
)
|
||||
|
||||
with col6:
|
||||
image_count = results.get('image_optimization', {}).get('image_count', 0)
|
||||
st.metric(
|
||||
"🖼️ Images Analyzed",
|
||||
image_count,
|
||||
help="Total images found and analyzed"
|
||||
)
|
||||
|
||||
# Analysis timestamp
|
||||
if results.get('analysis_timestamp'):
|
||||
timestamp = datetime.fromisoformat(results['analysis_timestamp'].replace('Z', '+00:00'))
|
||||
st.caption(f"📅 Audit completed: {timestamp.strftime('%Y-%m-%d %H:%M:%S UTC')}")
|
||||
|
||||
def _render_detailed_analysis(self, results: Dict[str, Any]):
|
||||
"""Render detailed analysis in tabs."""
|
||||
|
||||
# Create main analysis tabs
|
||||
tab1, tab2, tab3, tab4, tab5, tab6, tab7 = st.tabs([
|
||||
"🔍 Technical Issues",
|
||||
"⚡ Performance",
|
||||
"📊 Content Analysis",
|
||||
"🔗 URL Structure",
|
||||
"🖼️ Image SEO",
|
||||
"🛡️ Security",
|
||||
"🤖 AI Recommendations"
|
||||
])
|
||||
|
||||
with tab1:
|
||||
self._render_technical_issues(results.get('technical_issues', {}))
|
||||
|
||||
with tab2:
|
||||
self._render_performance_analysis(results.get('performance_analysis', {}))
|
||||
|
||||
with tab3:
|
||||
self._render_content_analysis(results.get('content_analysis', {}))
|
||||
|
||||
with tab4:
|
||||
self._render_url_structure(results.get('url_structure', {}))
|
||||
|
||||
with tab5:
|
||||
self._render_image_analysis(results.get('image_optimization', {}))
|
||||
|
||||
with tab6:
|
||||
self._render_security_analysis(results.get('security_headers', {}))
|
||||
|
||||
with tab7:
|
||||
self._render_ai_recommendations(results.get('ai_recommendations', {}))
|
||||
|
||||
def _render_technical_issues(self, technical_data: Dict[str, Any]):
|
||||
"""Render technical issues analysis."""
|
||||
|
||||
st.markdown("### 🔍 Technical SEO Issues")
|
||||
|
||||
if not technical_data:
|
||||
st.info("No technical issues data available")
|
||||
return
|
||||
|
||||
# HTTP Errors
|
||||
if technical_data.get('http_errors'):
|
||||
http_errors = technical_data['http_errors']
|
||||
|
||||
st.markdown("#### ❌ HTTP Status Code Errors")
|
||||
|
||||
if http_errors.get('total_errors', 0) > 0:
|
||||
st.error(f"Found {http_errors['total_errors']} pages with HTTP errors!")
|
||||
|
||||
# Error breakdown chart
|
||||
if http_errors.get('error_breakdown'):
|
||||
error_df = pd.DataFrame(
|
||||
list(http_errors['error_breakdown'].items()),
|
||||
columns=['Status Code', 'Count']
|
||||
)
|
||||
|
||||
fig = px.bar(error_df, x='Status Code', y='Count',
|
||||
title="HTTP Error Distribution")
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
# Error pages table
|
||||
if http_errors.get('error_pages'):
|
||||
st.markdown("**Pages with Errors:**")
|
||||
error_pages_df = pd.DataFrame(http_errors['error_pages'])
|
||||
st.dataframe(error_pages_df, use_container_width=True)
|
||||
else:
|
||||
st.success("✅ No HTTP errors found!")
|
||||
|
||||
# Redirect Issues
|
||||
if technical_data.get('redirect_issues'):
|
||||
redirect_data = technical_data['redirect_issues']
|
||||
|
||||
st.markdown("#### 🔄 Redirect Analysis")
|
||||
|
||||
total_redirects = redirect_data.get('total_redirects', 0)
|
||||
|
||||
if total_redirects > 0:
|
||||
st.warning(f"Found {total_redirects} redirect(s)")
|
||||
|
||||
# Redirect types
|
||||
if redirect_data.get('redirect_types'):
|
||||
redirect_df = pd.DataFrame(
|
||||
list(redirect_data['redirect_types'].items()),
|
||||
columns=['Redirect Type', 'Count']
|
||||
)
|
||||
st.bar_chart(redirect_df.set_index('Redirect Type'))
|
||||
else:
|
||||
st.success("✅ No redirects found")
|
||||
|
||||
# Duplicate Content
|
||||
if technical_data.get('duplicate_content'):
|
||||
duplicate_data = technical_data['duplicate_content']
|
||||
|
||||
st.markdown("#### 📋 Duplicate Content Issues")
|
||||
|
||||
duplicate_titles = duplicate_data.get('duplicate_titles', 0)
|
||||
|
||||
if duplicate_titles > 0:
|
||||
st.warning(f"Found {duplicate_titles} duplicate title(s)")
|
||||
|
||||
# Show duplicate title groups
|
||||
if duplicate_data.get('pages_with_duplicate_titles'):
|
||||
duplicate_df = pd.DataFrame(duplicate_data['pages_with_duplicate_titles'])
|
||||
st.dataframe(duplicate_df, use_container_width=True)
|
||||
else:
|
||||
st.success("✅ No duplicate titles found")
|
||||
|
||||
# Missing Elements
|
||||
if technical_data.get('missing_elements'):
|
||||
missing_data = technical_data['missing_elements']
|
||||
|
||||
st.markdown("#### 📝 Missing SEO Elements")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
missing_titles = missing_data.get('missing_titles', 0)
|
||||
if missing_titles > 0:
|
||||
st.error(f"Missing Titles: {missing_titles}")
|
||||
else:
|
||||
st.success("All pages have titles ✅")
|
||||
|
||||
with col2:
|
||||
missing_meta = missing_data.get('missing_meta_desc', 0)
|
||||
if missing_meta > 0:
|
||||
st.error(f"Missing Meta Descriptions: {missing_meta}")
|
||||
else:
|
||||
st.success("All pages have meta descriptions ✅")
|
||||
|
||||
with col3:
|
||||
missing_h1 = missing_data.get('missing_h1', 0)
|
||||
if missing_h1 > 0:
|
||||
st.error(f"Missing H1 tags: {missing_h1}")
|
||||
else:
|
||||
st.success("All pages have H1 tags ✅")
|
||||
|
||||
def _render_performance_analysis(self, performance_data: Dict[str, Any]):
|
||||
"""Render performance analysis."""
|
||||
|
||||
st.markdown("### ⚡ Website Performance Analysis")
|
||||
|
||||
if not performance_data:
|
||||
st.info("No performance data available")
|
||||
return
|
||||
|
||||
# Load Time Analysis
|
||||
if performance_data.get('load_time_analysis'):
|
||||
load_time_data = performance_data['load_time_analysis']
|
||||
|
||||
st.markdown("#### 🚀 Page Load Time Analysis")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
avg_load = load_time_data.get('avg_load_time', 0)
|
||||
st.metric("Average Load Time", f"{avg_load:.2f}s")
|
||||
|
||||
with col2:
|
||||
median_load = load_time_data.get('median_load_time', 0)
|
||||
st.metric("Median Load Time", f"{median_load:.2f}s")
|
||||
|
||||
with col3:
|
||||
p95_load = load_time_data.get('p95_load_time', 0)
|
||||
st.metric("95th Percentile", f"{p95_load:.2f}s")
|
||||
|
||||
# Performance distribution
|
||||
if load_time_data.get('performance_distribution'):
|
||||
perf_dist = load_time_data['performance_distribution']
|
||||
|
||||
# Create pie chart for performance distribution
|
||||
labels = ['Fast (≤1s)', 'Moderate (1-3s)', 'Slow (>3s)']
|
||||
values = [
|
||||
perf_dist.get('fast_pages', 0),
|
||||
perf_dist.get('moderate_pages', 0),
|
||||
perf_dist.get('slow_pages', 0)
|
||||
]
|
||||
|
||||
fig = px.pie(values=values, names=labels,
|
||||
title="Page Load Time Distribution")
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
# Content Size Analysis
|
||||
if performance_data.get('content_size_analysis'):
|
||||
size_data = performance_data['content_size_analysis']
|
||||
|
||||
st.markdown("#### 📦 Content Size Analysis")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
avg_size = size_data.get('avg_page_size', 0)
|
||||
st.metric("Average Page Size", f"{avg_size/1024:.1f} KB")
|
||||
|
||||
with col2:
|
||||
largest_size = size_data.get('largest_page', 0)
|
||||
st.metric("Largest Page", f"{largest_size/1024:.1f} KB")
|
||||
|
||||
with col3:
|
||||
large_pages = size_data.get('pages_over_1mb', 0)
|
||||
st.metric("Pages >1MB", large_pages)
|
||||
|
||||
# Server Performance
|
||||
if performance_data.get('server_performance'):
|
||||
server_data = performance_data['server_performance']
|
||||
|
||||
st.markdown("#### 🖥️ Server Performance")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
success_rate = server_data.get('success_rate', 0)
|
||||
st.metric("Success Rate", f"{success_rate:.1f}%")
|
||||
|
||||
with col2:
|
||||
error_rate = server_data.get('error_rate', 0)
|
||||
st.metric("Error Rate", f"{error_rate:.1f}%")
|
||||
|
||||
with col3:
|
||||
redirect_rate = server_data.get('redirect_rate', 0)
|
||||
st.metric("Redirect Rate", f"{redirect_rate:.1f}%")
|
||||
|
||||
def _render_content_analysis(self, content_data: Dict[str, Any]):
|
||||
"""Render content structure analysis."""
|
||||
|
||||
st.markdown("### 📊 Content Structure Analysis")
|
||||
|
||||
if not content_data:
|
||||
st.info("No content analysis data available")
|
||||
return
|
||||
|
||||
# Title Analysis
|
||||
if content_data.get('title_analysis'):
|
||||
title_data = content_data['title_analysis']
|
||||
|
||||
st.markdown("#### 📝 Title Tag Analysis")
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
avg_title_length = title_data.get('avg_title_length', 0)
|
||||
st.metric("Average Title Length", f"{avg_title_length:.0f} chars")
|
||||
|
||||
duplicate_titles = title_data.get('duplicate_titles', 0)
|
||||
st.metric("Duplicate Titles", duplicate_titles)
|
||||
|
||||
with col2:
|
||||
# Title length distribution
|
||||
if title_data.get('title_length_distribution'):
|
||||
length_dist = title_data['title_length_distribution']
|
||||
|
||||
labels = ['Too Short (<30)', 'Optimal (30-60)', 'Too Long (>60)']
|
||||
values = [
|
||||
length_dist.get('too_short', 0),
|
||||
length_dist.get('optimal', 0),
|
||||
length_dist.get('too_long', 0)
|
||||
]
|
||||
|
||||
fig = px.pie(values=values, names=labels,
|
||||
title="Title Length Distribution")
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
# Meta Description Analysis
|
||||
if content_data.get('meta_description_analysis'):
|
||||
meta_data = content_data['meta_description_analysis']
|
||||
|
||||
st.markdown("#### 🏷️ Meta Description Analysis")
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
avg_meta_length = meta_data.get('avg_meta_length', 0)
|
||||
st.metric("Average Meta Length", f"{avg_meta_length:.0f} chars")
|
||||
|
||||
missing_meta = meta_data.get('missing_meta_descriptions', 0)
|
||||
st.metric("Missing Meta Descriptions", missing_meta)
|
||||
|
||||
with col2:
|
||||
# Meta length distribution
|
||||
if meta_data.get('meta_length_distribution'):
|
||||
meta_dist = meta_data['meta_length_distribution']
|
||||
|
||||
labels = ['Too Short (<120)', 'Optimal (120-160)', 'Too Long (>160)']
|
||||
values = [
|
||||
meta_dist.get('too_short', 0),
|
||||
meta_dist.get('optimal', 0),
|
||||
meta_dist.get('too_long', 0)
|
||||
]
|
||||
|
||||
fig = px.pie(values=values, names=labels,
|
||||
title="Meta Description Length Distribution")
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
# Heading Structure
|
||||
if content_data.get('heading_structure'):
|
||||
heading_data = content_data['heading_structure']
|
||||
|
||||
st.markdown("#### 📋 Heading Structure Analysis")
|
||||
|
||||
# Create heading usage chart
|
||||
heading_usage = []
|
||||
for heading_type, data in heading_data.items():
|
||||
heading_usage.append({
|
||||
'Heading': heading_type.replace('_usage', '').upper(),
|
||||
'Usage Rate': data.get('usage_rate', 0),
|
||||
'Pages': data.get('pages_with_heading', 0)
|
||||
})
|
||||
|
||||
if heading_usage:
|
||||
heading_df = pd.DataFrame(heading_usage)
|
||||
|
||||
fig = px.bar(heading_df, x='Heading', y='Usage Rate',
|
||||
title="Heading Tag Usage Rates")
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
st.dataframe(heading_df, use_container_width=True)
|
||||
|
||||
def _render_url_structure(self, url_data: Dict[str, Any]):
|
||||
"""Render URL structure analysis."""
|
||||
|
||||
st.markdown("### 🔗 URL Structure Analysis")
|
||||
|
||||
if not url_data:
|
||||
st.info("No URL structure data available")
|
||||
return
|
||||
|
||||
# URL Length Analysis
|
||||
if url_data.get('url_length_analysis'):
|
||||
length_data = url_data['url_length_analysis']
|
||||
|
||||
st.markdown("#### 📏 URL Length Analysis")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
avg_length = length_data.get('avg_url_length', 0)
|
||||
st.metric("Average URL Length", f"{avg_length:.0f} chars")
|
||||
|
||||
with col2:
|
||||
max_length = length_data.get('max_url_length', 0)
|
||||
st.metric("Longest URL", f"{max_length:.0f} chars")
|
||||
|
||||
with col3:
|
||||
long_urls = length_data.get('long_urls_count', 0)
|
||||
st.metric("URLs >100 chars", long_urls)
|
||||
|
||||
# URL Structure Patterns
|
||||
if url_data.get('url_structure_patterns'):
|
||||
pattern_data = url_data['url_structure_patterns']
|
||||
|
||||
st.markdown("#### 🏗️ URL Structure Patterns")
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
https_usage = pattern_data.get('https_usage', 0)
|
||||
st.metric("HTTPS Usage", f"{https_usage:.1f}%")
|
||||
|
||||
with col2:
|
||||
subdomain_usage = pattern_data.get('subdomain_usage', 0)
|
||||
st.metric("Subdomains Found", subdomain_usage)
|
||||
|
||||
# Path Analysis
|
||||
if url_data.get('path_analysis'):
|
||||
path_data = url_data['path_analysis']
|
||||
|
||||
st.markdown("#### 📂 Path Depth Analysis")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
avg_depth = path_data.get('avg_path_depth', 0)
|
||||
st.metric("Average Path Depth", f"{avg_depth:.1f}")
|
||||
|
||||
with col2:
|
||||
max_depth = path_data.get('max_path_depth', 0)
|
||||
st.metric("Maximum Depth", max_depth)
|
||||
|
||||
with col3:
|
||||
deep_paths = path_data.get('deep_paths_count', 0)
|
||||
st.metric("Deep Paths (>4)", deep_paths)
|
||||
|
||||
# Optimization Issues
|
||||
if url_data.get('url_optimization'):
|
||||
opt_data = url_data['url_optimization']
|
||||
|
||||
st.markdown("#### ⚠️ URL Optimization Issues")
|
||||
|
||||
issues_found = opt_data.get('issues_found', 0)
|
||||
recommendations = opt_data.get('optimization_recommendations', [])
|
||||
|
||||
if issues_found > 0:
|
||||
st.warning(f"Found {issues_found} URL optimization issue(s)")
|
||||
|
||||
for rec in recommendations:
|
||||
st.write(f"• {rec}")
|
||||
else:
|
||||
st.success("✅ No URL optimization issues found")
|
||||
|
||||
def _render_image_analysis(self, image_data: Dict[str, Any]):
|
||||
"""Render image SEO analysis."""
|
||||
|
||||
st.markdown("### 🖼️ Image SEO Analysis")
|
||||
|
||||
if not image_data:
|
||||
st.info("No image analysis data available")
|
||||
return
|
||||
|
||||
# Image overview
|
||||
image_count = image_data.get('image_count', 0)
|
||||
st.metric("Total Images Found", image_count)
|
||||
|
||||
if image_count > 0:
|
||||
# Alt text analysis
|
||||
if image_data.get('alt_text_analysis'):
|
||||
alt_data = image_data['alt_text_analysis']
|
||||
|
||||
st.markdown("#### 📝 Alt Text Analysis")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
images_with_alt = alt_data.get('images_with_alt', 0)
|
||||
st.metric("Images with Alt Text", images_with_alt)
|
||||
|
||||
with col2:
|
||||
images_missing_alt = alt_data.get('images_missing_alt', 0)
|
||||
st.metric("Missing Alt Text", images_missing_alt)
|
||||
|
||||
with col3:
|
||||
alt_coverage = alt_data.get('alt_text_coverage', 0)
|
||||
st.metric("Alt Text Coverage", f"{alt_coverage:.1f}%")
|
||||
|
||||
# Image format analysis
|
||||
if image_data.get('image_format_analysis'):
|
||||
format_data = image_data['image_format_analysis']
|
||||
|
||||
st.markdown("#### 🎨 Image Format Analysis")
|
||||
|
||||
if format_data.get('format_distribution'):
|
||||
format_dist = format_data['format_distribution']
|
||||
|
||||
format_df = pd.DataFrame(
|
||||
list(format_dist.items()),
|
||||
columns=['Format', 'Count']
|
||||
)
|
||||
|
||||
fig = px.pie(format_df, values='Count', names='Format',
|
||||
title="Image Format Distribution")
|
||||
st.plotly_chart(fig, use_container_width=True)
|
||||
|
||||
modern_formats = format_data.get('modern_format_usage', 0)
|
||||
st.metric("Modern Formats (WebP/AVIF)", modern_formats)
|
||||
else:
|
||||
st.info("No images found to analyze")
|
||||
|
||||
def _render_security_analysis(self, security_data: Dict[str, Any]):
|
||||
"""Render security analysis."""
|
||||
|
||||
st.markdown("### 🛡️ Security Headers Analysis")
|
||||
|
||||
if not security_data:
|
||||
st.info("No security analysis data available")
|
||||
return
|
||||
|
||||
# Security score
|
||||
security_score = security_data.get('security_score', 0)
|
||||
|
||||
col1, col2 = st.columns([1, 2])
|
||||
|
||||
with col1:
|
||||
st.metric("Security Score", f"{security_score:.0f}%")
|
||||
|
||||
if security_score >= 80:
|
||||
st.success("🔒 Good security posture")
|
||||
elif security_score >= 50:
|
||||
st.warning("⚠️ Moderate security")
|
||||
else:
|
||||
st.error("🚨 Poor security posture")
|
||||
|
||||
with col2:
|
||||
# Security headers status
|
||||
if security_data.get('security_headers_present'):
|
||||
headers_status = security_data['security_headers_present']
|
||||
|
||||
st.markdown("**Security Headers Status:**")
|
||||
|
||||
for header, present in headers_status.items():
|
||||
status = "✅" if present else "❌"
|
||||
st.write(f"{status} {header}")
|
||||
|
||||
# Security recommendations
|
||||
if security_data.get('security_recommendations'):
|
||||
recommendations = security_data['security_recommendations']
|
||||
|
||||
if recommendations:
|
||||
st.markdown("#### 🔧 Security Recommendations")
|
||||
|
||||
for rec in recommendations:
|
||||
st.write(f"• {rec}")
|
||||
else:
|
||||
st.success("✅ All security headers properly configured")
|
||||
|
||||
def _render_ai_recommendations(self, ai_data: Dict[str, Any]):
|
||||
"""Render AI-generated recommendations."""
|
||||
|
||||
st.markdown("### 🤖 AI-Powered Technical Recommendations")
|
||||
|
||||
if not ai_data:
|
||||
st.info("No AI recommendations available")
|
||||
return
|
||||
|
||||
# Critical Issues
|
||||
if ai_data.get('critical_issues'):
|
||||
st.markdown("#### 🚨 Critical Issues (Fix Immediately)")
|
||||
|
||||
critical_issues = ai_data['critical_issues']
|
||||
for issue in critical_issues:
|
||||
st.error(f"🚨 {issue}")
|
||||
|
||||
# High Priority
|
||||
if ai_data.get('high_priority'):
|
||||
st.markdown("#### 🔥 High Priority Optimizations")
|
||||
|
||||
high_priority = ai_data['high_priority']
|
||||
for item in high_priority:
|
||||
st.warning(f"⚡ {item}")
|
||||
|
||||
# Medium Priority
|
||||
if ai_data.get('medium_priority'):
|
||||
st.markdown("#### 📈 Medium Priority Improvements")
|
||||
|
||||
medium_priority = ai_data['medium_priority']
|
||||
for item in medium_priority:
|
||||
st.info(f"📊 {item}")
|
||||
|
||||
# Implementation Steps
|
||||
if ai_data.get('implementation_steps'):
|
||||
st.markdown("#### 🛠️ Implementation Steps")
|
||||
|
||||
steps = ai_data['implementation_steps']
|
||||
for i, step in enumerate(steps, 1):
|
||||
st.write(f"{i}. {step}")
|
||||
|
||||
# Expected Impact
|
||||
if ai_data.get('expected_impact'):
|
||||
st.markdown("#### 📈 Expected Impact Assessment")
|
||||
|
||||
impact = ai_data['expected_impact']
|
||||
st.markdown(impact)
|
||||
|
||||
def _render_export_options(self, results: Dict[str, Any]):
|
||||
"""Render export options for analysis results."""
|
||||
|
||||
st.markdown("---")
|
||||
st.markdown("### 📥 Export Technical SEO Audit")
|
||||
|
||||
col1, col2, col3 = st.columns(3)
|
||||
|
||||
with col1:
|
||||
# JSON export
|
||||
if st.button("📄 Export Full Report (JSON)", use_container_width=True):
|
||||
json_data = json.dumps(results, indent=2, default=str)
|
||||
|
||||
st.download_button(
|
||||
label="⬇️ Download JSON Report",
|
||||
data=json_data,
|
||||
file_name=f"technical_seo_audit_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json",
|
||||
mime="application/json",
|
||||
use_container_width=True
|
||||
)
|
||||
|
||||
with col2:
|
||||
# CSV export for issues
|
||||
if st.button("📊 Export Issues CSV", use_container_width=True):
|
||||
issues_data = self._prepare_issues_csv(results)
|
||||
|
||||
if issues_data:
|
||||
st.download_button(
|
||||
label="⬇️ Download Issues CSV",
|
||||
data=issues_data,
|
||||
file_name=f"technical_issues_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv",
|
||||
mime="text/csv",
|
||||
use_container_width=True
|
||||
)
|
||||
else:
|
||||
st.info("No issues found to export")
|
||||
|
||||
with col3:
|
||||
# Executive summary
|
||||
if st.button("📋 Executive Summary", use_container_width=True):
|
||||
summary = self._generate_executive_summary(results)
|
||||
|
||||
st.download_button(
|
||||
label="⬇️ Download Summary",
|
||||
data=summary,
|
||||
file_name=f"technical_seo_summary_{datetime.now().strftime('%Y%m%d_%H%M%S')}.txt",
|
||||
mime="text/plain",
|
||||
use_container_width=True
|
||||
)
|
||||
|
||||
def _prepare_issues_csv(self, results: Dict[str, Any]) -> str:
|
||||
"""Prepare CSV data for technical issues."""
|
||||
|
||||
issues_list = []
|
||||
|
||||
# HTTP errors
|
||||
http_errors = results.get('technical_issues', {}).get('http_errors', {})
|
||||
if http_errors.get('error_pages'):
|
||||
for error in http_errors['error_pages']:
|
||||
issues_list.append({
|
||||
'Issue Type': 'HTTP Error',
|
||||
'Severity': 'High',
|
||||
'URL': error.get('url', ''),
|
||||
'Status Code': error.get('status', ''),
|
||||
'Description': f"HTTP {error.get('status', '')} error"
|
||||
})
|
||||
|
||||
# Missing elements
|
||||
missing_elements = results.get('technical_issues', {}).get('missing_elements', {})
|
||||
|
||||
# Add more issue types as needed...
|
||||
|
||||
if issues_list:
|
||||
issues_df = pd.DataFrame(issues_list)
|
||||
return issues_df.to_csv(index=False)
|
||||
|
||||
return ""
|
||||
|
||||
def _generate_executive_summary(self, results: Dict[str, Any]) -> str:
|
||||
"""Generate executive summary report."""
|
||||
|
||||
website_url = results.get('website_url', 'Unknown')
|
||||
timestamp = results.get('analysis_timestamp', datetime.now().isoformat())
|
||||
|
||||
summary = f"""
|
||||
TECHNICAL SEO AUDIT - EXECUTIVE SUMMARY
|
||||
======================================
|
||||
|
||||
Website: {website_url}
|
||||
Audit Date: {timestamp}
|
||||
|
||||
AUDIT OVERVIEW
|
||||
--------------
|
||||
Pages Crawled: {results.get('crawl_overview', {}).get('pages_crawled', 0)}
|
||||
HTTP Errors: {results.get('technical_issues', {}).get('http_errors', {}).get('total_errors', 0)}
|
||||
Average Load Time: {results.get('performance_analysis', {}).get('load_time_analysis', {}).get('avg_load_time', 0):.2f}s
|
||||
Security Score: {results.get('security_headers', {}).get('security_score', 0):.0f}%
|
||||
|
||||
CRITICAL FINDINGS
|
||||
-----------------
|
||||
"""
|
||||
|
||||
# Add critical findings
|
||||
error_count = results.get('technical_issues', {}).get('http_errors', {}).get('total_errors', 0)
|
||||
if error_count > 0:
|
||||
summary += f"• {error_count} pages have HTTP errors requiring immediate attention\n"
|
||||
|
||||
avg_load_time = results.get('performance_analysis', {}).get('load_time_analysis', {}).get('avg_load_time', 0)
|
||||
if avg_load_time > 3:
|
||||
summary += f"• Page load times are slow (avg: {avg_load_time:.2f}s), impacting user experience\n"
|
||||
|
||||
security_score = results.get('security_headers', {}).get('security_score', 0)
|
||||
if security_score < 80:
|
||||
summary += f"• Security headers need improvement (current score: {security_score:.0f}%)\n"
|
||||
|
||||
summary += f"\n\nDetailed technical audit completed by ALwrity Technical SEO Crawler\nGenerated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}"
|
||||
|
||||
return summary
|
||||
|
||||
# Render function for integration with main dashboard
|
||||
def render_technical_seo_crawler():
|
||||
"""Render the Technical SEO Crawler UI."""
|
||||
ui = TechnicalSEOCrawlerUI()
|
||||
ui.render()
|
||||
58
ToBeMigrated/ai_seo_tools/textstaty.py
Normal file
58
ToBeMigrated/ai_seo_tools/textstaty.py
Normal file
@@ -0,0 +1,58 @@
|
||||
"""Text analysis tools using textstat."""
|
||||
|
||||
import streamlit as st
|
||||
from textstat import textstat
|
||||
|
||||
def analyze_text(text):
|
||||
"""Analyze text using textstat metrics."""
|
||||
if not text:
|
||||
st.warning("Please enter some text to analyze.")
|
||||
return
|
||||
|
||||
# Calculate various metrics
|
||||
metrics = {
|
||||
"Flesch Reading Ease": textstat.flesch_reading_ease(text),
|
||||
"Flesch-Kincaid Grade Level": textstat.flesch_kincaid_grade(text),
|
||||
"Gunning Fog Index": textstat.gunning_fog(text),
|
||||
"SMOG Index": textstat.smog_index(text),
|
||||
"Automated Readability Index": textstat.automated_readability_index(text),
|
||||
"Coleman-Liau Index": textstat.coleman_liau_index(text),
|
||||
"Linsear Write Formula": textstat.linsear_write_formula(text),
|
||||
"Dale-Chall Readability Score": textstat.dale_chall_readability_score(text),
|
||||
"Readability Consensus": textstat.readability_consensus(text)
|
||||
}
|
||||
|
||||
# Display metrics in a clean format
|
||||
st.subheader("Text Analysis Results")
|
||||
for metric, value in metrics.items():
|
||||
st.metric(metric, f"{value:.2f}")
|
||||
|
||||
# Add visualizations
|
||||
st.subheader("Visualization")
|
||||
st.bar_chart(metrics)
|
||||
|
||||
st.title("📖 Text Readability Analyzer: Making Your Content Easy to Read")
|
||||
|
||||
st.write("""
|
||||
This tool is your guide to writing content that's easy for your audience to understand.
|
||||
Just paste in a sample of your text, and we'll break down the readability scores and offer actionable tips!
|
||||
""")
|
||||
|
||||
text_input = st.text_area("Paste your text here:", height=200)
|
||||
|
||||
if st.button("Analyze!"):
|
||||
with st.spinner("Analyzing your text..."):
|
||||
test_data = text_input
|
||||
if not test_data.strip():
|
||||
st.error("Please enter text to analyze.")
|
||||
else:
|
||||
analyze_text(test_data)
|
||||
|
||||
st.subheader("Key Takeaways:")
|
||||
st.write("---")
|
||||
st.markdown("""
|
||||
* **Don't Be Afraid to Simplify!** Often, simpler language makes content more impactful and easier to digest.
|
||||
* **Aim for a Reading Level Appropriate for Your Audience:** Consider the education level, background, and familiarity of your readers.
|
||||
* **Use Short Sentences:** This makes your content more scannable and easier to read.
|
||||
* **Write for Everyone:** Accessibility should always be a priority. When in doubt, aim for clear, concise language!
|
||||
""")
|
||||
2
ToBeMigrated/ai_web_researcher/TBD
Normal file
2
ToBeMigrated/ai_web_researcher/TBD
Normal file
@@ -0,0 +1,2 @@
|
||||
1). Replace Firecrawl with scrapy or crawlee : https://crawlee.dev/python/docs/introduction
|
||||
|
||||
980
ToBeMigrated/ai_web_researcher/arxiv_schlorly_research.py
Normal file
980
ToBeMigrated/ai_web_researcher/arxiv_schlorly_research.py
Normal file
@@ -0,0 +1,980 @@
|
||||
####################################################
|
||||
#
|
||||
# FIXME: Gotta use this lib: https://github.com/monk1337/resp/tree/main
|
||||
# https://github.com/danielnsilva/semanticscholar
|
||||
# https://github.com/shauryr/S2QA
|
||||
#
|
||||
####################################################
|
||||
|
||||
|
||||
import os
|
||||
import sys
|
||||
import re
|
||||
import pandas as pd
|
||||
import arxiv
|
||||
import PyPDF2
|
||||
import requests
|
||||
import networkx as nx
|
||||
from bs4 import BeautifulSoup
|
||||
from urllib.parse import urlparse
|
||||
from loguru import logger
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
import bibtexparser
|
||||
from pylatexenc.latex2text import LatexNodes2Text
|
||||
from matplotlib import pyplot as plt
|
||||
from collections import defaultdict
|
||||
from sklearn.feature_extraction.text import TfidfVectorizer
|
||||
from sklearn.metrics.pairwise import cosine_similarity
|
||||
from sklearn.cluster import KMeans
|
||||
import numpy as np
|
||||
|
||||
logger.remove()
|
||||
logger.add(sys.stdout, colorize=True, format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}")
|
||||
|
||||
def create_arxiv_client(page_size=100, delay_seconds=3.0, num_retries=3):
|
||||
"""
|
||||
Creates a reusable arXiv API client with custom configuration.
|
||||
|
||||
Args:
|
||||
page_size (int): Number of results per page (default: 100)
|
||||
delay_seconds (float): Delay between API requests (default: 3.0)
|
||||
num_retries (int): Number of retries for failed requests (default: 3)
|
||||
|
||||
Returns:
|
||||
arxiv.Client: Configured arXiv API client
|
||||
"""
|
||||
try:
|
||||
client = arxiv.Client(
|
||||
page_size=page_size,
|
||||
delay_seconds=delay_seconds,
|
||||
num_retries=num_retries
|
||||
)
|
||||
return client
|
||||
except Exception as e:
|
||||
logger.error(f"Error creating arXiv client: {e}")
|
||||
raise e
|
||||
|
||||
def expand_search_query(query, research_interests=None):
|
||||
"""
|
||||
Uses AI to expand the search query based on user's research interests.
|
||||
|
||||
Args:
|
||||
query (str): Original search query
|
||||
research_interests (list): List of user's research interests
|
||||
|
||||
Returns:
|
||||
str: Expanded search query
|
||||
"""
|
||||
try:
|
||||
interests_context = "\n".join(research_interests) if research_interests else ""
|
||||
prompt = f"""Given the original arXiv search query: '{query}'
|
||||
{f'And considering these research interests:\n{interests_context}' if interests_context else ''}
|
||||
Generate an expanded arXiv search query that:
|
||||
1. Includes relevant synonyms and related concepts
|
||||
2. Uses appropriate arXiv search operators (AND, OR, etc.)
|
||||
3. Incorporates field-specific tags (ti:, abs:, au:, etc.)
|
||||
4. Maintains focus on the core topic
|
||||
Return only the expanded query without any explanation."""
|
||||
|
||||
expanded_query = llm_text_gen(prompt)
|
||||
logger.info(f"Expanded query: {expanded_query}")
|
||||
return expanded_query
|
||||
except Exception as e:
|
||||
logger.error(f"Error expanding search query: {e}")
|
||||
return query
|
||||
|
||||
def analyze_citation_network(papers):
|
||||
"""
|
||||
Analyzes citation relationships between papers using DOIs and references.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata dictionaries
|
||||
|
||||
Returns:
|
||||
dict: Citation network analysis results
|
||||
"""
|
||||
try:
|
||||
# Create a directed graph for citations
|
||||
G = nx.DiGraph()
|
||||
|
||||
# Add nodes and edges
|
||||
for paper in papers:
|
||||
paper_id = paper['entry_id']
|
||||
G.add_node(paper_id, title=paper['title'])
|
||||
|
||||
# Add edges based on DOIs and references
|
||||
if paper['doi']:
|
||||
for other_paper in papers:
|
||||
if other_paper['doi'] and other_paper['doi'] in paper['summary']:
|
||||
G.add_edge(paper_id, other_paper['entry_id'])
|
||||
|
||||
# Calculate network metrics
|
||||
analysis = {
|
||||
'influential_papers': sorted(nx.pagerank(G).items(), key=lambda x: x[1], reverse=True),
|
||||
'citation_clusters': list(nx.connected_components(G.to_undirected())),
|
||||
'citation_paths': dict(nx.all_pairs_shortest_path_length(G))
|
||||
}
|
||||
return analysis
|
||||
except Exception as e:
|
||||
logger.error(f"Error analyzing citation network: {e}")
|
||||
return {}
|
||||
|
||||
def categorize_papers(papers):
|
||||
"""
|
||||
Uses AI to categorize papers based on their metadata and content.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata dictionaries
|
||||
|
||||
Returns:
|
||||
dict: Paper categorization results
|
||||
"""
|
||||
try:
|
||||
categorized_papers = {}
|
||||
for paper in papers:
|
||||
prompt = f"""Analyze this research paper and provide detailed categorization:
|
||||
Title: {paper['title']}
|
||||
Abstract: {paper['summary']}
|
||||
Primary Category: {paper['primary_category']}
|
||||
Categories: {', '.join(paper['categories'])}
|
||||
|
||||
Provide a JSON response with these fields:
|
||||
1. main_theme: Primary research theme
|
||||
2. sub_themes: List of related sub-themes
|
||||
3. methodology: Research methodology used
|
||||
4. application_domains: Potential application areas
|
||||
5. technical_complexity: Level (Basic/Intermediate/Advanced)"""
|
||||
|
||||
categorization = llm_text_gen(prompt)
|
||||
categorized_papers[paper['entry_id']] = categorization
|
||||
|
||||
return categorized_papers
|
||||
except Exception as e:
|
||||
logger.error(f"Error categorizing papers: {e}")
|
||||
return {}
|
||||
|
||||
def get_paper_recommendations(papers, research_interests):
|
||||
"""
|
||||
Generates personalized paper recommendations based on user's research interests.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata dictionaries
|
||||
research_interests (list): User's research interests
|
||||
|
||||
Returns:
|
||||
dict: Personalized paper recommendations
|
||||
"""
|
||||
try:
|
||||
interests_text = "\n".join(research_interests)
|
||||
recommendations = {}
|
||||
|
||||
for paper in papers:
|
||||
prompt = f"""Evaluate this paper's relevance to the user's research interests:
|
||||
Paper:
|
||||
- Title: {paper['title']}
|
||||
- Abstract: {paper['summary']}
|
||||
- Categories: {', '.join(paper['categories'])}
|
||||
|
||||
User's Research Interests:
|
||||
{interests_text}
|
||||
|
||||
Provide a JSON response with:
|
||||
1. relevance_score: 0-100
|
||||
2. relevance_aspects: List of matching aspects
|
||||
3. potential_value: How this paper could benefit the user's research"""
|
||||
|
||||
evaluation = llm_text_gen(prompt)
|
||||
recommendations[paper['entry_id']] = evaluation
|
||||
|
||||
return recommendations
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating paper recommendations: {e}")
|
||||
return {}
|
||||
|
||||
def fetch_arxiv_data(query, max_results=10, sort_by=arxiv.SortCriterion.SubmittedDate, sort_order=None, client=None, research_interests=None):
|
||||
"""
|
||||
Fetches arXiv data based on a query with advanced search options.
|
||||
|
||||
Args:
|
||||
query (str): The search query (supports advanced syntax, e.g., 'au:einstein AND cat:physics')
|
||||
max_results (int): The maximum number of results to fetch
|
||||
sort_by (arxiv.SortCriterion): Sorting criterion (default: SubmittedDate)
|
||||
sort_order (str): Sort order ('ascending' or 'descending', default: None)
|
||||
client (arxiv.Client): Optional custom client (default: None, creates new client)
|
||||
|
||||
Returns:
|
||||
list: A list of arXiv data with extended metadata
|
||||
"""
|
||||
try:
|
||||
if client is None:
|
||||
client = create_arxiv_client()
|
||||
|
||||
# Expand search query using AI if research interests are provided
|
||||
expanded_query = expand_search_query(query, research_interests) if research_interests else query
|
||||
logger.info(f"Using expanded query: {expanded_query}")
|
||||
|
||||
search = arxiv.Search(
|
||||
query=expanded_query,
|
||||
max_results=max_results,
|
||||
sort_by=sort_by,
|
||||
sort_order=sort_order
|
||||
)
|
||||
|
||||
results = list(client.results(search))
|
||||
all_data = [
|
||||
{
|
||||
'title': result.title,
|
||||
'published': result.published,
|
||||
'updated': result.updated,
|
||||
'entry_id': result.entry_id,
|
||||
'summary': result.summary,
|
||||
'authors': [str(author) for author in result.authors],
|
||||
'pdf_url': result.pdf_url,
|
||||
'journal_ref': getattr(result, 'journal_ref', None),
|
||||
'doi': getattr(result, 'doi', None),
|
||||
'primary_category': getattr(result, 'primary_category', None),
|
||||
'categories': getattr(result, 'categories', []),
|
||||
'links': [link.href for link in getattr(result, 'links', [])]
|
||||
}
|
||||
for result in results
|
||||
]
|
||||
|
||||
# Enhance results with AI-powered analysis
|
||||
if all_data:
|
||||
# Analyze citation network
|
||||
citation_analysis = analyze_citation_network(all_data)
|
||||
|
||||
# Categorize papers using AI
|
||||
paper_categories = categorize_papers(all_data)
|
||||
|
||||
# Generate recommendations if research interests are provided
|
||||
recommendations = get_paper_recommendations(all_data, research_interests) if research_interests else {}
|
||||
|
||||
# Perform content analysis
|
||||
content_analyses = [analyze_paper_content(paper['entry_id']) for paper in all_data]
|
||||
trend_analysis = analyze_research_trends(all_data)
|
||||
concept_mapping = map_cross_paper_concepts(all_data)
|
||||
|
||||
# Generate bibliography data
|
||||
bibliography_data = {
|
||||
'bibtex_entries': [generate_bibtex_entry(paper) for paper in all_data],
|
||||
'citations': {
|
||||
'apa': [convert_citation_format(generate_bibtex_entry(paper), 'apa') for paper in all_data],
|
||||
'mla': [convert_citation_format(generate_bibtex_entry(paper), 'mla') for paper in all_data],
|
||||
'chicago': [convert_citation_format(generate_bibtex_entry(paper), 'chicago') for paper in all_data]
|
||||
},
|
||||
'reference_graph': visualize_reference_graph(all_data),
|
||||
'citation_impact': analyze_citation_impact(all_data)
|
||||
}
|
||||
|
||||
# Add enhanced data to results
|
||||
enhanced_data = {
|
||||
'papers': all_data,
|
||||
'citation_analysis': citation_analysis,
|
||||
'paper_categories': paper_categories,
|
||||
'recommendations': recommendations,
|
||||
'content_analyses': content_analyses,
|
||||
'trend_analysis': trend_analysis,
|
||||
'concept_mapping': concept_mapping,
|
||||
'bibliography': bibliography_data
|
||||
}
|
||||
return enhanced_data
|
||||
|
||||
return {'papers': all_data}
|
||||
except Exception as e:
|
||||
logger.error(f"An error occurred while fetching data from arXiv: {e}")
|
||||
raise e
|
||||
|
||||
def create_dataframe(data, column_names):
|
||||
"""
|
||||
Creates a DataFrame from the provided data.
|
||||
|
||||
Args:
|
||||
data (list): The data to convert to a DataFrame.
|
||||
column_names (list): The column names for the DataFrame.
|
||||
|
||||
Returns:
|
||||
DataFrame: The created DataFrame.
|
||||
"""
|
||||
try:
|
||||
df = pd.DataFrame(data, columns=column_names)
|
||||
return df
|
||||
except Exception as e:
|
||||
logger.error(f"An error occurred while creating DataFrame: {e}")
|
||||
return pd.DataFrame()
|
||||
|
||||
def get_arxiv_main_content(url):
|
||||
"""
|
||||
Returns the main content of an arXiv paper.
|
||||
|
||||
Args:
|
||||
url (str): The URL of the arXiv paper.
|
||||
|
||||
Returns:
|
||||
str: The main content of the paper as a string.
|
||||
"""
|
||||
try:
|
||||
response = requests.get(url)
|
||||
response.raise_for_status()
|
||||
soup = BeautifulSoup(response.content, "html.parser")
|
||||
main_content = soup.find('div', class_='ltx_page_content')
|
||||
if not main_content:
|
||||
logger.warning("Main content not found in the page.")
|
||||
return "Main content not found."
|
||||
alert_section = main_content.find('div', class_='package-alerts ltx_document')
|
||||
if (alert_section):
|
||||
alert_section.decompose()
|
||||
for element_id in ["abs", "authors"]:
|
||||
element = main_content.find(id=element_id)
|
||||
if (element):
|
||||
element.decompose()
|
||||
return main_content.text.strip()
|
||||
except Exception as html_error:
|
||||
logger.warning(f"HTML content not accessible, trying PDF: {html_error}")
|
||||
return get_pdf_content(url)
|
||||
|
||||
def download_paper(paper_id, output_dir="downloads", filename=None, get_source=False):
|
||||
"""
|
||||
Downloads a paper's PDF or source files with enhanced error handling.
|
||||
|
||||
Args:
|
||||
paper_id (str): The arXiv ID of the paper
|
||||
output_dir (str): Directory to save the downloaded file (default: 'downloads')
|
||||
filename (str): Custom filename (default: None, uses paper ID)
|
||||
get_source (bool): If True, downloads source files instead of PDF (default: False)
|
||||
|
||||
Returns:
|
||||
str: Path to the downloaded file or None if download fails
|
||||
"""
|
||||
try:
|
||||
# Create output directory if it doesn't exist
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
|
||||
# Get paper metadata
|
||||
client = create_arxiv_client()
|
||||
paper = next(client.results(arxiv.Search(id_list=[paper_id])))
|
||||
|
||||
# Set filename if not provided
|
||||
if not filename:
|
||||
safe_title = re.sub(r'[^\w\-_.]', '_', paper.title[:50])
|
||||
filename = f"{paper_id}_{safe_title}"
|
||||
filename += ".tar.gz" if get_source else ".pdf"
|
||||
|
||||
# Full path for the downloaded file
|
||||
file_path = os.path.join(output_dir, filename)
|
||||
|
||||
# Download the file
|
||||
if get_source:
|
||||
paper.download_source(dirpath=output_dir, filename=filename)
|
||||
else:
|
||||
paper.download_pdf(dirpath=output_dir, filename=filename)
|
||||
|
||||
logger.info(f"Successfully downloaded {'source' if get_source else 'PDF'} to {file_path}")
|
||||
return file_path
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error downloading {'source' if get_source else 'PDF'} for {paper_id}: {e}")
|
||||
return None
|
||||
|
||||
def analyze_paper_content(url_or_id, cleanup=True):
|
||||
"""
|
||||
Analyzes paper content using AI to extract key information and insights.
|
||||
|
||||
Args:
|
||||
url_or_id (str): The arXiv URL or ID of the paper
|
||||
cleanup (bool): Whether to delete the PDF after extraction (default: True)
|
||||
|
||||
Returns:
|
||||
dict: Analysis results including summary, key findings, and concepts
|
||||
"""
|
||||
try:
|
||||
# Get paper content
|
||||
content = get_pdf_content(url_or_id, cleanup)
|
||||
if not content or 'Failed to' in content:
|
||||
return {'error': content}
|
||||
|
||||
# Generate paper summary
|
||||
summary_prompt = f"""Analyze this research paper and provide a comprehensive summary:
|
||||
{content[:8000]} # Limit content length for API
|
||||
|
||||
Provide a JSON response with:
|
||||
1. executive_summary: Brief overview (2-3 sentences)
|
||||
2. key_findings: List of main research findings
|
||||
3. methodology: Research methods used
|
||||
4. implications: Practical implications of the research
|
||||
5. limitations: Study limitations and constraints"""
|
||||
|
||||
summary_analysis = llm_text_gen(summary_prompt)
|
||||
|
||||
# Extract key concepts and relationships
|
||||
concepts_prompt = f"""Analyze this research paper and identify key concepts and relationships:
|
||||
{content[:8000]}
|
||||
|
||||
Provide a JSON response with:
|
||||
1. main_concepts: List of key technical concepts
|
||||
2. concept_relationships: How concepts are related
|
||||
3. novel_contributions: New ideas or approaches introduced
|
||||
4. technical_requirements: Required technologies or methods
|
||||
5. future_directions: Suggested future research"""
|
||||
|
||||
concept_analysis = llm_text_gen(concepts_prompt)
|
||||
|
||||
return {
|
||||
'summary_analysis': summary_analysis,
|
||||
'concept_analysis': concept_analysis,
|
||||
'full_text': content
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Error analyzing paper content: {e}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def analyze_research_trends(papers):
|
||||
"""
|
||||
Analyzes research trends across multiple papers.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata and content
|
||||
|
||||
Returns:
|
||||
dict: Trend analysis results
|
||||
"""
|
||||
try:
|
||||
# Collect paper information
|
||||
papers_info = []
|
||||
for paper in papers:
|
||||
content = get_pdf_content(paper['entry_id'], cleanup=True)
|
||||
if content and 'Failed to' not in content:
|
||||
papers_info.append({
|
||||
'title': paper['title'],
|
||||
'abstract': paper['summary'],
|
||||
'content': content[:8000], # Limit content length
|
||||
'year': paper['published'].year
|
||||
})
|
||||
|
||||
if not papers_info:
|
||||
return {'error': 'No valid paper content found for analysis'}
|
||||
|
||||
# Analyze trends
|
||||
trends_prompt = f"""Analyze these research papers and identify key trends:
|
||||
Papers:
|
||||
{str(papers_info)}
|
||||
|
||||
Provide a JSON response with:
|
||||
1. temporal_trends: How research focus evolved over time
|
||||
2. emerging_themes: New and growing research areas
|
||||
3. declining_themes: Decreasing research focus areas
|
||||
4. methodology_trends: Evolution of research methods
|
||||
5. technology_trends: Trends in technology usage
|
||||
6. research_gaps: Identified gaps and opportunities"""
|
||||
|
||||
trend_analysis = llm_text_gen(trends_prompt)
|
||||
return {'trend_analysis': trend_analysis}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error analyzing research trends: {e}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def map_cross_paper_concepts(papers):
|
||||
"""
|
||||
Maps concepts and relationships across multiple papers.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata and content
|
||||
|
||||
Returns:
|
||||
dict: Concept mapping results
|
||||
"""
|
||||
try:
|
||||
# Analyze each paper
|
||||
paper_analyses = []
|
||||
for paper in papers:
|
||||
analysis = analyze_paper_content(paper['entry_id'])
|
||||
if 'error' not in analysis:
|
||||
paper_analyses.append({
|
||||
'paper_id': paper['entry_id'],
|
||||
'title': paper['title'],
|
||||
'analysis': analysis
|
||||
})
|
||||
|
||||
if not paper_analyses:
|
||||
return {'error': 'No valid paper analyses for concept mapping'}
|
||||
|
||||
# Generate cross-paper concept map
|
||||
mapping_prompt = f"""Analyze relationships between concepts across these papers:
|
||||
{str(paper_analyses)}
|
||||
|
||||
Provide a JSON response with:
|
||||
1. shared_concepts: Concepts appearing in multiple papers
|
||||
2. concept_evolution: How concepts developed across papers
|
||||
3. conflicting_views: Different interpretations of same concepts
|
||||
4. complementary_findings: How papers complement each other
|
||||
5. knowledge_gaps: Areas needing more research"""
|
||||
|
||||
concept_mapping = llm_text_gen(mapping_prompt)
|
||||
return {'concept_mapping': concept_mapping}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error mapping cross-paper concepts: {e}")
|
||||
return {'error': str(e)}
|
||||
|
||||
def generate_bibtex_entry(paper):
|
||||
"""
|
||||
Generates a BibTeX entry for a paper with complete metadata.
|
||||
|
||||
Args:
|
||||
paper (dict): Paper metadata dictionary
|
||||
|
||||
Returns:
|
||||
str: BibTeX entry string
|
||||
"""
|
||||
try:
|
||||
# Generate a unique citation key
|
||||
first_author = paper['authors'][0].split()[-1] if paper['authors'] else 'Unknown'
|
||||
year = paper['published'].year if paper['published'] else '0000'
|
||||
citation_key = f"{first_author}{year}{paper['entry_id'].split('/')[-1]}"
|
||||
|
||||
# Format authors for BibTeX
|
||||
authors = ' and '.join(paper['authors'])
|
||||
|
||||
# Create BibTeX entry
|
||||
bibtex = f"@article{{{citation_key},\n"
|
||||
bibtex += f" title = {{{paper['title']}}},\n"
|
||||
bibtex += f" author = {{{authors}}},\n"
|
||||
bibtex += f" year = {{{year}}},\n"
|
||||
bibtex += f" journal = {{arXiv preprint}},\n"
|
||||
bibtex += f" archivePrefix = {{arXiv}},\n"
|
||||
bibtex += f" eprint = {{{paper['entry_id'].split('/')[-1]}}},\n"
|
||||
if paper['doi']:
|
||||
bibtex += f" doi = {{{paper['doi']}}},\n"
|
||||
bibtex += f" url = {{{paper['entry_id']}}},\n"
|
||||
bibtex += f" abstract = {{{paper['summary']}}}\n"
|
||||
bibtex += "}"
|
||||
|
||||
return bibtex
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating BibTeX entry: {e}")
|
||||
return ""
|
||||
|
||||
def convert_citation_format(bibtex_str, target_format):
|
||||
"""
|
||||
Converts BibTeX citations to other formats and validates the output.
|
||||
|
||||
Args:
|
||||
bibtex_str (str): BibTeX entry string
|
||||
target_format (str): Target citation format ('apa', 'mla', 'chicago', etc.)
|
||||
|
||||
Returns:
|
||||
str: Formatted citation string
|
||||
"""
|
||||
try:
|
||||
# Parse BibTeX entry
|
||||
bib_database = bibtexparser.loads(bibtex_str)
|
||||
entry = bib_database.entries[0]
|
||||
|
||||
# Generate citation format prompt
|
||||
prompt = f"""Convert this bibliographic information to {target_format} format:
|
||||
Title: {entry.get('title', '')}
|
||||
Authors: {entry.get('author', '')}
|
||||
Year: {entry.get('year', '')}
|
||||
Journal: {entry.get('journal', '')}
|
||||
DOI: {entry.get('doi', '')}
|
||||
URL: {entry.get('url', '')}
|
||||
|
||||
Return only the formatted citation without any explanation."""
|
||||
|
||||
# Use AI to generate formatted citation
|
||||
formatted_citation = llm_text_gen(prompt)
|
||||
return formatted_citation.strip()
|
||||
except Exception as e:
|
||||
logger.error(f"Error converting citation format: {e}")
|
||||
return ""
|
||||
|
||||
def visualize_reference_graph(papers):
|
||||
"""
|
||||
Creates a visual representation of the citation network.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata dictionaries
|
||||
|
||||
Returns:
|
||||
str: Path to the saved visualization file
|
||||
"""
|
||||
try:
|
||||
# Create directed graph
|
||||
G = nx.DiGraph()
|
||||
|
||||
# Add nodes and edges
|
||||
for paper in papers:
|
||||
paper_id = paper['entry_id']
|
||||
G.add_node(paper_id, title=paper['title'])
|
||||
|
||||
# Add citation edges
|
||||
if paper['doi']:
|
||||
for other_paper in papers:
|
||||
if other_paper['doi'] and other_paper['doi'] in paper['summary']:
|
||||
G.add_edge(paper_id, other_paper['entry_id'])
|
||||
|
||||
# Set up the visualization
|
||||
plt.figure(figsize=(12, 8))
|
||||
pos = nx.spring_layout(G)
|
||||
|
||||
# Draw the graph
|
||||
nx.draw(G, pos, with_labels=False, node_color='lightblue',
|
||||
node_size=1000, arrowsize=20)
|
||||
|
||||
# Add labels
|
||||
labels = nx.get_node_attributes(G, 'title')
|
||||
nx.draw_networkx_labels(G, pos, labels, font_size=8)
|
||||
|
||||
# Save the visualization
|
||||
output_path = 'reference_graph.png'
|
||||
plt.savefig(output_path, dpi=300, bbox_inches='tight')
|
||||
plt.close()
|
||||
|
||||
return output_path
|
||||
except Exception as e:
|
||||
logger.error(f"Error visualizing reference graph: {e}")
|
||||
return ""
|
||||
|
||||
def analyze_citation_impact(papers):
|
||||
"""
|
||||
Analyzes citation impact and influence patterns.
|
||||
|
||||
Args:
|
||||
papers (list): List of paper metadata dictionaries
|
||||
|
||||
Returns:
|
||||
dict: Citation impact analysis results
|
||||
"""
|
||||
try:
|
||||
# Create citation network
|
||||
G = nx.DiGraph()
|
||||
for paper in papers:
|
||||
G.add_node(paper['entry_id'], **paper)
|
||||
if paper['doi']:
|
||||
for other_paper in papers:
|
||||
if other_paper['doi'] and other_paper['doi'] in paper['summary']:
|
||||
G.add_edge(paper_id, other_paper['entry_id'])
|
||||
|
||||
# Calculate impact metrics
|
||||
impact_analysis = {
|
||||
'citation_counts': dict(G.in_degree()),
|
||||
'influence_scores': nx.pagerank(G),
|
||||
'authority_scores': nx.authority_matrix(G).diagonal(),
|
||||
'hub_scores': nx.hub_matrix(G).diagonal(),
|
||||
'citation_paths': dict(nx.all_pairs_shortest_path_length(G))
|
||||
}
|
||||
|
||||
# Add temporal analysis
|
||||
year_citations = defaultdict(int)
|
||||
for paper in papers:
|
||||
if paper['published']:
|
||||
year = paper['published'].year
|
||||
year_citations[year] += G.in_degree(paper['entry_id'])
|
||||
impact_analysis['temporal_trends'] = dict(year_citations)
|
||||
|
||||
return impact_analysis
|
||||
except Exception as e:
|
||||
logger.error(f"Error analyzing citation impact: {e}")
|
||||
return {}
|
||||
|
||||
def get_pdf_content(url_or_id, cleanup=True):
|
||||
"""
|
||||
Extracts text content from a paper's PDF with improved error handling.
|
||||
|
||||
Args:
|
||||
url_or_id (str): The arXiv URL or ID of the paper
|
||||
cleanup (bool): Whether to delete the PDF after extraction (default: True)
|
||||
|
||||
Returns:
|
||||
str: The extracted text content or error message
|
||||
"""
|
||||
try:
|
||||
# Extract arxiv ID from URL if needed
|
||||
arxiv_id = url_or_id.split('/')[-1] if '/' in url_or_id else url_or_id
|
||||
|
||||
# Download PDF
|
||||
pdf_path = download_paper(arxiv_id)
|
||||
if not pdf_path:
|
||||
return "Failed to download PDF."
|
||||
|
||||
# Extract text from PDF
|
||||
pdf_text = ''
|
||||
with open(pdf_path, 'rb') as f:
|
||||
pdf_reader = PyPDF2.PdfReader(f)
|
||||
for page_num, page in enumerate(pdf_reader.pages, 1):
|
||||
try:
|
||||
page_text = page.extract_text()
|
||||
if page_text:
|
||||
pdf_text += f"\n--- Page {page_num} ---\n{page_text}"
|
||||
except Exception as err:
|
||||
logger.error(f"Error extracting text from page {page_num}: {err}")
|
||||
continue
|
||||
|
||||
# Clean up
|
||||
if cleanup:
|
||||
try:
|
||||
os.remove(pdf_path)
|
||||
logger.debug(f"Cleaned up temporary PDF file: {pdf_path}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup PDF file {pdf_path}: {e}")
|
||||
|
||||
# Process and return text
|
||||
if not pdf_text.strip():
|
||||
return "No text content could be extracted from the PDF."
|
||||
|
||||
return clean_pdf_text(pdf_text)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to process PDF: {e}")
|
||||
return f"Failed to retrieve content: {str(e)}"
|
||||
|
||||
def clean_pdf_text(text):
|
||||
"""
|
||||
Helper function to clean the text extracted from a PDF.
|
||||
|
||||
Args:
|
||||
text (str): The text to clean.
|
||||
|
||||
Returns:
|
||||
str: The cleaned text.
|
||||
"""
|
||||
pattern = r'References\s*.*'
|
||||
text = re.sub(pattern, '', text, flags=re.IGNORECASE | re.DOTALL)
|
||||
sections_to_remove = ['Acknowledgements', 'References', 'Bibliography']
|
||||
for section in sections_to_remove:
|
||||
pattern = r'(' + re.escape(section) + r'\s*.*?)(?=\n[A-Z]{2,}|$)'
|
||||
text = re.sub(pattern, '', text, flags=re.DOTALL | re.IGNORECASE)
|
||||
return text
|
||||
|
||||
def download_image(image_url, base_url, folder="images"):
|
||||
"""
|
||||
Downloads an image from a URL.
|
||||
|
||||
Args:
|
||||
image_url (str): The URL of the image.
|
||||
base_url (str): The base URL of the website.
|
||||
folder (str): The folder to save the image.
|
||||
|
||||
Returns:
|
||||
bool: True if the image was downloaded successfully, False otherwise.
|
||||
"""
|
||||
if image_url.startswith('data:image'):
|
||||
logger.info(f"Skipping download of data URI image: {image_url}")
|
||||
return False
|
||||
if not os.path.exists(folder):
|
||||
os.makedirs(folder)
|
||||
if not urlparse(image_url).scheme:
|
||||
if not base_url.endswith('/'):
|
||||
base_url += '/'
|
||||
image_url = base_url + image_url
|
||||
try:
|
||||
response = requests.get(image_url)
|
||||
response.raise_for_status()
|
||||
image_name = image_url.split("/")[-1]
|
||||
with open(os.path.join(folder, image_name), 'wb') as file:
|
||||
file.write(response.content)
|
||||
return True
|
||||
except requests.RequestException as e:
|
||||
logger.error(f"Error downloading {image_url}: {e}")
|
||||
return False
|
||||
|
||||
def scrape_images_from_arxiv(url):
|
||||
"""
|
||||
Scrapes images from an arXiv page.
|
||||
|
||||
Args:
|
||||
url (str): The URL of the arXiv page.
|
||||
|
||||
Returns:
|
||||
list: A list of image URLs.
|
||||
"""
|
||||
try:
|
||||
response = requests.get(url)
|
||||
response.raise_for_status()
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
images = soup.find_all('img')
|
||||
image_urls = [img['src'] for img in images if 'src' in img.attrs]
|
||||
return image_urls
|
||||
except requests.RequestException as e:
|
||||
logger.error(f"Error fetching page {url}: {e}")
|
||||
return []
|
||||
|
||||
def generate_bibtex(paper_id, client=None):
|
||||
"""
|
||||
Generate a BibTeX entry for an arXiv paper with enhanced metadata.
|
||||
|
||||
Args:
|
||||
paper_id (str): The arXiv ID of the paper
|
||||
client (arxiv.Client): Optional custom client (default: None)
|
||||
|
||||
Returns:
|
||||
str: BibTeX entry as a string
|
||||
"""
|
||||
try:
|
||||
if client is None:
|
||||
client = create_arxiv_client()
|
||||
|
||||
# Fetch paper metadata
|
||||
paper = next(client.results(arxiv.Search(id_list=[paper_id])))
|
||||
|
||||
# Extract author information
|
||||
authors = [str(author) for author in paper.authors]
|
||||
first_author = authors[0].split(', ')[0] if authors else 'Unknown'
|
||||
|
||||
# Format year
|
||||
year = paper.published.year if paper.published else 'Unknown'
|
||||
|
||||
# Create citation key
|
||||
citation_key = f"{first_author}{str(year)[-2:]}"
|
||||
|
||||
# Build BibTeX entry
|
||||
bibtex = [
|
||||
f"@article{{{citation_key},",
|
||||
f" author = {{{' and '.join(authors)}}},",
|
||||
f" title = {{{paper.title}}},",
|
||||
f" year = {{{year}}},",
|
||||
f" eprint = {{{paper_id}}},",
|
||||
f" archivePrefix = {{arXiv}},"
|
||||
]
|
||||
|
||||
# Add optional fields if available
|
||||
if paper.doi:
|
||||
bibtex.append(f" doi = {{{paper.doi}}},")
|
||||
if getattr(paper, 'journal_ref', None):
|
||||
bibtex.append(f" journal = {{{paper.journal_ref}}},")
|
||||
if getattr(paper, 'primary_category', None):
|
||||
bibtex.append(f" primaryClass = {{{paper.primary_category}}},")
|
||||
|
||||
# Add URL and close entry
|
||||
bibtex.extend([
|
||||
f" url = {{https://arxiv.org/abs/{paper_id}}}",
|
||||
"}"
|
||||
])
|
||||
|
||||
return '\n'.join(bibtex)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating BibTeX for {paper_id}: {e}")
|
||||
return ""
|
||||
|
||||
def batch_download_papers(paper_ids, output_dir="downloads", get_source=False):
|
||||
"""
|
||||
Download multiple papers in batch with progress tracking.
|
||||
|
||||
Args:
|
||||
paper_ids (list): List of arXiv IDs to download
|
||||
output_dir (str): Directory to save downloaded files (default: 'downloads')
|
||||
get_source (bool): If True, downloads source files instead of PDFs (default: False)
|
||||
|
||||
Returns:
|
||||
dict: Mapping of paper IDs to their download status and paths
|
||||
"""
|
||||
results = {}
|
||||
client = create_arxiv_client()
|
||||
|
||||
for paper_id in paper_ids:
|
||||
try:
|
||||
file_path = download_paper(paper_id, output_dir, get_source=get_source)
|
||||
results[paper_id] = {
|
||||
'success': bool(file_path),
|
||||
'path': file_path,
|
||||
'error': None
|
||||
}
|
||||
except Exception as e:
|
||||
results[paper_id] = {
|
||||
'success': False,
|
||||
'path': None,
|
||||
'error': str(e)
|
||||
}
|
||||
logger.error(f"Failed to download {paper_id}: {e}")
|
||||
|
||||
return results
|
||||
|
||||
def batch_generate_bibtex(paper_ids):
|
||||
"""
|
||||
Generate BibTeX entries for multiple papers.
|
||||
|
||||
Args:
|
||||
paper_ids (list): List of arXiv IDs
|
||||
|
||||
Returns:
|
||||
dict: Mapping of paper IDs to their BibTeX entries
|
||||
"""
|
||||
results = {}
|
||||
client = create_arxiv_client()
|
||||
|
||||
for paper_id in paper_ids:
|
||||
try:
|
||||
bibtex = generate_bibtex(paper_id, client)
|
||||
results[paper_id] = {
|
||||
'success': bool(bibtex),
|
||||
'bibtex': bibtex,
|
||||
'error': None
|
||||
}
|
||||
except Exception as e:
|
||||
results[paper_id] = {
|
||||
'success': False,
|
||||
'bibtex': '',
|
||||
'error': str(e)
|
||||
}
|
||||
logger.error(f"Failed to generate BibTeX for {paper_id}: {e}")
|
||||
|
||||
return results
|
||||
|
||||
def extract_arxiv_ids_from_line(line):
|
||||
"""
|
||||
Extract the arXiv ID from a given line of text.
|
||||
|
||||
Args:
|
||||
line (str): A line of text potentially containing an arXiv URL.
|
||||
|
||||
Returns:
|
||||
str: The extracted arXiv ID, or None if not found.
|
||||
"""
|
||||
arxiv_id_pattern = re.compile(r'arxiv\.org\/abs\/(\d+\.\d+)(v\d+)?')
|
||||
match = arxiv_id_pattern.search(line)
|
||||
if match:
|
||||
return match.group(1) + (match.group(2) if match.group(2) else '')
|
||||
return None
|
||||
|
||||
def read_written_ids(file_path):
|
||||
"""
|
||||
Read already written arXiv IDs from a file.
|
||||
|
||||
Args:
|
||||
file_path (str): Path to the file containing written IDs.
|
||||
|
||||
Returns:
|
||||
set: A set of arXiv IDs.
|
||||
"""
|
||||
written_ids = set()
|
||||
try:
|
||||
with open(file_path, 'r', encoding="utf-8") as file:
|
||||
for line in file:
|
||||
written_ids.add(line.strip())
|
||||
except FileNotFoundError:
|
||||
logger.error(f"File not found: {file_path}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error while reading the file: {e}")
|
||||
return written_ids
|
||||
|
||||
def append_id_to_file(arxiv_id, output_file_path):
|
||||
"""
|
||||
Append a single arXiv ID to a file. Checks if the file exists and creates it if not.
|
||||
|
||||
Args:
|
||||
arxiv_id (str): The arXiv ID to append.
|
||||
output_file_path (str): Path to the output file.
|
||||
"""
|
||||
try:
|
||||
if not os.path.exists(output_file_path):
|
||||
logger.info(f"File does not exist. Creating new file: {output_file_path}")
|
||||
with open(output_file_path, 'a', encoding="utf-8") as outfile:
|
||||
outfile.write(arxiv_id + '\n')
|
||||
else:
|
||||
logger.info(f"Appending to existing file: {output_file_path}")
|
||||
with open(output_file_path, 'a', encoding="utf-8") as outfile:
|
||||
outfile.write(arxiv_id + '\n')
|
||||
except Exception as e:
|
||||
logger.error(f"Error while appending to file: {e}")
|
||||
100
ToBeMigrated/ai_web_researcher/common_utils.py
Normal file
100
ToBeMigrated/ai_web_researcher/common_utils.py
Normal file
@@ -0,0 +1,100 @@
|
||||
# Common utils for web_researcher
|
||||
import os
|
||||
import sys
|
||||
import re
|
||||
import json
|
||||
from pathlib import Path
|
||||
from datetime import datetime, timedelta
|
||||
from pathlib import Path
|
||||
from loguru import logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
|
||||
def cfg_search_param(flag):
|
||||
"""
|
||||
Read values from the main_config.json file and return them as variables and a dictionary.
|
||||
|
||||
Args:
|
||||
flag (str): A flag to determine which configuration values to return.
|
||||
|
||||
Returns:
|
||||
various: The values read from the config file based on the flag.
|
||||
"""
|
||||
try:
|
||||
file_path = Path(os.environ.get("ALWRITY_CONFIG", ""))
|
||||
if not file_path.is_file():
|
||||
raise FileNotFoundError(f"Configuration file not found: {file_path}")
|
||||
logger.info(f"Reading search config params from {file_path}")
|
||||
|
||||
with open(file_path, 'r', encoding='utf-8') as file:
|
||||
config = json.load(file)
|
||||
web_research_section = config["Search Engine Parameters"]
|
||||
|
||||
if 'serperdev' in flag:
|
||||
# Get values as variables
|
||||
geo_location = web_research_section.get("Geographic Location")
|
||||
search_language = web_research_section.get("Search Language")
|
||||
num_results = web_research_section.get("Number of Results")
|
||||
return geo_location, search_language, num_results
|
||||
|
||||
elif 'tavily' in flag:
|
||||
include_urls = web_research_section.get("Include Domains")
|
||||
pattern = re.compile(r"^(https?://[^\s,]+)(,\s*https?://[^\s,]+)*$")
|
||||
if pattern.match(include_urls):
|
||||
include_urls = [url.strip() for url in include_urls.split(',')]
|
||||
else:
|
||||
include_urls = None
|
||||
return include_urls
|
||||
|
||||
elif 'exa' in flag:
|
||||
include_urls = web_research_section.get("Include Domains")
|
||||
pattern = re.compile(r"^(https?://\w+)(,\s*https?://\w+)*$")
|
||||
if pattern.match(include_urls) is not None:
|
||||
include_urls = include_urls.split(',')
|
||||
elif re.match(r"^http?://\w+$", include_urls) is not None:
|
||||
include_urls = include_urls.split(" ")
|
||||
else:
|
||||
include_urls = None
|
||||
|
||||
num_results = web_research_section.get("Number of Results")
|
||||
similar_url = web_research_section.get("Similar URL")
|
||||
time_range = web_research_section.get("Time Range")
|
||||
if time_range == "past day":
|
||||
start_published_date = (datetime.now() - timedelta(days=1)).strftime('%Y-%m-%d')
|
||||
elif time_range == "past week":
|
||||
start_published_date = (datetime.now() - timedelta(days=7)).strftime("%Y-%m-%d")
|
||||
elif time_range == "past month":
|
||||
start_published_date = (datetime.now() - timedelta(days=30)).strftime('%Y-%m-%d')
|
||||
elif time_range == "past year":
|
||||
start_published_date = (datetime.now() - timedelta(days=365)).strftime('%Y-%m-%d')
|
||||
elif time_range == "anytime" or not time_range:
|
||||
start_published_date = None
|
||||
time_range = start_published_date
|
||||
return include_urls, time_range, num_results, similar_url
|
||||
|
||||
except FileNotFoundError:
|
||||
logger.error(f"Error: Config file '{file_path}' not found.")
|
||||
return {}, None, None, None
|
||||
except KeyError as e:
|
||||
logger.error(f"Error: Missing section or option in config file: {e}")
|
||||
return {}, None, None, None
|
||||
except ValueError as e:
|
||||
logger.error(f"Error: Invalid value in config file: {e}")
|
||||
return {}, None, None, None
|
||||
|
||||
def save_in_file(table_content):
|
||||
""" Helper function to save search analysis in a file. """
|
||||
file_path = os.environ.get('SEARCH_SAVE_FILE')
|
||||
try:
|
||||
# Save the content to the file
|
||||
with open(file_path, "a+", encoding="utf-8") as file:
|
||||
file.write(table_content)
|
||||
file.write("\n" * 3) # Add three newlines at the end
|
||||
logger.info(f"Search content saved to {file_path}")
|
||||
return file_path
|
||||
except Exception as e:
|
||||
logger.error(f"Error occurred while writing to the file: {e}")
|
||||
256
ToBeMigrated/ai_web_researcher/finance_data_researcher.py
Normal file
256
ToBeMigrated/ai_web_researcher/finance_data_researcher.py
Normal file
@@ -0,0 +1,256 @@
|
||||
import matplotlib.pyplot as plt
|
||||
import pandas as pd
|
||||
import yfinance as yf
|
||||
import pandas_ta as ta
|
||||
import matplotlib.dates as mdates
|
||||
from datetime import datetime, timedelta
|
||||
import logging
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
||||
|
||||
def calculate_technical_indicators(data: pd.DataFrame) -> pd.DataFrame:
|
||||
"""
|
||||
Calculates a suite of technical indicators using pandas_ta.
|
||||
|
||||
Args:
|
||||
data (pd.DataFrame): DataFrame containing historical stock price data.
|
||||
|
||||
Returns:
|
||||
pd.DataFrame: DataFrame with added technical indicators.
|
||||
"""
|
||||
try:
|
||||
# Moving Averages
|
||||
data.ta.macd(append=True)
|
||||
data.ta.sma(length=20, append=True)
|
||||
data.ta.ema(length=50, append=True)
|
||||
|
||||
# Momentum Indicators
|
||||
data.ta.rsi(append=True)
|
||||
data.ta.stoch(append=True)
|
||||
|
||||
# Volatility Indicators
|
||||
data.ta.bbands(append=True)
|
||||
data.ta.adx(append=True)
|
||||
|
||||
# Other Indicators
|
||||
data.ta.obv(append=True)
|
||||
data.ta.willr(append=True)
|
||||
data.ta.cmf(append=True)
|
||||
data.ta.psar(append=True)
|
||||
|
||||
# Custom Calculations
|
||||
data['OBV_in_million'] = data['OBV'] / 1e6
|
||||
data['MACD_histogram_12_26_9'] = data['MACDh_12_26_9']
|
||||
|
||||
logging.info("Technical indicators calculated successfully.")
|
||||
return data
|
||||
except KeyError as e:
|
||||
logging.error(f"Missing key in data: {e}")
|
||||
except ValueError as e:
|
||||
logging.error(f"Value error: {e}")
|
||||
except Exception as e:
|
||||
logging.error(f"Error during technical indicator calculation: {e}")
|
||||
return None
|
||||
|
||||
def get_last_day_summary(data: pd.DataFrame) -> pd.Series:
|
||||
"""
|
||||
Extracts and summarizes technical indicators for the last trading day.
|
||||
|
||||
Args:
|
||||
data (pd.DataFrame): DataFrame with calculated technical indicators.
|
||||
|
||||
Returns:
|
||||
pd.Series: Summary of technical indicators for the last day.
|
||||
"""
|
||||
try:
|
||||
last_day_summary = data.iloc[-1][[
|
||||
'Adj Close', 'MACD_12_26_9', 'MACD_histogram_12_26_9', 'RSI_14',
|
||||
'BBL_5_2.0', 'BBM_5_2.0', 'BBU_5_2.0', 'SMA_20', 'EMA_50',
|
||||
'OBV_in_million', 'STOCHk_14_3_3', 'STOCHd_14_3_3', 'ADX_14',
|
||||
'WILLR_14', 'CMF_20', 'PSARl_0.02_0.2', 'PSARs_0.02_0.2'
|
||||
]]
|
||||
logging.info("Last day summary extracted.")
|
||||
return last_day_summary
|
||||
except KeyError as e:
|
||||
logging.error(f"Missing columns in data: {e}")
|
||||
except Exception as e:
|
||||
logging.error(f"Error extracting last day summary: {e}")
|
||||
return None
|
||||
|
||||
def analyze_stock(ticker_symbol: str, start_date: datetime, end_date: datetime) -> pd.Series:
|
||||
"""
|
||||
Fetches stock data, calculates technical indicators, and provides a summary.
|
||||
|
||||
Args:
|
||||
ticker_symbol (str): The stock symbol.
|
||||
start_date (datetime): Start date for data retrieval.
|
||||
end_date (datetime): End date for data retrieval.
|
||||
|
||||
Returns:
|
||||
pd.Series: Summary of technical indicators for the last day.
|
||||
"""
|
||||
try:
|
||||
# Fetch stock data
|
||||
stock_data = yf.download(ticker_symbol, start=start_date, end=end_date)
|
||||
logging.info(f"Stock data fetched for {ticker_symbol} from {start_date} to {end_date}")
|
||||
|
||||
# Calculate technical indicators
|
||||
stock_data = calculate_technical_indicators(stock_data)
|
||||
|
||||
# Get last day summary
|
||||
if stock_data is not None:
|
||||
last_day_summary = get_last_day_summary(stock_data)
|
||||
if last_day_summary is not None:
|
||||
print("Summary of Technical Indicators for the Last Day:")
|
||||
print(last_day_summary)
|
||||
return last_day_summary
|
||||
else:
|
||||
logging.error("Stock data is None, unable to calculate indicators.")
|
||||
except Exception as e:
|
||||
logging.error(f"Error during analysis: {e}")
|
||||
return None
|
||||
|
||||
def get_finance_data(symbol: str) -> pd.Series:
|
||||
"""
|
||||
Fetches financial data for a given stock symbol.
|
||||
|
||||
Args:
|
||||
symbol (str): The stock symbol.
|
||||
|
||||
Returns:
|
||||
pd.Series: Summary of technical indicators for the last day.
|
||||
"""
|
||||
end_date = datetime.today()
|
||||
start_date = end_date - timedelta(days=120)
|
||||
|
||||
# Perform analysis
|
||||
last_day_summary = analyze_stock(symbol, start_date, end_date)
|
||||
return last_day_summary
|
||||
|
||||
def analyze_options_data(ticker: str, expiry_date: str) -> tuple:
|
||||
"""
|
||||
Analyzes option data for a given ticker and expiry date.
|
||||
|
||||
Args:
|
||||
ticker (str): The stock ticker symbol.
|
||||
expiry_date (str): The option expiry date.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing calculated metrics for call and put options.
|
||||
"""
|
||||
call_df = options.get_calls(ticker, expiry_date)
|
||||
put_df = options.get_puts(ticker, expiry_date)
|
||||
|
||||
# Implied Volatility Analysis:
|
||||
avg_call_iv = call_df["Implied Volatility"].str.rstrip("%").astype(float).mean()
|
||||
avg_put_iv = put_df["Implied Volatility"].str.rstrip("%").astype(float).mean()
|
||||
logging.info(f"Average Implied Volatility for Call Options: {avg_call_iv}%")
|
||||
logging.info(f"Average Implied Volatility for Put Options: {avg_put_iv}%")
|
||||
|
||||
# Option Prices Analysis:
|
||||
avg_call_last_price = call_df["Last Price"].mean()
|
||||
avg_put_last_price = put_df["Last Price"].mean()
|
||||
logging.info(f"Average Last Price for Call Options: {avg_call_last_price}")
|
||||
logging.info(f"Average Last Price for Put Options: {avg_put_last_price}")
|
||||
|
||||
# Strike Price Analysis:
|
||||
min_call_strike = call_df["Strike"].min()
|
||||
max_call_strike = call_df["Strike"].max()
|
||||
min_put_strike = put_df["Strike"].min()
|
||||
max_put_strike = put_df["Strike"].max()
|
||||
logging.info(f"Minimum Strike Price for Call Options: {min_call_strike}")
|
||||
logging.info(f"Maximum Strike Price for Call Options: {max_call_strike}")
|
||||
logging.info(f"Minimum Strike Price for Put Options: {min_put_strike}")
|
||||
logging.info(f"Maximum Strike Price for Put Options: {max_put_strike}")
|
||||
|
||||
# Volume Analysis:
|
||||
total_call_volume = call_df["Volume"].str.replace('-', '0').astype(float).sum()
|
||||
total_put_volume = put_df["Volume"].str.replace('-', '0').astype(float).sum()
|
||||
logging.info(f"Total Volume for Call Options: {total_call_volume}")
|
||||
logging.info(f"Total Volume for Put Options: {total_put_volume}")
|
||||
|
||||
# Open Interest Analysis:
|
||||
call_df['Open Interest'] = call_df['Open Interest'].str.replace('-', '0').astype(float)
|
||||
put_df['Open Interest'] = put_df['Open Interest'].str.replace('-', '0').astype(float)
|
||||
total_call_open_interest = call_df["Open Interest"].sum()
|
||||
total_put_open_interest = put_df["Open Interest"].sum()
|
||||
logging.info(f"Total Open Interest for Call Options: {total_call_open_interest}")
|
||||
logging.info(f"Total Open Interest for Put Options: {total_put_open_interest}")
|
||||
|
||||
# Convert Implied Volatility to float
|
||||
call_df['Implied Volatility'] = call_df['Implied Volatility'].str.replace('%', '').astype(float)
|
||||
put_df['Implied Volatility'] = put_df['Implied Volatility'].str.replace('%', '').astype(float)
|
||||
|
||||
# Calculate Put-Call Ratio
|
||||
put_call_ratio = total_put_volume / total_call_volume
|
||||
logging.info(f"Put-Call Ratio: {put_call_ratio}")
|
||||
|
||||
# Calculate Implied Volatility Percentile
|
||||
call_iv_percentile = (call_df['Implied Volatility'] > call_df['Implied Volatility'].mean()).mean() * 100
|
||||
put_iv_percentile = (put_df['Implied Volatility'] > put_df['Implied Volatility'].mean()).mean() * 100
|
||||
logging.info(f"Call Option Implied Volatility Percentile: {call_iv_percentile}")
|
||||
logging.info(f"Put Option Implied Volatility Percentile: {put_iv_percentile}")
|
||||
|
||||
# Calculate Implied Volatility Skew
|
||||
implied_vol_skew = call_df['Implied Volatility'].mean() - put_df['Implied Volatility'].mean()
|
||||
logging.info(f"Implied Volatility Skew: {implied_vol_skew}")
|
||||
|
||||
# Determine market sentiment
|
||||
is_bullish_sentiment = call_df['Implied Volatility'].mean() > put_df['Implied Volatility'].mean()
|
||||
sentiment = "bullish" if is_bullish_sentiment else "bearish"
|
||||
logging.info(f"The overall sentiment of {ticker} is {sentiment}.")
|
||||
|
||||
return (avg_call_iv, avg_put_iv, avg_call_last_price, avg_put_last_price,
|
||||
min_call_strike, max_call_strike, min_put_strike, max_put_strike,
|
||||
total_call_volume, total_put_volume, total_call_open_interest, total_put_open_interest,
|
||||
put_call_ratio, call_iv_percentile, put_iv_percentile, implied_vol_skew, sentiment)
|
||||
|
||||
def get_fin_options_data(ticker: str) -> list:
|
||||
"""
|
||||
Fetches and analyzes options data for a given stock ticker.
|
||||
|
||||
Args:
|
||||
ticker (str): The stock ticker symbol.
|
||||
|
||||
Returns:
|
||||
list: A list of sentences summarizing the options data.
|
||||
"""
|
||||
current_price = round(stock_info.get_live_price(ticker), 3)
|
||||
option_expiry_dates = options.get_expiration_dates(ticker)
|
||||
nearest_expiry = option_expiry_dates[0]
|
||||
|
||||
results = analyze_options_data(ticker, nearest_expiry)
|
||||
|
||||
# Unpack the results tuple
|
||||
(avg_call_iv, avg_put_iv, avg_call_last_price, avg_put_last_price,
|
||||
min_call_strike, max_call_strike, min_put_strike, max_put_strike,
|
||||
total_call_volume, total_put_volume, total_call_open_interest, total_put_open_interest,
|
||||
put_call_ratio, call_iv_percentile, put_iv_percentile, implied_vol_skew, sentiment) = results
|
||||
|
||||
# Create a list of complete sentences with the results
|
||||
results_sentences = [
|
||||
f"Average Implied Volatility for Call Options: {avg_call_iv}%",
|
||||
f"Average Implied Volatility for Put Options: {avg_put_iv}%",
|
||||
f"Average Last Price for Call Options: {avg_call_last_price}",
|
||||
f"Average Last Price for Put Options: {avg_put_last_price}",
|
||||
f"Minimum Strike Price for Call Options: {min_call_strike}",
|
||||
f"Maximum Strike Price for Call Options: {max_call_strike}",
|
||||
f"Minimum Strike Price for Put Options: {min_put_strike}",
|
||||
f"Maximum Strike Price for Put Options: {max_put_strike}",
|
||||
f"Total Volume for Call Options: {total_call_volume}",
|
||||
f"Total Volume for Put Options: {total_put_volume}",
|
||||
f"Total Open Interest for Call Options: {total_call_open_interest}",
|
||||
f"Total Open Interest for Put Options: {total_put_open_interest}",
|
||||
f"Put-Call Ratio: {put_call_ratio}",
|
||||
f"Call Option Implied Volatility Percentile: {call_iv_percentile}",
|
||||
f"Put Option Implied Volatility Percentile: {put_iv_percentile}",
|
||||
f"Implied Volatility Skew: {implied_vol_skew}",
|
||||
f"The overall sentiment of {ticker} is {sentiment}."
|
||||
]
|
||||
|
||||
# Print each sentence
|
||||
for sentence in results_sentences:
|
||||
logging.info(sentence)
|
||||
|
||||
return results_sentences
|
||||
96
ToBeMigrated/ai_web_researcher/firecrawl_web_crawler.py
Normal file
96
ToBeMigrated/ai_web_researcher/firecrawl_web_crawler.py
Normal file
@@ -0,0 +1,96 @@
|
||||
import os
|
||||
from pathlib import Path
|
||||
from firecrawl import FirecrawlApp
|
||||
import logging
|
||||
from dotenv import load_dotenv
|
||||
|
||||
# Load environment variables from .env file
|
||||
load_dotenv(Path('../../.env'))
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
||||
|
||||
def initialize_client() -> FirecrawlApp:
|
||||
"""
|
||||
Initialize and return a Firecrawl client.
|
||||
|
||||
Returns:
|
||||
FirecrawlApp: An instance of the Firecrawl client.
|
||||
"""
|
||||
return FirecrawlApp(api_key=os.getenv("FIRECRAWL_API_KEY"))
|
||||
|
||||
def scrape_website(website_url: str, depth: int = 1, max_pages: int = 10) -> dict:
|
||||
"""
|
||||
Scrape a website starting from the given URL.
|
||||
|
||||
Args:
|
||||
website_url (str): The URL of the website to scrape.
|
||||
depth (int, optional): The depth of crawling. Default is 1.
|
||||
max_pages (int, optional): The maximum number of pages to scrape. Default is 10.
|
||||
|
||||
Returns:
|
||||
dict: The result of the website scraping, or None if an error occurred.
|
||||
"""
|
||||
client = initialize_client()
|
||||
try:
|
||||
result = client.crawl_url({
|
||||
'url': website_url,
|
||||
'depth': depth,
|
||||
'max_pages': max_pages
|
||||
})
|
||||
return result
|
||||
except KeyError as e:
|
||||
logging.error(f"Missing key in data: {e}")
|
||||
except ValueError as e:
|
||||
logging.error(f"Value error: {e}")
|
||||
except Exception as e:
|
||||
logging.error(f"Error scraping website: {e}")
|
||||
return None
|
||||
|
||||
def scrape_url(url: str) -> dict:
|
||||
"""
|
||||
Scrape a specific URL.
|
||||
|
||||
Args:
|
||||
url (str): The URL to scrape.
|
||||
|
||||
Returns:
|
||||
dict: The result of the URL scraping, or None if an error occurred.
|
||||
"""
|
||||
client = initialize_client()
|
||||
try:
|
||||
result = client.scrape_url(url)
|
||||
return result
|
||||
except KeyError as e:
|
||||
logging.error(f"Missing key in data: {e}")
|
||||
except ValueError as e:
|
||||
logging.error(f"Value error: {e}")
|
||||
except Exception as e:
|
||||
logging.error(f"Error scraping URL: {e}")
|
||||
return None
|
||||
|
||||
def extract_data(url: str, schema: dict) -> dict:
|
||||
"""
|
||||
Extract structured data from a URL using the provided schema.
|
||||
|
||||
Args:
|
||||
url (str): The URL to extract data from.
|
||||
schema (dict): The schema to use for data extraction.
|
||||
|
||||
Returns:
|
||||
dict: The extracted data, or None if an error occurred.
|
||||
"""
|
||||
client = initialize_client()
|
||||
try:
|
||||
result = client.extract({
|
||||
'url': url,
|
||||
'schema': schema
|
||||
})
|
||||
return result
|
||||
except KeyError as e:
|
||||
logging.error(f"Missing key in data: {e}")
|
||||
except ValueError as e:
|
||||
logging.error(f"Value error: {e}")
|
||||
except Exception as e:
|
||||
logging.error(f"Error extracting data: {e}")
|
||||
return None
|
||||
339
ToBeMigrated/ai_web_researcher/google_serp_search.py
Normal file
339
ToBeMigrated/ai_web_researcher/google_serp_search.py
Normal file
@@ -0,0 +1,339 @@
|
||||
"""
|
||||
This Python script performs Google searches using various services such as SerpApi, Serper.dev, and more. It displays the search results, including organic results, People Also Ask, and Related Searches, in formatted tables. The script also utilizes GPT to generate titles and FAQs for the Google search results.
|
||||
|
||||
Features:
|
||||
- Utilizes SerpApi, Serper.dev, and other services for Google searches.
|
||||
- Displays organic search results, including position, title, link, and snippet.
|
||||
- Presents People Also Ask questions and snippets in a formatted table.
|
||||
- Includes Related Searches in the combined table with People Also Ask.
|
||||
- Configures logging with Loguru for informative messages.
|
||||
- Uses Rich and Tabulate for visually appealing and formatted tables.
|
||||
|
||||
Usage:
|
||||
- Ensure the necessary API keys are set in the .env file.
|
||||
- Run the script to perform a Google search with the specified query.
|
||||
- View the displayed tables with organic results, People Also Ask, and Related Searches.
|
||||
- Additional information, such as generated titles and FAQs using GPT, is presented.
|
||||
|
||||
Modifications:
|
||||
- Update the environment variables in the .env file with the required API keys.
|
||||
- Customize the search parameters, such as location and language, in the functions as needed.
|
||||
- Adjust logging configurations, table formatting, and other aspects based on preferences.
|
||||
|
||||
"""
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sys
|
||||
import configparser
|
||||
from pathlib import Path
|
||||
import pandas as pd
|
||||
import json
|
||||
import requests
|
||||
from clint.textui import progress
|
||||
import streamlit as st
|
||||
|
||||
#from serpapi import GoogleSearch
|
||||
from loguru import logger
|
||||
from tabulate import tabulate
|
||||
#from GoogleNews import GoogleNews
|
||||
# Configure logger
|
||||
logger.remove()
|
||||
from dotenv import load_dotenv
|
||||
# Load environment variables from .env file
|
||||
load_dotenv(Path('../../.env'))
|
||||
logger.add(
|
||||
sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
from .common_utils import save_in_file, cfg_search_param
|
||||
from tenacity import retry, stop_after_attempt, wait_random_exponential
|
||||
|
||||
|
||||
@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
|
||||
def google_search(query):
|
||||
"""
|
||||
Perform a Google search for the given query.
|
||||
|
||||
Args:
|
||||
query (str): The search query.
|
||||
flag (str, optional): The search flag (default is "faq").
|
||||
|
||||
Returns:
|
||||
list: List of search results based on the specified flag.
|
||||
"""
|
||||
#try:
|
||||
# perform_serpapi_google_search(query)
|
||||
# logger.info(f"FIXME: Google serapi: {query}")
|
||||
# #return process_search_results(search_result)
|
||||
#except Exception as err:
|
||||
# logger.error(f"ERROR: Check Here: https://serpapi.com/. Your requests may be over. {err}")
|
||||
|
||||
# Retry with serper.dev
|
||||
try:
|
||||
logger.info("Trying Google search with Serper.dev: https://serper.dev/api-key")
|
||||
search_result = perform_serperdev_google_search(query)
|
||||
if search_result:
|
||||
process_search_results(search_result)
|
||||
return(search_result)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed Google search with serper.dev: {err}")
|
||||
return None
|
||||
|
||||
|
||||
# # Retry with BROWSERLESS API
|
||||
# try:
|
||||
# search_result = perform_browserless_google_search(query)
|
||||
# #return process_search_results(search_result, flag)
|
||||
# except Exception as err:
|
||||
# logger.error("FIXME: Failed to do Google search with BROWSERLESS API.")
|
||||
# logger.debug("FIXME: Trying with dataforSEO API.")
|
||||
|
||||
|
||||
|
||||
def perform_serpapi_google_search(query):
|
||||
"""
|
||||
Perform a Google search using the SerpApi service.
|
||||
|
||||
Args:
|
||||
query (str): The search query.
|
||||
location (str, optional): The location for the search (default is "Austin, Texas").
|
||||
api_key (str, optional): Your secret API key for SerpApi.
|
||||
|
||||
Returns:
|
||||
dict: A dictionary containing the search results.
|
||||
"""
|
||||
try:
|
||||
logger.info("Reading Web search config values from main_config")
|
||||
geo_location, search_language, num_results, time_range, include_domains, similar_url = read_return_config_section('web_research')
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to read web research params: {err}")
|
||||
return
|
||||
try:
|
||||
# Check if API key is provided
|
||||
if not os.getenv("SERPAPI_KEY"):
|
||||
#raise ValueError("SERPAPI_KEY key is required for SerpApi")
|
||||
logger.error("SERPAPI_KEY key is required for SerpApi")
|
||||
return
|
||||
|
||||
|
||||
# Create a GoogleSearch instance
|
||||
search = GoogleSearch({
|
||||
"q": query,
|
||||
"location": location,
|
||||
"api_key": api_key
|
||||
})
|
||||
# Get search results as a dictionary
|
||||
result = search.get_dict()
|
||||
return result
|
||||
|
||||
except ValueError as ve:
|
||||
# Handle missing API key error
|
||||
logger.info(f"SERPAPI ValueError: {ve}")
|
||||
except Exception as e:
|
||||
# Handle other exceptions
|
||||
logger.info(f"SERPAPI An error occurred: {e}")
|
||||
|
||||
|
||||
def perform_serperdev_google_search(query):
|
||||
"""
|
||||
Perform a Google search using the Serper API.
|
||||
|
||||
Args:
|
||||
query (str): The search query.
|
||||
|
||||
Returns:
|
||||
dict: The JSON response from the Serper API.
|
||||
"""
|
||||
# Get the Serper API key from environment variables
|
||||
logger.info("Doing serper.dev google search.")
|
||||
serper_api_key = os.getenv('SERPER_API_KEY')
|
||||
|
||||
# Check if the API key is available
|
||||
if not serper_api_key:
|
||||
raise ValueError("SERPER_API_KEY is missing. Set it in the .env file.")
|
||||
|
||||
# Serper API endpoint URL
|
||||
url = "https://google.serper.dev/search"
|
||||
|
||||
try:
|
||||
geo_loc, lang, num_results = cfg_search_param('serperdev')
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to read config {err}")
|
||||
|
||||
# Build payload as end user or main_config
|
||||
payload = json.dumps({
|
||||
"q": query,
|
||||
"gl": geo_loc,
|
||||
"hl": lang,
|
||||
"num": num_results,
|
||||
"autocorrect": True,
|
||||
})
|
||||
|
||||
# Request headers with API key
|
||||
headers = {
|
||||
'X-API-KEY': serper_api_key,
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
|
||||
# Send a POST request to the Serper API with progress bar
|
||||
with progress.Bar(label="Searching", expected_size=100) as bar:
|
||||
response = requests.post(url, headers=headers, data=payload, stream=True)
|
||||
# Check if the request was successful
|
||||
if response.status_code == 200:
|
||||
# Parse and return the JSON response
|
||||
return response.json()
|
||||
else:
|
||||
# Print an error message if the request fails
|
||||
logger.error(f"Error: {response.status_code}, {response.text}")
|
||||
return None
|
||||
|
||||
|
||||
def perform_serper_news_search(news_keywords, news_country, news_language):
|
||||
""" Function for Serper.dev News google search """
|
||||
# Get the Serper API key from environment variables
|
||||
logger.info(f"Doing serper.dev google search. {news_keywords} - {news_country} - {news_language}")
|
||||
serper_api_key = os.getenv('SERPER_API_KEY')
|
||||
|
||||
# Check if the API key is available
|
||||
if not serper_api_key:
|
||||
raise ValueError("SERPER_API_KEY is missing. Set it in the .env file.")
|
||||
|
||||
# Serper API endpoint URL
|
||||
url = "https://google.serper.dev/news"
|
||||
payload = json.dumps({
|
||||
"q": news_keywords,
|
||||
"gl": news_country,
|
||||
"hl": news_language,
|
||||
})
|
||||
# Request headers with API key
|
||||
headers = {
|
||||
'X-API-KEY': serper_api_key,
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
# Send a POST request to the Serper API with progress bar
|
||||
with progress.Bar(label="Searching News", expected_size=100) as bar:
|
||||
response = requests.post(url, headers=headers, data=payload, stream=True)
|
||||
# Check if the request was successful
|
||||
if response.status_code == 200:
|
||||
# Parse and return the JSON response
|
||||
#process_search_results(response, "news")
|
||||
return response.json()
|
||||
else:
|
||||
# Print an error message if the request fails
|
||||
logger.error(f"Error: {response.status_code}, {response.text}")
|
||||
return None
|
||||
|
||||
|
||||
|
||||
def perform_browserless_google_search():
|
||||
return
|
||||
|
||||
def perform_dataforseo_google_search():
|
||||
return
|
||||
|
||||
|
||||
def google_news(search_keywords, news_period="7d", region="IN"):
|
||||
""" Get news articles from google_news"""
|
||||
googlenews = GoogleNews()
|
||||
googlenews.enableException(True)
|
||||
googlenews = GoogleNews(lang='en', region=region)
|
||||
googlenews = GoogleNews(period=news_period)
|
||||
print(googlenews.get_news('APPLE'))
|
||||
print(googlenews.search('APPLE'))
|
||||
|
||||
|
||||
def process_search_results(search_results, search_type="general"):
|
||||
"""
|
||||
Create a Pandas DataFrame from the search results.
|
||||
|
||||
Args:
|
||||
search_results (dict): The search results JSON.
|
||||
|
||||
Returns:
|
||||
pd.DataFrame: Pandas DataFrame containing the search results.
|
||||
"""
|
||||
data = []
|
||||
logger.info(f"Google Search Parameters: {search_results.get('searchParameters', {})}")
|
||||
if 'general' in search_type:
|
||||
organic_results = search_results.get("organic", [])
|
||||
if 'news' in search_type:
|
||||
organic_results = search_results.get("news", [])
|
||||
|
||||
# Displaying Organic Results
|
||||
organic_data = []
|
||||
for result in search_results["organic"]:
|
||||
position = result.get("position", "")
|
||||
title = result.get("title", "")
|
||||
link = result.get("link", "")
|
||||
snippet = result.get("snippet", "")
|
||||
organic_data.append([position, title, link, snippet])
|
||||
|
||||
organic_headers = ["Rank", "Title", "Link", "Snippet"]
|
||||
organic_table = tabulate(organic_data,
|
||||
headers=organic_headers,
|
||||
tablefmt="fancy_grid",
|
||||
colalign=["center", "left", "left", "left"],
|
||||
maxcolwidths=[5, 25, 35, 50])
|
||||
|
||||
# Print the tables
|
||||
print("\n\n📢❗🚨 Google search Organic Results:")
|
||||
print(organic_table)
|
||||
|
||||
# Displaying People Also Ask and Related Searches combined
|
||||
combined_data = []
|
||||
try:
|
||||
people_also_ask_data = []
|
||||
if "peopleAlsoAsk" in search_results:
|
||||
for question in search_results["peopleAlsoAsk"]:
|
||||
title = question.get("title", "")
|
||||
snippet = question.get("snippet", "")
|
||||
link = question.get("link", "")
|
||||
people_also_ask_data.append([title, snippet, link])
|
||||
except Exception as people_also_ask_err:
|
||||
logger.error(f"Error processing 'peopleAlsoAsk': {people_also_ask_err}")
|
||||
people_also_ask_data = []
|
||||
|
||||
related_searches_data = []
|
||||
for query in search_results.get("relatedSearches", []):
|
||||
related_searches_data.append([query.get("query", "")])
|
||||
related_searches_headers = ["Related Search"]
|
||||
|
||||
if people_also_ask_data:
|
||||
# Add Related Searches as a column to People Also Ask
|
||||
combined_data = [
|
||||
row + [related_searches_data[i][0] if i < len(related_searches_data) else ""]
|
||||
for i, row in enumerate(people_also_ask_data)
|
||||
]
|
||||
combined_headers = ["Question", "Snippet", "Link", "Related Search"]
|
||||
# Display the combined table
|
||||
combined_table = tabulate(
|
||||
combined_data,
|
||||
headers=combined_headers,
|
||||
tablefmt="fancy_grid",
|
||||
colalign=["left", "left", "left", "left"],
|
||||
maxcolwidths=[20, 50, 20, 30]
|
||||
)
|
||||
else:
|
||||
combined_table = tabulate(
|
||||
related_searches_data,
|
||||
headers=related_searches_headers,
|
||||
tablefmt="fancy_grid",
|
||||
colalign=["left"],
|
||||
maxcolwidths=[60]
|
||||
)
|
||||
|
||||
print("\n\n📢❗🚨 People Also Ask & Related Searches:")
|
||||
print(combined_table)
|
||||
# Save the combined table to a file
|
||||
try:
|
||||
# Display on Alwrity UI
|
||||
st.write(organic_table)
|
||||
st.write(combined_table)
|
||||
save_in_file(organic_table)
|
||||
save_in_file(combined_table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"Failed to save search results: {save_results_err}")
|
||||
return search_results
|
||||
500
ToBeMigrated/ai_web_researcher/google_trends_researcher.py
Normal file
500
ToBeMigrated/ai_web_researcher/google_trends_researcher.py
Normal file
@@ -0,0 +1,500 @@
|
||||
"""
|
||||
This Python script analyzes Google search keywords by fetching auto-suggestions, performing keyword clustering, and visualizing Google Trends data. It uses various libraries such as pytrends, requests_html, tqdm, and more.
|
||||
|
||||
Features:
|
||||
- Fetches auto-suggestions for a given search keyword from Google.
|
||||
- Performs keyword clustering using K-means algorithm based on TF-IDF vectors.
|
||||
- Visualizes Google Trends data, including interest over time and interest by region.
|
||||
- Retrieves related queries and topics for a set of search keywords.
|
||||
- Utilizes visualization libraries such as Matplotlib, Plotly, and Rich for displaying results.
|
||||
- Incorporates logger.for error handling and informative messages.
|
||||
|
||||
Usage:
|
||||
- Provide a search term or a list of search terms for analysis.
|
||||
- Run the script to fetch auto-suggestions, perform clustering, and visualize Google Trends data.
|
||||
- Explore the displayed results, including top keywords in each cluster and related topics.
|
||||
|
||||
Modifications:
|
||||
- Customize the search terms in the 'do_google_trends_analysis' function.
|
||||
- Adjust the number of clusters for keyword clustering and other parameters as needed.
|
||||
- Explore further visualizations and analyses based on the generated data.
|
||||
|
||||
Note: Ensure that the required libraries are installed using 'pip install pytrends requests_html tqdm tabulate plotly rich'.
|
||||
"""
|
||||
|
||||
import os
|
||||
import time # I wish
|
||||
import random
|
||||
import requests
|
||||
import numpy as np
|
||||
import sys
|
||||
from sklearn.feature_extraction.text import TfidfVectorizer
|
||||
from sklearn.cluster import KMeans
|
||||
import matplotlib.pyplot as plt
|
||||
from sklearn.metrics import silhouette_score, silhouette_samples
|
||||
from rich.console import Console
|
||||
from rich.progress import Progress
|
||||
import urllib
|
||||
import json
|
||||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
import plotly.express as px
|
||||
import plotly.io as pio
|
||||
from requests_html import HTML, HTMLSession
|
||||
from urllib.parse import quote_plus
|
||||
from tqdm import tqdm
|
||||
from tabulate import tabulate
|
||||
from pytrends.request import TrendReq
|
||||
from loguru import logger
|
||||
|
||||
# Configure logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
|
||||
def fetch_google_trends_interest_overtime(keyword):
|
||||
try:
|
||||
pytrends = TrendReq(hl='en-US', tz=360)
|
||||
pytrends.build_payload([keyword], timeframe='today 1-y', geo='US')
|
||||
|
||||
# 1. Interest Over Time
|
||||
data = pytrends.interest_over_time()
|
||||
data = data.reset_index()
|
||||
|
||||
# Visualization using Matplotlib
|
||||
plt.figure(figsize=(10, 6))
|
||||
plt.plot(data['date'], data[keyword], label=keyword)
|
||||
plt.title(f'Interest Over Time for "{keyword}"')
|
||||
plt.xlabel('Date')
|
||||
plt.ylabel('Interest')
|
||||
plt.legend()
|
||||
plt.show()
|
||||
|
||||
return data
|
||||
except Exception as e:
|
||||
logger.error(f"Error in fetch_google_trends_data: {e}")
|
||||
return pd.DataFrame()
|
||||
|
||||
|
||||
def plot_interest_by_region(kw_list):
|
||||
try:
|
||||
from pytrends.request import TrendReq
|
||||
import matplotlib.pyplot as plt
|
||||
trends = TrendReq()
|
||||
trends.build_payload(kw_list=kw_list)
|
||||
kw_list = ' '.join(kw_list)
|
||||
data = trends.interest_by_region() #sorting by region
|
||||
data = data.sort_values(by=f"{kw_list}", ascending=False)
|
||||
print("\n📢❗🚨 ")
|
||||
print(f"Top 10 regions with highest interest for keyword: {kw_list}")
|
||||
data = data.head(10) #Top 10
|
||||
print(data)
|
||||
data.reset_index().plot(x="geoName", y=f"{kw_list}",
|
||||
figsize=(20,15), kind="bar")
|
||||
plt.style.use('fivethirtyeight')
|
||||
plt.show()
|
||||
# FIXME: Send this image to vision GPT for analysis.
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error plotting interest by region: {e}")
|
||||
return None
|
||||
|
||||
|
||||
|
||||
|
||||
def get_related_topics_and_save_csv(search_keywords):
|
||||
search_keywords = [f"{search_keywords}"]
|
||||
try:
|
||||
pytrends = TrendReq(hl='en-US', tz=360)
|
||||
pytrends.build_payload(kw_list=search_keywords, timeframe='today 12-m')
|
||||
|
||||
# Get related topics - this returns a dictionary
|
||||
topics_data = pytrends.related_topics()
|
||||
|
||||
# Extract data for the first keyword
|
||||
if topics_data and search_keywords[0] in topics_data:
|
||||
keyword_data = topics_data[search_keywords[0]]
|
||||
|
||||
# Create two separate dataframes for top and rising
|
||||
top_df = keyword_data.get('top', pd.DataFrame())
|
||||
rising_df = keyword_data.get('rising', pd.DataFrame())
|
||||
|
||||
return {
|
||||
'top': top_df[['topic_title', 'value']] if not top_df.empty else pd.DataFrame(),
|
||||
'rising': rising_df[['topic_title', 'value']] if not rising_df.empty else pd.DataFrame()
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Error in related topics: {e}")
|
||||
return {'top': pd.DataFrame(), 'rising': pd.DataFrame()}
|
||||
|
||||
def get_related_queries_and_save_csv(search_keywords):
|
||||
search_keywords = [f"{search_keywords}"]
|
||||
try:
|
||||
pytrends = TrendReq(hl='en-US', tz=360)
|
||||
pytrends.build_payload(kw_list=search_keywords, timeframe='today 12-m')
|
||||
|
||||
# Get related queries - this returns a dictionary
|
||||
queries_data = pytrends.related_queries()
|
||||
|
||||
# Extract data for the first keyword
|
||||
if queries_data and search_keywords[0] in queries_data:
|
||||
keyword_data = queries_data[search_keywords[0]]
|
||||
|
||||
# Create two separate dataframes for top and rising
|
||||
top_df = keyword_data.get('top', pd.DataFrame())
|
||||
rising_df = keyword_data.get('rising', pd.DataFrame())
|
||||
|
||||
return {
|
||||
'top': top_df if not top_df.empty else pd.DataFrame(),
|
||||
'rising': rising_df if not rising_df.empty else pd.DataFrame()
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Error in related queries: {e}")
|
||||
return {'top': pd.DataFrame(), 'rising': pd.DataFrame()}
|
||||
|
||||
|
||||
def get_source(url):
|
||||
try:
|
||||
session = HTMLSession()
|
||||
response = session.get(url)
|
||||
response.raise_for_status() # Raise an HTTPError for bad responses
|
||||
return response
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger.error(f"Error during HTTP request: {e}")
|
||||
return None
|
||||
|
||||
|
||||
|
||||
def get_results(query):
|
||||
try:
|
||||
query = urllib.parse.quote_plus(query)
|
||||
response = get_source(f"https://suggestqueries.google.com/complete/search?output=chrome&hl=en&q={query}")
|
||||
time.sleep(random.uniform(0.1, 0.6))
|
||||
|
||||
if response:
|
||||
response.raise_for_status()
|
||||
results = json.loads(response.text)
|
||||
return results
|
||||
else:
|
||||
return None
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"Error decoding JSON response: {e}")
|
||||
return None
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger.error(f"Error during HTTP request: {e}")
|
||||
return None
|
||||
|
||||
|
||||
|
||||
def format_results(results):
|
||||
try:
|
||||
suggestions = []
|
||||
for index, value in enumerate(results[1]):
|
||||
suggestion = {'term': value, 'relevance': results[4]['google:suggestrelevance'][index]}
|
||||
suggestions.append(suggestion)
|
||||
return suggestions
|
||||
except (KeyError, IndexError) as e:
|
||||
logger.error(f"Error parsing search results: {e}")
|
||||
return []
|
||||
|
||||
|
||||
|
||||
def get_expanded_term_suffixes():
|
||||
return ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm','n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z']
|
||||
|
||||
|
||||
|
||||
def get_expanded_term_prefixes():
|
||||
# For shopping, review type blogs.
|
||||
#return ['discount *', 'pricing *', 'cheap', 'best price *', 'lowest price', 'best value', 'sale', 'affordable', 'promo', 'budget''what *', 'where *', 'how to *', 'why *', 'buy*', 'how much*','best *', 'worse *', 'rent*', 'sale*', 'offer*','vs*','or*']
|
||||
return ['what *', 'where *', 'how to *', 'why *','best *', 'vs*', 'or*']
|
||||
|
||||
|
||||
|
||||
def get_expanded_terms(query):
|
||||
try:
|
||||
expanded_term_prefixes = get_expanded_term_prefixes()
|
||||
expanded_term_suffixes = get_expanded_term_suffixes()
|
||||
|
||||
terms = [query]
|
||||
|
||||
for term in expanded_term_prefixes:
|
||||
terms.append(f"{term} {query}")
|
||||
|
||||
for term in expanded_term_suffixes:
|
||||
terms.append(f"{query} {term}")
|
||||
|
||||
return terms
|
||||
except Exception as e:
|
||||
logger.error(f"Error in get_expanded_terms: {e}")
|
||||
return []
|
||||
|
||||
|
||||
|
||||
def get_expanded_suggestions(query):
|
||||
try:
|
||||
all_results = []
|
||||
|
||||
expanded_terms = get_expanded_terms(query)
|
||||
for term in tqdm(expanded_terms, desc="📢❗🚨 Fetching Google AutoSuggestions", unit="term"):
|
||||
results = get_results(term)
|
||||
if results:
|
||||
formatted_results = format_results(results)
|
||||
all_results += formatted_results
|
||||
all_results = sorted(all_results, key=lambda k: k.get('relevance', 0), reverse=True)
|
||||
|
||||
return all_results
|
||||
except Exception as e:
|
||||
logger.error(f"Error in get_expanded_suggestions: {e}")
|
||||
return []
|
||||
|
||||
|
||||
|
||||
def get_suggestions_for_keyword(search_term):
|
||||
""" """
|
||||
try:
|
||||
expanded_results = get_expanded_suggestions(search_term)
|
||||
expanded_results_df = pd.DataFrame(expanded_results)
|
||||
expanded_results_df.columns = ['Keywords', 'Relevance']
|
||||
#expanded_results_df.to_csv('results.csv', index=False)
|
||||
pd.set_option('display.max_rows', expanded_results_df.shape[0]+1)
|
||||
expanded_results_df.drop_duplicates('Keywords', inplace=True)
|
||||
table = tabulate(expanded_results_df, headers=['Keywords', 'Relevance'], tablefmt='fancy_grid')
|
||||
# FIXME: Too much data for LLM context window. We will need to embed it.
|
||||
#try:
|
||||
# save_in_file(table)
|
||||
#except Exception as save_results_err:
|
||||
# logger.error(f"Failed to save search results: {save_results_err}")
|
||||
return expanded_results_df
|
||||
except Exception as e:
|
||||
logger.error(f"get_suggestions_for_keyword: Error in main: {e}")
|
||||
|
||||
|
||||
|
||||
def perform_keyword_clustering(expanded_results_df, num_clusters=5):
|
||||
try:
|
||||
# Preprocessing: Convert the keywords to lowercase
|
||||
expanded_results_df['Keywords'] = expanded_results_df['Keywords'].str.lower()
|
||||
|
||||
# Vectorization: Create a TF-IDF vectorizer
|
||||
vectorizer = TfidfVectorizer()
|
||||
|
||||
# Fit the vectorizer to the keywords
|
||||
tfidf_vectors = vectorizer.fit_transform(expanded_results_df['Keywords'])
|
||||
|
||||
# Applying K-means clustering
|
||||
kmeans = KMeans(n_clusters=num_clusters, random_state=42)
|
||||
cluster_labels = kmeans.fit_predict(tfidf_vectors)
|
||||
|
||||
# Add cluster labels to the DataFrame
|
||||
expanded_results_df['cluster_label'] = cluster_labels
|
||||
|
||||
# Assessing cluster quality through silhouette score
|
||||
silhouette_avg = silhouette_score(tfidf_vectors, cluster_labels)
|
||||
print(f"Silhouette Score: {silhouette_avg}")
|
||||
|
||||
# Visualize cluster quality using a silhouette plot
|
||||
#visualize_silhouette(tfidf_vectors, cluster_labels)
|
||||
|
||||
return expanded_results_df
|
||||
except Exception as e:
|
||||
logger.error(f"Error in perform_keyword_clustering: {e}")
|
||||
return pd.DataFrame()
|
||||
|
||||
|
||||
|
||||
def visualize_silhouette(X, labels):
|
||||
try:
|
||||
silhouette_avg = silhouette_score(X, labels)
|
||||
print(f"Silhouette Score: {silhouette_avg}")
|
||||
|
||||
# Create a subplot with 1 row and 2 columns
|
||||
fig, ax1 = plt.subplots(1, 1, figsize=(8, 6))
|
||||
|
||||
# The 1st subplot is the silhouette plot
|
||||
ax1.set_xlim([-0.1, 1])
|
||||
ax1.set_ylim([0, X.shape[0] + (len(set(labels)) + 1) * 10])
|
||||
|
||||
# Compute the silhouette scores for each sample
|
||||
sample_silhouette_values = silhouette_samples(X, labels)
|
||||
|
||||
y_lower = 10
|
||||
for i in set(labels):
|
||||
# Aggregate the silhouette scores for samples belonging to the cluster
|
||||
ith_cluster_silhouette_values = sample_silhouette_values[labels == i]
|
||||
ith_cluster_silhouette_values.sort()
|
||||
|
||||
size_cluster_i = ith_cluster_silhouette_values.shape[0]
|
||||
y_upper = y_lower + size_cluster_i
|
||||
|
||||
color = plt.cm.nipy_spectral(float(i) / len(set(labels)))
|
||||
ax1.fill_betweenx(np.arange(y_lower, y_upper),
|
||||
0, ith_cluster_silhouette_values,
|
||||
facecolor=color, edgecolor=color, alpha=0.7)
|
||||
|
||||
# Label the silhouette plots with their cluster numbers at the middle
|
||||
ax1.text(-0.05, y_lower + 0.5 * size_cluster_i, str(i))
|
||||
|
||||
# Compute the new y_lower for the next plot
|
||||
y_lower = y_upper + 10 # 10 for the 0 samples
|
||||
|
||||
ax1.set_title("Silhouette plot for KMeans clustering")
|
||||
ax1.set_xlabel("Silhouette coefficient values")
|
||||
ax1.set_ylabel("Cluster label")
|
||||
|
||||
# The vertical line for the average silhouette score of all the values
|
||||
ax1.axvline(x=silhouette_avg, color="red", linestyle="--")
|
||||
|
||||
plt.show()
|
||||
except Exception as e:
|
||||
logger.error(f"Error in visualize_silhouette: {e}")
|
||||
|
||||
|
||||
|
||||
def print_and_return_top_keywords(expanded_results_df, num_clusters=5):
|
||||
"""
|
||||
Display and return top keywords in each cluster.
|
||||
|
||||
Args:
|
||||
expanded_results_df (pd.DataFrame): DataFrame containing expanded keywords, relevance, and cluster labels.
|
||||
num_clusters (int or str): Number of clusters or 'all'.
|
||||
|
||||
Returns:
|
||||
pd.DataFrame: DataFrame with top keywords for each cluster.
|
||||
"""
|
||||
top_keywords_df = pd.DataFrame()
|
||||
|
||||
if num_clusters == 'all':
|
||||
unique_clusters = expanded_results_df['cluster_label'].unique()
|
||||
else:
|
||||
unique_clusters = range(int(num_clusters))
|
||||
|
||||
for i in unique_clusters:
|
||||
cluster_df = expanded_results_df[expanded_results_df['cluster_label'] == i]
|
||||
top_keywords = cluster_df.sort_values(by='Relevance', ascending=False).head(5)
|
||||
top_keywords_df = pd.concat([top_keywords_df, top_keywords])
|
||||
|
||||
print(f"\n📢❗🚨 GTop Keywords for All Clusters:")
|
||||
table = tabulate(top_keywords_df, headers='keys', tablefmt='fancy_grid')
|
||||
# Save the combined table to a file
|
||||
try:
|
||||
save_in_file(table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"🚨 Failed to save search results: {save_results_err}")
|
||||
print(table)
|
||||
return top_keywords_df
|
||||
|
||||
|
||||
def generate_wordcloud(keywords):
|
||||
"""
|
||||
Generate and display a word cloud from a list of keywords.
|
||||
|
||||
Args:
|
||||
keywords (list): List of keywords.
|
||||
"""
|
||||
# Convert the list of keywords to a string
|
||||
text = ' '.join(keywords)
|
||||
|
||||
# Generate word cloud
|
||||
wordcloud = WordCloud(width=800, height=400, background_color='white').generate(text)
|
||||
|
||||
# Display the word cloud using matplotlib
|
||||
plt.figure(figsize=(600, 200))
|
||||
plt.imshow(wordcloud, interpolation='bilinear')
|
||||
plt.axis('off')
|
||||
plt.show()
|
||||
|
||||
|
||||
|
||||
def save_in_file(table_content):
|
||||
""" Helper function to save search analysis in a file. """
|
||||
file_path = os.environ.get('SEARCH_SAVE_FILE')
|
||||
try:
|
||||
# Save the content to the file
|
||||
with open(file_path, "a+", encoding="utf-8") as file:
|
||||
file.write(table_content)
|
||||
file.write("\n" * 3) # Add three newlines at the end
|
||||
logger.info(f"Search content saved to {file_path}")
|
||||
except Exception as e:
|
||||
logger.error(f"Error occurred while writing to the file: {e}")
|
||||
|
||||
|
||||
def do_google_trends_analysis(search_term):
|
||||
""" Get a google search keywords, get its stats."""
|
||||
search_term = [f"{search_term}"]
|
||||
all_the_keywords = []
|
||||
try:
|
||||
for asearch_term in search_term:
|
||||
#FIXME: Lets work with a single root keyword.
|
||||
suggestions_df = get_suggestions_for_keyword(asearch_term)
|
||||
if len(suggestions_df['Keywords']) > 10:
|
||||
result_df = perform_keyword_clustering(suggestions_df)
|
||||
# Display top keywords in each cluster
|
||||
top_keywords = print_and_return_top_keywords(result_df)
|
||||
all_the_keywords.append(top_keywords['Keywords'].tolist())
|
||||
else:
|
||||
all_the_keywords.append(suggestions_df['Keywords'].tolist())
|
||||
all_the_keywords = ','.join([', '.join(filter(None, map(str, sublist))) for sublist in all_the_keywords])
|
||||
|
||||
# Generate a random sleep time between 2 and 3 seconds
|
||||
time.sleep(random.uniform(2, 3))
|
||||
|
||||
# Display additional information
|
||||
try:
|
||||
result_df = get_related_topics_and_save_csv(search_term)
|
||||
logger.info(f"Related topics:: result_df: {result_df}")
|
||||
# Extract 'Top' topic_title
|
||||
if result_df:
|
||||
top_topic_title = result_df['top']['topic_title'].values.tolist()
|
||||
# Join each sublist into one string separated by comma
|
||||
#top_topic_title = [','.join(filter(None, map(str, sublist))) for sublist in top_topic_title]
|
||||
top_topic_title = ','.join([', '.join(filter(None, map(str, sublist))) for sublist in top_topic_title])
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to get results from google trends related topics: {err}")
|
||||
|
||||
# TBD: Not getting great results OR unable to understand them.
|
||||
#all_the_keywords += top_topic_title
|
||||
all_the_keywords = all_the_keywords.split(',')
|
||||
# Split the list into chunks of 5 keywords
|
||||
chunk_size = 4
|
||||
chunks = [all_the_keywords[i:i + chunk_size] for i in range(0, len(all_the_keywords), chunk_size)]
|
||||
# Create a DataFrame with columns named 'Keyword 1', 'Keyword 2', etc.
|
||||
combined_df = pd.DataFrame(chunks, columns=[f'K📢eyword Col{i + 1}' for i in range(chunk_size)])
|
||||
|
||||
# Print the table
|
||||
table = tabulate(combined_df, headers='keys', tablefmt='fancy_grid')
|
||||
# Save the combined table to a file
|
||||
try:
|
||||
save_in_file(table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"Failed to save search results: {save_results_err}")
|
||||
print(table)
|
||||
|
||||
#generate_wordcloud(all_the_keywords)
|
||||
return(all_the_keywords)
|
||||
except Exception as e:
|
||||
logger.error(f"Error in Google Trends Analysis: {e}")
|
||||
|
||||
|
||||
def get_trending_searches(country='united_states'):
|
||||
"""Get trending searches for a specific country."""
|
||||
try:
|
||||
pytrends = TrendReq(hl='en-US', tz=360)
|
||||
trending_searches = pytrends.trending_searches(pn=country)
|
||||
return trending_searches
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting trending searches: {e}")
|
||||
return pd.DataFrame()
|
||||
|
||||
def get_realtime_trends(country='US'):
|
||||
"""Get realtime trending searches for a specific country."""
|
||||
try:
|
||||
pytrends = TrendReq(hl='en-US', tz=360)
|
||||
realtime_trends = pytrends.realtime_trending_searches(pn=country)
|
||||
return realtime_trends
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting realtime trends: {e}")
|
||||
return pd.DataFrame()
|
||||
803
ToBeMigrated/ai_web_researcher/gpt_online_researcher.py
Normal file
803
ToBeMigrated/ai_web_researcher/gpt_online_researcher.py
Normal file
@@ -0,0 +1,803 @@
|
||||
################################################################
|
||||
#
|
||||
# ## Features
|
||||
#
|
||||
# - **Web Research**: Alwrity enables users to conduct web research efficiently.
|
||||
# By providing keywords or topics of interest, users can initiate searches across multiple platforms simultaneously.
|
||||
#
|
||||
# - **Google SERP Search**: The tool integrates with Google Search Engine Results Pages (SERP)
|
||||
# to retrieve relevant information based on user queries. It offers insights into organic search results,
|
||||
# People Also Ask, and related searches.
|
||||
#
|
||||
# - **Tavily AI Integration**: Alwrity leverages Tavily AI's capabilities to enhance web research.
|
||||
# It utilizes advanced algorithms to search for information and extract relevant data from various sources.
|
||||
#
|
||||
# - **Metaphor AI Semantic Search**: Alwrity employs Metaphor AI's semantic search technology to find related articles and content.
|
||||
# By analyzing context and meaning, it delivers precise and accurate results.
|
||||
#
|
||||
# - **Google Trends Analysis**: The tool provides Google Trends analysis for user-defined keywords.
|
||||
# It helps users understand the popularity and trends associated with specific topics over time.
|
||||
#
|
||||
##############################################################
|
||||
|
||||
import os
|
||||
import json
|
||||
import time
|
||||
from pathlib import Path
|
||||
import sys
|
||||
from datetime import datetime
|
||||
import streamlit as st
|
||||
import pandas as pd
|
||||
import random
|
||||
import numpy as np
|
||||
|
||||
from lib.alwrity_ui.display_google_serp_results import (
|
||||
process_research_results,
|
||||
process_search_results,
|
||||
display_research_results
|
||||
)
|
||||
from lib.alwrity_ui.google_trends_ui import display_google_trends_data, process_trends_data
|
||||
|
||||
from .tavily_ai_search import do_tavily_ai_search
|
||||
from .metaphor_basic_neural_web_search import metaphor_search_articles, streamlit_display_metaphor_results
|
||||
from .google_serp_search import google_search
|
||||
from .google_trends_researcher import do_google_trends_analysis
|
||||
#from .google_gemini_web_researcher import do_gemini_web_research
|
||||
|
||||
from loguru import logger
|
||||
# Configure logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
|
||||
def gpt_web_researcher(search_keywords, search_mode, **kwargs):
|
||||
"""Keyword based web researcher with progress tracking."""
|
||||
|
||||
logger.info(f"Starting web research - Keywords: {search_keywords}, Mode: {search_mode}")
|
||||
logger.debug(f"Additional parameters: {kwargs}")
|
||||
|
||||
try:
|
||||
# Reset session state variables for this research operation
|
||||
if 'metaphor_results_displayed' in st.session_state:
|
||||
del st.session_state.metaphor_results_displayed
|
||||
|
||||
# Initialize result container
|
||||
research_results = None
|
||||
|
||||
# Create status containers
|
||||
status_container = st.empty()
|
||||
progress_bar = st.progress(0)
|
||||
|
||||
def update_progress(message, progress=None, level="info"):
|
||||
if progress is not None:
|
||||
progress_bar.progress(progress)
|
||||
if level == "error":
|
||||
status_container.error(f"🚫 {message}")
|
||||
elif level == "warning":
|
||||
status_container.warning(f"⚠️ {message}")
|
||||
else:
|
||||
status_container.info(f"🔄 {message}")
|
||||
logger.debug(f"Progress update [{level}]: {message}")
|
||||
|
||||
if search_mode == "google":
|
||||
logger.info("Starting Google research pipeline")
|
||||
|
||||
try:
|
||||
# First try Google SERP
|
||||
update_progress("Initiating SERP search...", progress=10)
|
||||
serp_results = do_google_serp_search(search_keywords, **kwargs)
|
||||
|
||||
if serp_results and serp_results.get('organic'):
|
||||
logger.info("SERP search successful")
|
||||
update_progress("SERP search completed", progress=40)
|
||||
research_results = serp_results
|
||||
else:
|
||||
logger.warning("SERP search returned no results, falling back to Gemini")
|
||||
update_progress("No SERP results, trying Gemini...", progress=45)
|
||||
|
||||
# Keep it commented. Fallback to Gemini
|
||||
#try:
|
||||
# gemini_results = do_gemini_web_research(search_keywords)
|
||||
# if gemini_results:
|
||||
# logger.info("Gemini research successful")
|
||||
# update_progress("Gemini research completed", progress=80)
|
||||
# research_results = {
|
||||
# 'source': 'gemini',
|
||||
# 'results': gemini_results
|
||||
# }
|
||||
#except Exception as gemini_err:
|
||||
# logger.error(f"Gemini research failed: {gemini_err}")
|
||||
# update_progress("Gemini research failed", level="warning")
|
||||
|
||||
if research_results:
|
||||
update_progress("Processing final results...", progress=90)
|
||||
processed_results = process_research_results(research_results)
|
||||
|
||||
if processed_results:
|
||||
update_progress("Research completed!", progress=100, level="success")
|
||||
display_research_results(processed_results)
|
||||
return processed_results
|
||||
else:
|
||||
error_msg = "Failed to process research results"
|
||||
logger.warning(error_msg)
|
||||
update_progress(error_msg, level="warning")
|
||||
return None
|
||||
else:
|
||||
error_msg = "No results from either SERP or Gemini"
|
||||
logger.warning(error_msg)
|
||||
update_progress(error_msg, level="warning")
|
||||
return None
|
||||
|
||||
except Exception as search_err:
|
||||
error_msg = f"Research pipeline failed: {str(search_err)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
update_progress(error_msg, level="error")
|
||||
raise
|
||||
|
||||
elif search_mode == "ai":
|
||||
logger.info("Starting AI research pipeline")
|
||||
|
||||
try:
|
||||
# Do Tavily AI Search
|
||||
update_progress("Initiating Tavily AI search...", progress=10)
|
||||
|
||||
# Extract relevant parameters for Tavily search
|
||||
include_domains = kwargs.pop('include_domains', None)
|
||||
search_depth = kwargs.pop('search_depth', 'advanced')
|
||||
|
||||
# Pass the parameters to do_tavily_ai_search
|
||||
t_results = do_tavily_ai_search(
|
||||
search_keywords, # Pass as positional argument
|
||||
max_results=kwargs.get('num_results', 10),
|
||||
include_domains=include_domains,
|
||||
search_depth=search_depth,
|
||||
**kwargs
|
||||
)
|
||||
|
||||
# Do Metaphor AI Search
|
||||
update_progress("Initiating Metaphor AI search...", progress=50)
|
||||
metaphor_results, metaphor_titles = do_metaphor_ai_research(search_keywords)
|
||||
|
||||
if metaphor_results is None:
|
||||
update_progress("Metaphor AI search failed, continuing with Tavily results only...", level="warning")
|
||||
else:
|
||||
update_progress("Metaphor AI search completed successfully", progress=75)
|
||||
# Add debug logging to check the structure of metaphor_results
|
||||
logger.debug(f"Metaphor results structure: {type(metaphor_results)}")
|
||||
if isinstance(metaphor_results, dict):
|
||||
logger.debug(f"Metaphor results keys: {metaphor_results.keys()}")
|
||||
if 'data' in metaphor_results:
|
||||
logger.debug(f"Metaphor data keys: {metaphor_results['data'].keys()}")
|
||||
if 'results' in metaphor_results['data']:
|
||||
logger.debug(f"Number of results: {len(metaphor_results['data']['results'])}")
|
||||
|
||||
# Display Metaphor results only if not already displayed
|
||||
if 'metaphor_results_displayed' not in st.session_state:
|
||||
st.session_state.metaphor_results_displayed = True
|
||||
# Make sure to pass the correct parameters to streamlit_display_metaphor_results
|
||||
streamlit_display_metaphor_results(metaphor_results, search_keywords)
|
||||
|
||||
# Add Google Trends Analysis
|
||||
update_progress("Initiating Google Trends analysis...", progress=80)
|
||||
try:
|
||||
# Add an informative message about Google Trends
|
||||
with st.expander("ℹ️ About Google Trends Analysis", expanded=False):
|
||||
st.markdown("""
|
||||
**What is Google Trends Analysis?**
|
||||
|
||||
Google Trends Analysis provides insights into how often a particular search-term is entered relative to the total search-volume across various regions of the world, and in various languages.
|
||||
|
||||
**What data will be shown?**
|
||||
|
||||
- **Related Keywords**: Terms that are frequently searched together with your keyword
|
||||
- **Interest Over Time**: How interest in your keyword has changed over the past 12 months
|
||||
- **Regional Interest**: Where in the world your keyword is most popular
|
||||
- **Related Queries**: What people search for before and after searching for your keyword
|
||||
- **Related Topics**: Topics that are closely related to your keyword
|
||||
|
||||
**How to use this data:**
|
||||
|
||||
- Identify trending topics in your industry
|
||||
- Understand seasonal patterns in search behavior
|
||||
- Discover related keywords for content planning
|
||||
- Target content to specific regions with high interest
|
||||
""")
|
||||
|
||||
trends_results = do_google_pytrends_analysis(search_keywords)
|
||||
if trends_results:
|
||||
update_progress("Google Trends analysis completed successfully", progress=90)
|
||||
# Store trends results in the research_results
|
||||
if metaphor_results:
|
||||
metaphor_results['trends_data'] = trends_results
|
||||
else:
|
||||
# If metaphor_results is None, create a new container for results
|
||||
metaphor_results = {'trends_data': trends_results}
|
||||
|
||||
# Display Google Trends data using the new UI module
|
||||
display_google_trends_data(trends_results, search_keywords)
|
||||
else:
|
||||
update_progress("Google Trends analysis returned no results", level="warning")
|
||||
except Exception as trends_err:
|
||||
logger.error(f"Google Trends analysis failed: {trends_err}")
|
||||
update_progress("Google Trends analysis failed", level="warning")
|
||||
st.error(f"Error in Google Trends analysis: {str(trends_err)}")
|
||||
|
||||
# Return the combined results
|
||||
update_progress("Research completed!", progress=100, level="success")
|
||||
return metaphor_results or t_results
|
||||
|
||||
except Exception as ai_err:
|
||||
error_msg = f"AI research pipeline failed: {str(ai_err)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
update_progress(error_msg, level="error")
|
||||
raise
|
||||
|
||||
else:
|
||||
error_msg = f"Unsupported search mode: {search_mode}"
|
||||
logger.error(error_msg)
|
||||
update_progress(error_msg, level="error")
|
||||
raise ValueError(error_msg)
|
||||
|
||||
except Exception as err:
|
||||
error_msg = f"Failed in gpt_web_researcher: {str(err)}"
|
||||
logger.error(error_msg, exc_info=True)
|
||||
if 'update_progress' in locals():
|
||||
update_progress(error_msg, level="error")
|
||||
raise
|
||||
|
||||
|
||||
def do_google_serp_search(search_keywords, status_container, update_progress, **kwargs):
|
||||
"""Perform Google SERP analysis with sidebar progress tracking."""
|
||||
|
||||
logger.info("="*50)
|
||||
logger.info("Starting Google SERP Search")
|
||||
logger.info("="*50)
|
||||
|
||||
try:
|
||||
# Validate parameters
|
||||
update_progress("Validating search parameters", progress=0.1)
|
||||
status_container.info("📝 Validating parameters...")
|
||||
|
||||
if not search_keywords or not isinstance(search_keywords, str):
|
||||
logger.error(f"Invalid search keywords: {search_keywords}")
|
||||
raise ValueError("Search keywords must be a non-empty string")
|
||||
|
||||
# Update search initiation
|
||||
update_progress(f"Initiating search for: '{search_keywords}'", progress=0.2)
|
||||
status_container.info("🌐 Querying search API...")
|
||||
logger.info(f"Search params: {kwargs}")
|
||||
|
||||
# Execute search
|
||||
g_results = google_search(search_keywords)
|
||||
|
||||
if g_results:
|
||||
# Log success
|
||||
update_progress("Search completed successfully", progress=0.8, level="success")
|
||||
|
||||
# Update statistics
|
||||
stats = f"""Found:
|
||||
- {len(g_results.get('organic', []))} organic results
|
||||
- {len(g_results.get('peopleAlsoAsk', []))} related questions
|
||||
- {len(g_results.get('relatedSearches', []))} related searches"""
|
||||
update_progress(stats, progress=0.9)
|
||||
|
||||
# Process results
|
||||
update_progress("Processing search results", progress=0.95)
|
||||
status_container.info("⚡ Processing results...")
|
||||
processed_results = process_search_results(g_results)
|
||||
|
||||
# Extract titles
|
||||
update_progress("Extracting information", progress=0.98)
|
||||
g_titles = extract_info(g_results, 'titles')
|
||||
|
||||
# Final success
|
||||
update_progress("Analysis completed successfully", progress=1.0, level="success")
|
||||
status_container.success("✨ Research completed!")
|
||||
|
||||
# Clear main status after delay
|
||||
time.sleep(1)
|
||||
status_container.empty()
|
||||
|
||||
return {
|
||||
'results': g_results,
|
||||
'titles': g_titles,
|
||||
'summary': processed_results,
|
||||
'stats': {
|
||||
'organic_count': len(g_results.get('organic', [])),
|
||||
'questions_count': len(g_results.get('peopleAlsoAsk', [])),
|
||||
'related_count': len(g_results.get('relatedSearches', []))
|
||||
}
|
||||
}
|
||||
|
||||
else:
|
||||
update_progress("No results found", progress=0.5, level="warning")
|
||||
status_container.warning("⚠️ No results found")
|
||||
return None
|
||||
|
||||
except Exception as err:
|
||||
error_msg = f"Search failed: {str(err)}"
|
||||
update_progress(error_msg, progress=0.5, level="error")
|
||||
logger.error(error_msg)
|
||||
logger.debug("Stack trace:", exc_info=True)
|
||||
raise
|
||||
|
||||
finally:
|
||||
logger.info("="*50)
|
||||
logger.info("Google SERP Search function completed")
|
||||
logger.info("="*50)
|
||||
|
||||
|
||||
def do_tavily_ai_search(search_keywords, max_results=10, **kwargs):
|
||||
""" Common function to do Tavily AI web research."""
|
||||
try:
|
||||
logger.info(f"Doing Tavily AI search for: {search_keywords}")
|
||||
|
||||
# Prepare Tavily search parameters
|
||||
tavily_params = {
|
||||
'max_results': max_results,
|
||||
'search_depth': 'advanced' if kwargs.get('search_depth', 3) > 2 else 'basic',
|
||||
'time_range': kwargs.get('time_range', 'year'),
|
||||
'include_domains': kwargs.get('include_domains', [""]) if kwargs.get('include_domains') else [""]
|
||||
}
|
||||
|
||||
# Import the Tavily search function directly
|
||||
from .tavily_ai_search import do_tavily_ai_search as tavily_search
|
||||
|
||||
# Call the actual Tavily search function
|
||||
t_results = tavily_search(
|
||||
keywords=search_keywords,
|
||||
**tavily_params
|
||||
)
|
||||
|
||||
if t_results:
|
||||
t_titles = tavily_extract_information(t_results, 'titles')
|
||||
t_answer = tavily_extract_information(t_results, 'answer')
|
||||
return(t_results, t_titles, t_answer)
|
||||
else:
|
||||
logger.warning("No results returned from Tavily AI search")
|
||||
return None, None, None
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to do Tavily AI Search: {err}")
|
||||
return None, None, None
|
||||
|
||||
|
||||
def do_metaphor_ai_research(search_keywords):
|
||||
"""
|
||||
Perform Metaphor AI research and return results with titles.
|
||||
|
||||
Args:
|
||||
search_keywords (str): Keywords to search for
|
||||
|
||||
Returns:
|
||||
tuple: (response_articles, titles) or (None, None) if search fails
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Start Semantic/Neural web search with Metaphor: {search_keywords}")
|
||||
response_articles = metaphor_search_articles(search_keywords)
|
||||
|
||||
if response_articles and 'data' in response_articles:
|
||||
m_titles = [result.get('title', '') for result in response_articles['data'].get('results', [])]
|
||||
return response_articles, m_titles
|
||||
else:
|
||||
logger.warning("No valid results from Metaphor search")
|
||||
return None, None
|
||||
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to do Metaphor search: {err}")
|
||||
return None, None
|
||||
|
||||
|
||||
def do_google_pytrends_analysis(keywords):
|
||||
"""
|
||||
Perform Google Trends analysis for the given keywords.
|
||||
|
||||
Args:
|
||||
keywords (str): The search keywords to analyze
|
||||
|
||||
Returns:
|
||||
dict: A dictionary containing formatted Google Trends data with the following keys:
|
||||
- related_keywords: List of related keywords
|
||||
- interest_over_time: DataFrame with date and interest columns
|
||||
- regional_interest: DataFrame with country_code, country, and interest columns
|
||||
- related_queries: DataFrame with query and value columns
|
||||
- related_topics: DataFrame with topic and value columns
|
||||
"""
|
||||
logger.info(f"Performing Google Trends analysis for keywords: {keywords}")
|
||||
|
||||
# Create a progress container for Streamlit
|
||||
progress_container = st.empty()
|
||||
progress_bar = st.progress(0)
|
||||
|
||||
def update_progress(message, progress=None, level="info"):
|
||||
"""Helper function to update progress in Streamlit UI"""
|
||||
if progress is not None:
|
||||
progress_bar.progress(progress)
|
||||
|
||||
if level == "error":
|
||||
progress_container.error(f"🚫 {message}")
|
||||
elif level == "warning":
|
||||
progress_container.warning(f"⚠️ {message}")
|
||||
else:
|
||||
progress_container.info(f"🔄 {message}")
|
||||
logger.debug(f"Progress update [{level}]: {message}")
|
||||
|
||||
try:
|
||||
# Initialize the formatted data dictionary
|
||||
formatted_data = {
|
||||
'related_keywords': [],
|
||||
'interest_over_time': pd.DataFrame(),
|
||||
'regional_interest': pd.DataFrame(),
|
||||
'related_queries': pd.DataFrame(),
|
||||
'related_topics': pd.DataFrame()
|
||||
}
|
||||
|
||||
# Get raw trends data from google_trends_researcher
|
||||
update_progress("Fetching Google Trends data...", progress=10)
|
||||
raw_trends_data = do_google_trends_analysis(keywords)
|
||||
|
||||
if not raw_trends_data:
|
||||
logger.warning("No Google Trends data returned")
|
||||
update_progress("No Google Trends data returned", level="warning", progress=20)
|
||||
return formatted_data
|
||||
|
||||
# Process related keywords from the raw data
|
||||
update_progress("Processing related keywords...", progress=30)
|
||||
if isinstance(raw_trends_data, list):
|
||||
formatted_data['related_keywords'] = raw_trends_data
|
||||
elif isinstance(raw_trends_data, dict):
|
||||
if 'keywords' in raw_trends_data:
|
||||
formatted_data['related_keywords'] = raw_trends_data['keywords']
|
||||
if 'interest_over_time' in raw_trends_data:
|
||||
formatted_data['interest_over_time'] = raw_trends_data['interest_over_time']
|
||||
if 'regional_interest' in raw_trends_data:
|
||||
formatted_data['regional_interest'] = raw_trends_data['regional_interest']
|
||||
if 'related_queries' in raw_trends_data:
|
||||
formatted_data['related_queries'] = raw_trends_data['related_queries']
|
||||
if 'related_topics' in raw_trends_data:
|
||||
formatted_data['related_topics'] = raw_trends_data['related_topics']
|
||||
|
||||
# If we have keywords but missing other data, try to fetch them using pytrends directly
|
||||
if formatted_data['related_keywords'] and (
|
||||
formatted_data['interest_over_time'].empty or
|
||||
formatted_data['regional_interest'].empty or
|
||||
formatted_data['related_queries'].empty or
|
||||
formatted_data['related_topics'].empty
|
||||
):
|
||||
try:
|
||||
update_progress("Fetching additional data from Google Trends API...", progress=40)
|
||||
from pytrends.request import TrendReq
|
||||
pytrends = TrendReq(hl='en-US', tz=360)
|
||||
|
||||
# Build payload with the main keyword
|
||||
update_progress("Building search payload...", progress=45)
|
||||
pytrends.build_payload([keywords], timeframe='today 12-m', geo='')
|
||||
|
||||
# Get interest over time if missing
|
||||
if formatted_data['interest_over_time'].empty:
|
||||
try:
|
||||
update_progress("Fetching interest over time data...", progress=50)
|
||||
interest_df = pytrends.interest_over_time()
|
||||
if not interest_df.empty:
|
||||
formatted_data['interest_over_time'] = interest_df.reset_index()
|
||||
update_progress(f"Successfully fetched interest over time data with {len(formatted_data['interest_over_time'])} data points", progress=55)
|
||||
else:
|
||||
update_progress("No interest over time data available", level="warning", progress=55)
|
||||
except Exception as e:
|
||||
logger.error(f"Error fetching interest over time: {e}")
|
||||
update_progress(f"Error fetching interest over time: {str(e)}", level="warning", progress=55)
|
||||
|
||||
# Get regional interest if missing
|
||||
if formatted_data['regional_interest'].empty:
|
||||
try:
|
||||
update_progress("Fetching regional interest data...", progress=60)
|
||||
regional_df = pytrends.interest_by_region()
|
||||
if not regional_df.empty:
|
||||
formatted_data['regional_interest'] = regional_df.reset_index()
|
||||
update_progress(f"Successfully fetched regional interest data for {len(formatted_data['regional_interest'])} regions", progress=65)
|
||||
else:
|
||||
update_progress("No regional interest data available", level="warning", progress=65)
|
||||
except Exception as e:
|
||||
logger.error(f"Error fetching regional interest: {e}")
|
||||
update_progress(f"Error fetching regional interest: {str(e)}", level="warning", progress=65)
|
||||
|
||||
# Get related queries if missing
|
||||
if formatted_data['related_queries'].empty:
|
||||
try:
|
||||
update_progress("Fetching related queries data...", progress=70)
|
||||
# Get related queries data
|
||||
related_queries = pytrends.related_queries()
|
||||
|
||||
# Create empty DataFrame as fallback
|
||||
formatted_data['related_queries'] = pd.DataFrame(columns=['query', 'value'])
|
||||
|
||||
# Simple direct approach to avoid list index errors
|
||||
if related_queries and isinstance(related_queries, dict):
|
||||
# Check if our keyword exists in the results
|
||||
if keywords in related_queries:
|
||||
keyword_data = related_queries[keywords]
|
||||
|
||||
# Process top queries if available
|
||||
if 'top' in keyword_data and keyword_data['top'] is not None:
|
||||
try:
|
||||
update_progress("Processing top related queries...", progress=75)
|
||||
# Convert to DataFrame if it's not already
|
||||
if isinstance(keyword_data['top'], pd.DataFrame):
|
||||
top_df = keyword_data['top']
|
||||
else:
|
||||
# Try to convert to DataFrame
|
||||
top_df = pd.DataFrame(keyword_data['top'])
|
||||
|
||||
# Ensure it has the right columns
|
||||
if not top_df.empty:
|
||||
# Rename columns if needed
|
||||
if 'query' in top_df.columns:
|
||||
# Already has the right column name
|
||||
pass
|
||||
elif len(top_df.columns) > 0:
|
||||
# Use first column as query
|
||||
top_df = top_df.rename(columns={top_df.columns[0]: 'query'})
|
||||
|
||||
# Add to our results
|
||||
formatted_data['related_queries'] = top_df
|
||||
update_progress(f"Successfully processed {len(top_df)} top related queries", progress=80)
|
||||
except Exception as e:
|
||||
logger.warning(f"Error processing top queries: {e}")
|
||||
update_progress(f"Error processing top queries: {str(e)}", level="warning", progress=80)
|
||||
|
||||
# Process rising queries if available
|
||||
if 'rising' in keyword_data and keyword_data['rising'] is not None:
|
||||
try:
|
||||
update_progress("Processing rising related queries...", progress=85)
|
||||
# Convert to DataFrame if it's not already
|
||||
if isinstance(keyword_data['rising'], pd.DataFrame):
|
||||
rising_df = keyword_data['rising']
|
||||
else:
|
||||
# Try to convert to DataFrame
|
||||
rising_df = pd.DataFrame(keyword_data['rising'])
|
||||
|
||||
# Ensure it has the right columns
|
||||
if not rising_df.empty:
|
||||
# Rename columns if needed
|
||||
if 'query' in rising_df.columns:
|
||||
# Already has the right column name
|
||||
pass
|
||||
elif len(rising_df.columns) > 0:
|
||||
# Use first column as query
|
||||
rising_df = rising_df.rename(columns={rising_df.columns[0]: 'query'})
|
||||
|
||||
# Combine with existing data if we have any
|
||||
if not formatted_data['related_queries'].empty:
|
||||
formatted_data['related_queries'] = pd.concat([formatted_data['related_queries'], rising_df])
|
||||
update_progress(f"Successfully processed {len(rising_df)} rising related queries", progress=90)
|
||||
else:
|
||||
formatted_data['related_queries'] = rising_df
|
||||
update_progress(f"Successfully processed {len(rising_df)} rising related queries", progress=90)
|
||||
except Exception as e:
|
||||
logger.warning(f"Error processing rising queries: {e}")
|
||||
update_progress(f"Error processing rising queries: {str(e)}", level="warning", progress=90)
|
||||
except Exception as e:
|
||||
logger.error(f"Error fetching related queries: {e}")
|
||||
update_progress(f"Error fetching related queries: {str(e)}", level="warning", progress=90)
|
||||
# Ensure we have an empty DataFrame with the right columns
|
||||
formatted_data['related_queries'] = pd.DataFrame(columns=['query', 'value'])
|
||||
|
||||
# Get related topics if missing
|
||||
if formatted_data['related_topics'].empty:
|
||||
try:
|
||||
update_progress("Fetching related topics data...", progress=95)
|
||||
# Get related topics data
|
||||
related_topics = pytrends.related_topics()
|
||||
|
||||
# Create empty DataFrame as fallback
|
||||
formatted_data['related_topics'] = pd.DataFrame(columns=['topic', 'value'])
|
||||
|
||||
# Simple direct approach to avoid list index errors
|
||||
if related_topics and isinstance(related_topics, dict):
|
||||
# Check if our keyword exists in the results
|
||||
if keywords in related_topics:
|
||||
keyword_data = related_topics[keywords]
|
||||
|
||||
# Process top topics if available
|
||||
if 'top' in keyword_data and keyword_data['top'] is not None:
|
||||
try:
|
||||
update_progress("Processing top related topics...", progress=97)
|
||||
# Convert to DataFrame if it's not already
|
||||
if isinstance(keyword_data['top'], pd.DataFrame):
|
||||
top_df = keyword_data['top']
|
||||
else:
|
||||
# Try to convert to DataFrame
|
||||
top_df = pd.DataFrame(keyword_data['top'])
|
||||
|
||||
# Ensure it has the right columns
|
||||
if not top_df.empty:
|
||||
# Rename columns if needed
|
||||
if 'topic_title' in top_df.columns:
|
||||
top_df = top_df.rename(columns={'topic_title': 'topic'})
|
||||
elif len(top_df.columns) > 0 and 'topic' not in top_df.columns:
|
||||
# Use first column as topic
|
||||
top_df = top_df.rename(columns={top_df.columns[0]: 'topic'})
|
||||
|
||||
# Add to our results
|
||||
formatted_data['related_topics'] = top_df
|
||||
update_progress(f"Successfully processed {len(top_df)} top related topics", progress=98)
|
||||
except Exception as e:
|
||||
logger.warning(f"Error processing top topics: {e}")
|
||||
update_progress(f"Error processing top topics: {str(e)}", level="warning", progress=98)
|
||||
|
||||
# Process rising topics if available
|
||||
if 'rising' in keyword_data and keyword_data['rising'] is not None:
|
||||
try:
|
||||
update_progress("Processing rising related topics...", progress=99)
|
||||
# Convert to DataFrame if it's not already
|
||||
if isinstance(keyword_data['rising'], pd.DataFrame):
|
||||
rising_df = keyword_data['rising']
|
||||
else:
|
||||
# Try to convert to DataFrame
|
||||
rising_df = pd.DataFrame(keyword_data['rising'])
|
||||
|
||||
# Ensure it has the right columns
|
||||
if not rising_df.empty:
|
||||
# Rename columns if needed
|
||||
if 'topic_title' in rising_df.columns:
|
||||
rising_df = rising_df.rename(columns={'topic_title': 'topic'})
|
||||
elif len(rising_df.columns) > 0 and 'topic' not in rising_df.columns:
|
||||
# Use first column as topic
|
||||
rising_df = rising_df.rename(columns={rising_df.columns[0]: 'topic'})
|
||||
|
||||
# Combine with existing data if we have any
|
||||
if not formatted_data['related_topics'].empty:
|
||||
formatted_data['related_topics'] = pd.concat([formatted_data['related_topics'], rising_df])
|
||||
update_progress(f"Successfully processed {len(rising_df)} rising related topics", progress=100)
|
||||
else:
|
||||
formatted_data['related_topics'] = rising_df
|
||||
update_progress(f"Successfully processed {len(rising_df)} rising related topics", progress=100)
|
||||
except Exception as e:
|
||||
logger.warning(f"Error processing rising topics: {e}")
|
||||
update_progress(f"Error processing rising topics: {str(e)}", level="warning", progress=100)
|
||||
except Exception as e:
|
||||
logger.error(f"Error fetching related topics: {e}")
|
||||
update_progress(f"Error fetching related topics: {str(e)}", level="warning", progress=100)
|
||||
# Ensure we have an empty DataFrame with the right columns
|
||||
formatted_data['related_topics'] = pd.DataFrame(columns=['topic', 'value'])
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error fetching additional trends data: {e}")
|
||||
update_progress(f"Error fetching additional trends data: {str(e)}", level="warning", progress=100)
|
||||
|
||||
# Ensure all DataFrames have the correct column names for the UI
|
||||
update_progress("Finalizing data formatting...", progress=100)
|
||||
|
||||
if not formatted_data['interest_over_time'].empty:
|
||||
if 'date' not in formatted_data['interest_over_time'].columns:
|
||||
formatted_data['interest_over_time'] = formatted_data['interest_over_time'].reset_index()
|
||||
if 'interest' not in formatted_data['interest_over_time'].columns and keywords in formatted_data['interest_over_time'].columns:
|
||||
formatted_data['interest_over_time'] = formatted_data['interest_over_time'].rename(columns={keywords: 'interest'})
|
||||
|
||||
if not formatted_data['regional_interest'].empty:
|
||||
if 'country_code' not in formatted_data['regional_interest'].columns and 'geoName' in formatted_data['regional_interest'].columns:
|
||||
formatted_data['regional_interest'] = formatted_data['regional_interest'].rename(columns={'geoName': 'country_code'})
|
||||
if 'interest' not in formatted_data['regional_interest'].columns and keywords in formatted_data['regional_interest'].columns:
|
||||
formatted_data['regional_interest'] = formatted_data['regional_interest'].rename(columns={keywords: 'interest'})
|
||||
|
||||
if not formatted_data['related_queries'].empty:
|
||||
# Handle different column names that might be present in the related queries DataFrame
|
||||
if 'query' not in formatted_data['related_queries'].columns:
|
||||
if 'Top query' in formatted_data['related_queries'].columns:
|
||||
formatted_data['related_queries'] = formatted_data['related_queries'].rename(columns={'Top query': 'query'})
|
||||
elif 'Rising query' in formatted_data['related_queries'].columns:
|
||||
formatted_data['related_queries'] = formatted_data['related_queries'].rename(columns={'Rising query': 'query'})
|
||||
elif 'query' not in formatted_data['related_queries'].columns and len(formatted_data['related_queries'].columns) > 0:
|
||||
# If we have a DataFrame but no 'query' column, use the first column as 'query'
|
||||
first_col = formatted_data['related_queries'].columns[0]
|
||||
formatted_data['related_queries'] = formatted_data['related_queries'].rename(columns={first_col: 'query'})
|
||||
|
||||
if 'value' not in formatted_data['related_queries'].columns and len(formatted_data['related_queries'].columns) > 1:
|
||||
# If we have a second column, use it as 'value'
|
||||
second_col = formatted_data['related_queries'].columns[1]
|
||||
formatted_data['related_queries'] = formatted_data['related_queries'].rename(columns={second_col: 'value'})
|
||||
elif 'value' not in formatted_data['related_queries'].columns:
|
||||
# If no 'value' column exists, add one with default values
|
||||
formatted_data['related_queries']['value'] = 0
|
||||
|
||||
if not formatted_data['related_topics'].empty:
|
||||
# Handle different column names that might be present in the related topics DataFrame
|
||||
if 'topic' not in formatted_data['related_topics'].columns:
|
||||
if 'topic_title' in formatted_data['related_topics'].columns:
|
||||
formatted_data['related_topics'] = formatted_data['related_topics'].rename(columns={'topic_title': 'topic'})
|
||||
elif 'topic' not in formatted_data['related_topics'].columns and len(formatted_data['related_topics'].columns) > 0:
|
||||
# If we have a DataFrame but no 'topic' column, use the first column as 'topic'
|
||||
first_col = formatted_data['related_topics'].columns[0]
|
||||
formatted_data['related_topics'] = formatted_data['related_topics'].rename(columns={first_col: 'topic'})
|
||||
|
||||
if 'value' not in formatted_data['related_topics'].columns and len(formatted_data['related_topics'].columns) > 1:
|
||||
# If we have a second column, use it as 'value'
|
||||
second_col = formatted_data['related_topics'].columns[1]
|
||||
formatted_data['related_topics'] = formatted_data['related_topics'].rename(columns={second_col: 'value'})
|
||||
elif 'value' not in formatted_data['related_topics'].columns:
|
||||
# If no 'value' column exists, add one with default values
|
||||
formatted_data['related_topics']['value'] = 0
|
||||
|
||||
# Clear the progress container after completion
|
||||
progress_container.empty()
|
||||
progress_bar.empty()
|
||||
|
||||
return formatted_data
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in Google Trends analysis: {e}")
|
||||
update_progress(f"Error in Google Trends analysis: {str(e)}", level="error", progress=100)
|
||||
# Clear the progress container after error
|
||||
progress_container.empty()
|
||||
progress_bar.empty()
|
||||
return {
|
||||
'related_keywords': [],
|
||||
'interest_over_time': pd.DataFrame(),
|
||||
'regional_interest': pd.DataFrame(),
|
||||
'related_queries': pd.DataFrame(),
|
||||
'related_topics': pd.DataFrame()
|
||||
}
|
||||
|
||||
|
||||
def metaphor_extract_titles_or_text(json_data, return_titles=True):
|
||||
"""
|
||||
Extract either titles or text from the given JSON structure.
|
||||
|
||||
Args:
|
||||
json_data (list): List of Result objects in JSON format.
|
||||
return_titles (bool): If True, return titles. If False, return text.
|
||||
|
||||
Returns:
|
||||
list: List of titles or text.
|
||||
"""
|
||||
if return_titles:
|
||||
return [(result.title) for result in json_data]
|
||||
else:
|
||||
return [result.text for result in json_data]
|
||||
|
||||
|
||||
def extract_info(json_data, info_type):
|
||||
"""
|
||||
Extract information (titles, peopleAlsoAsk, or relatedSearches) from the given JSON.
|
||||
|
||||
Args:
|
||||
json_data (dict): The JSON data.
|
||||
info_type (str): The type of information to extract (titles, peopleAlsoAsk, relatedSearches).
|
||||
|
||||
Returns:
|
||||
list or None: A list containing the requested information, or None if the type is invalid.
|
||||
"""
|
||||
if info_type == "titles":
|
||||
return [result.get("title") for result in json_data.get("organic", [])]
|
||||
elif info_type == "peopleAlsoAsk":
|
||||
return [item.get("question") for item in json_data.get("peopleAlsoAsk", [])]
|
||||
elif info_type == "relatedSearches":
|
||||
return [item.get("query") for item in json_data.get("relatedSearches", [])]
|
||||
else:
|
||||
print("Invalid info_type. Please use 'titles', 'peopleAlsoAsk', or 'relatedSearches'.")
|
||||
return None
|
||||
|
||||
|
||||
def tavily_extract_information(json_data, keyword):
|
||||
"""
|
||||
Extract information from the given JSON based on the specified keyword.
|
||||
|
||||
Args:
|
||||
json_data (dict): The JSON data.
|
||||
keyword (str): The keyword (title, content, answer, follow-query).
|
||||
|
||||
Returns:
|
||||
list or str: The extracted information based on the keyword.
|
||||
"""
|
||||
if keyword == 'titles':
|
||||
return [result['title'] for result in json_data['results']]
|
||||
elif keyword == 'content':
|
||||
return [result['content'] for result in json_data['results']]
|
||||
elif keyword == 'answer':
|
||||
return json_data['answer']
|
||||
elif keyword == 'follow-query':
|
||||
return json_data['follow_up_questions']
|
||||
else:
|
||||
return f"Invalid keyword: {keyword}"
|
||||
@@ -0,0 +1,623 @@
|
||||
import os
|
||||
import sys
|
||||
import pandas as pd
|
||||
from io import StringIO
|
||||
from pathlib import Path
|
||||
|
||||
from metaphor_python import Metaphor
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
import streamlit as st
|
||||
from loguru import logger
|
||||
from tqdm import tqdm
|
||||
from tabulate import tabulate
|
||||
from collections import namedtuple
|
||||
import textwrap
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(Path('../../.env'))
|
||||
|
||||
from exa_py import Exa
|
||||
|
||||
from tenacity import (retry, stop_after_attempt, wait_random_exponential,)# for exponential backoff
|
||||
from .gpt_summarize_web_content import summarize_web_content
|
||||
from .gpt_competitor_analysis import summarize_competitor_content
|
||||
from .common_utils import save_in_file, cfg_search_param
|
||||
|
||||
|
||||
@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
|
||||
def get_metaphor_client():
|
||||
"""
|
||||
Get the Metaphor client.
|
||||
|
||||
Returns:
|
||||
Metaphor: An instance of the Metaphor client.
|
||||
"""
|
||||
METAPHOR_API_KEY = os.environ.get('METAPHOR_API_KEY')
|
||||
if not METAPHOR_API_KEY:
|
||||
logger.error("METAPHOR_API_KEY environment variable not set!")
|
||||
st.error("METAPHOR_API_KEY environment variable not set!")
|
||||
raise ValueError("METAPHOR_API_KEY environment variable not set!")
|
||||
return Exa(METAPHOR_API_KEY)
|
||||
|
||||
|
||||
def metaphor_rag_search():
|
||||
""" Mainly used for researching blog sections. """
|
||||
metaphor = get_metaphor_client()
|
||||
query = "blog research" # Example query, this can be parameterized as needed
|
||||
results = metaphor.search(query)
|
||||
if not results:
|
||||
logger.error("No results found for the query.")
|
||||
st.error("No results found for the query.")
|
||||
return None
|
||||
|
||||
# Process the results (this is a placeholder, actual processing logic will depend on requirements)
|
||||
processed_results = [result['title'] for result in results]
|
||||
|
||||
# Display the results
|
||||
st.write("Search Results:")
|
||||
st.write(processed_results)
|
||||
|
||||
return processed_results
|
||||
|
||||
def metaphor_find_similar(similar_url, usecase, num_results=5, start_published_date=None, end_published_date=None,
|
||||
include_domains=None, exclude_domains=None, include_text=None, exclude_text=None,
|
||||
summary_query=None, progress_bar=None):
|
||||
"""Find similar content using Metaphor API."""
|
||||
|
||||
try:
|
||||
# Initialize progress if not provided
|
||||
if progress_bar is None:
|
||||
progress_bar = st.progress(0.0)
|
||||
|
||||
# Update progress
|
||||
progress_bar.progress(0.1, text="Initializing search...")
|
||||
|
||||
# Get Metaphor client
|
||||
metaphor = get_metaphor_client()
|
||||
logger.info(f"Initialized Metaphor client for URL: {similar_url}")
|
||||
|
||||
# Prepare search parameters
|
||||
search_params = {
|
||||
"highlights": True,
|
||||
"num_results": num_results,
|
||||
}
|
||||
|
||||
# Add optional parameters if provided
|
||||
if start_published_date:
|
||||
search_params["start_published_date"] = start_published_date
|
||||
if end_published_date:
|
||||
search_params["end_published_date"] = end_published_date
|
||||
if include_domains:
|
||||
search_params["include_domains"] = include_domains
|
||||
if exclude_domains:
|
||||
search_params["exclude_domains"] = exclude_domains
|
||||
if include_text:
|
||||
search_params["include_text"] = include_text
|
||||
if exclude_text:
|
||||
search_params["exclude_text"] = exclude_text
|
||||
|
||||
# Add summary query
|
||||
if summary_query:
|
||||
search_params["summary"] = summary_query
|
||||
else:
|
||||
search_params["summary"] = {"query": f"Find {usecase} similar to the given URL."}
|
||||
|
||||
logger.debug(f"Search parameters: {search_params}")
|
||||
|
||||
# Update progress
|
||||
progress_bar.progress(0.2, text="Preparing search parameters...")
|
||||
|
||||
# Make API call
|
||||
logger.info("Calling Metaphor API find_similar_and_contents...")
|
||||
search_response = metaphor.find_similar_and_contents(
|
||||
similar_url,
|
||||
**search_params
|
||||
)
|
||||
|
||||
if search_response and hasattr(search_response, 'results'):
|
||||
competitors = search_response.results
|
||||
total_results = len(competitors)
|
||||
|
||||
# Update progress
|
||||
progress_bar.progress(0.3, text=f"Found {total_results} results...")
|
||||
|
||||
# Process results
|
||||
processed_results = []
|
||||
for i, result in enumerate(competitors):
|
||||
# Calculate progress as decimal (0.0-1.0)
|
||||
progress = 0.3 + (0.6 * (i / total_results))
|
||||
progress_text = f"Processing result {i+1}/{total_results}..."
|
||||
progress_bar.progress(progress, text=progress_text)
|
||||
|
||||
# Process each result
|
||||
processed_result = {
|
||||
"Title": result.title,
|
||||
"URL": result.url,
|
||||
"Content Summary": result.text if hasattr(result, 'text') else "No content available"
|
||||
}
|
||||
processed_results.append(processed_result)
|
||||
|
||||
# Update progress
|
||||
progress_bar.progress(0.9, text="Finalizing results...")
|
||||
|
||||
# Create DataFrame
|
||||
df = pd.DataFrame(processed_results)
|
||||
|
||||
# Update progress
|
||||
progress_bar.progress(1.0, text="Analysis completed!")
|
||||
|
||||
return df, search_response
|
||||
|
||||
else:
|
||||
logger.warning("No results found in search response")
|
||||
progress_bar.progress(1.0, text="No results found")
|
||||
return pd.DataFrame(), search_response
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in metaphor_find_similar: {str(e)}", exc_info=True)
|
||||
if progress_bar:
|
||||
progress_bar.progress(1.0, text="Error occurred during analysis")
|
||||
raise
|
||||
|
||||
|
||||
def calculate_date_range(time_range: str) -> tuple:
|
||||
"""
|
||||
Calculate start and end dates based on time range selection.
|
||||
|
||||
Args:
|
||||
time_range (str): One of 'past_day', 'past_week', 'past_month', 'past_year', 'anytime'
|
||||
|
||||
Returns:
|
||||
tuple: (start_date, end_date) in ISO format with milliseconds
|
||||
"""
|
||||
now = datetime.utcnow()
|
||||
end_date = now.strftime('%Y-%m-%dT%H:%M:%S.999Z')
|
||||
|
||||
if time_range == 'past_day':
|
||||
start_date = (now - timedelta(days=1)).strftime('%Y-%m-%dT%H:%M:%S.000Z')
|
||||
elif time_range == 'past_week':
|
||||
start_date = (now - timedelta(weeks=1)).strftime('%Y-%m-%dT%H:%M:%S.000Z')
|
||||
elif time_range == 'past_month':
|
||||
start_date = (now - timedelta(days=30)).strftime('%Y-%m-%dT%H:%M:%S.000Z')
|
||||
elif time_range == 'past_year':
|
||||
start_date = (now - timedelta(days=365)).strftime('%Y-%m-%dT%H:%M:%S.000Z')
|
||||
else: # anytime
|
||||
start_date = None
|
||||
end_date = None
|
||||
|
||||
return start_date, end_date
|
||||
|
||||
def metaphor_search_articles(query, search_options: dict = None):
|
||||
"""
|
||||
Search for articles using the Metaphor/Exa API.
|
||||
|
||||
Args:
|
||||
query (str): The search query.
|
||||
search_options (dict): Search configuration options including:
|
||||
- num_results (int): Number of results to retrieve
|
||||
- use_autoprompt (bool): Whether to use autoprompt
|
||||
- include_domains (list): List of domains to include
|
||||
- time_range (str): One of 'past_day', 'past_week', 'past_month', 'past_year', 'anytime'
|
||||
- exclude_domains (list): List of domains to exclude
|
||||
|
||||
Returns:
|
||||
dict: Search results and metadata
|
||||
"""
|
||||
exa = get_metaphor_client()
|
||||
try:
|
||||
# Initialize default search options
|
||||
if search_options is None:
|
||||
search_options = {}
|
||||
|
||||
# Get config parameters or use defaults
|
||||
try:
|
||||
include_domains, _, num_results, _ = cfg_search_param('exa')
|
||||
except Exception as cfg_err:
|
||||
logger.warning(f"Failed to load config parameters: {cfg_err}. Using defaults.")
|
||||
include_domains = None
|
||||
num_results = 10
|
||||
|
||||
# Calculate date range based on time_range option
|
||||
time_range = search_options.get('time_range', 'anytime')
|
||||
start_published_date, end_published_date = calculate_date_range(time_range)
|
||||
|
||||
# Prepare search parameters
|
||||
search_params = {
|
||||
'num_results': search_options.get('num_results', num_results),
|
||||
'summary': True, # Always get summaries
|
||||
'include_domains': search_options.get('include_domains', include_domains),
|
||||
'use_autoprompt': search_options.get('use_autoprompt', True),
|
||||
}
|
||||
|
||||
# Add date parameters only if they are not None
|
||||
if start_published_date:
|
||||
search_params['start_published_date'] = start_published_date
|
||||
if end_published_date:
|
||||
search_params['end_published_date'] = end_published_date
|
||||
|
||||
logger.info(f"Exa web search with params: {search_params} and Query: {query}")
|
||||
|
||||
# Execute search
|
||||
search_response = exa.search_and_contents(
|
||||
query,
|
||||
**search_params
|
||||
)
|
||||
|
||||
if not search_response or not hasattr(search_response, 'results'):
|
||||
logger.warning("No results returned from Exa search")
|
||||
return None
|
||||
|
||||
# Get cost information safely
|
||||
try:
|
||||
cost_dollars = {
|
||||
'total': float(search_response.cost_dollars['total']),
|
||||
} if hasattr(search_response, 'cost_dollars') else None
|
||||
except Exception as cost_err:
|
||||
logger.warning(f"Error processing cost information: {cost_err}")
|
||||
cost_dollars = None
|
||||
|
||||
# Format response to match expected structure
|
||||
formatted_response = {
|
||||
"data": {
|
||||
"requestId": getattr(search_response, 'request_id', None),
|
||||
"resolvedSearchType": "neural",
|
||||
"results": [
|
||||
{
|
||||
"id": result.url,
|
||||
"title": result.title,
|
||||
"url": result.url,
|
||||
"publishedDate": result.published_date if hasattr(result, 'published_date') else None,
|
||||
"author": getattr(result, 'author', None),
|
||||
"score": getattr(result, 'score', 0),
|
||||
"summary": result.summary if hasattr(result, 'summary') else None,
|
||||
"text": result.text if hasattr(result, 'text') else None,
|
||||
"image": getattr(result, 'image', None),
|
||||
"favicon": getattr(result, 'favicon', None)
|
||||
}
|
||||
for result in search_response.results
|
||||
],
|
||||
"costDollars": cost_dollars
|
||||
}
|
||||
}
|
||||
|
||||
# Get AI-generated answer from Metaphor
|
||||
try:
|
||||
exa_answer = get_exa_answer(query)
|
||||
if exa_answer:
|
||||
formatted_response.update(exa_answer)
|
||||
except Exception as exa_err:
|
||||
logger.warning(f"Error getting Exa answer: {exa_err}")
|
||||
|
||||
# Get AI-generated answer from Tavily
|
||||
try:
|
||||
# Import the function directly from the module
|
||||
import importlib
|
||||
tavily_module = importlib.import_module('lib.ai_web_researcher.tavily_ai_search')
|
||||
if hasattr(tavily_module, 'do_tavily_ai_search'):
|
||||
tavily_response = tavily_module.do_tavily_ai_search(query)
|
||||
if tavily_response and 'answer' in tavily_response:
|
||||
formatted_response.update({
|
||||
"tavily_answer": tavily_response.get("answer"),
|
||||
"tavily_citations": tavily_response.get("citations", []),
|
||||
"tavily_cost_dollars": tavily_response.get("costDollars", {"total": 0})
|
||||
})
|
||||
else:
|
||||
logger.warning("do_tavily_ai_search function not found in tavily_ai_search module")
|
||||
except Exception as tavily_err:
|
||||
logger.warning(f"Error getting Tavily answer: {tavily_err}")
|
||||
|
||||
# Return the formatted response without displaying it
|
||||
# The display will be handled by gpt_web_researcher
|
||||
return formatted_response
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error in Exa searching articles: {e}")
|
||||
return None
|
||||
|
||||
def streamlit_display_metaphor_results(metaphor_response, search_keywords=None):
|
||||
"""Display Metaphor search results in Streamlit."""
|
||||
|
||||
if not metaphor_response:
|
||||
st.error("No search results found.")
|
||||
return
|
||||
|
||||
# Add debug logging
|
||||
logger.debug(f"Displaying Metaphor results. Type: {type(metaphor_response)}")
|
||||
if isinstance(metaphor_response, dict):
|
||||
logger.debug(f"Metaphor response keys: {metaphor_response.keys()}")
|
||||
|
||||
# Initialize session state variables if they don't exist
|
||||
if 'search_insights' not in st.session_state:
|
||||
st.session_state.search_insights = None
|
||||
if 'metaphor_response' not in st.session_state:
|
||||
st.session_state.metaphor_response = None
|
||||
if 'insights_generated' not in st.session_state:
|
||||
st.session_state.insights_generated = False
|
||||
|
||||
# Store the current response in session state
|
||||
st.session_state.metaphor_response = metaphor_response
|
||||
|
||||
# Display search results
|
||||
st.subheader("🔍 Search Results")
|
||||
|
||||
# Calculate metrics - handle different data structures
|
||||
results = []
|
||||
if isinstance(metaphor_response, dict):
|
||||
if 'data' in metaphor_response and 'results' in metaphor_response['data']:
|
||||
results = metaphor_response['data']['results']
|
||||
elif 'results' in metaphor_response:
|
||||
results = metaphor_response['results']
|
||||
|
||||
total_results = len(results)
|
||||
avg_relevance = sum(r.get('score', 0) for r in results) / total_results if total_results > 0 else 0
|
||||
|
||||
# Display metrics
|
||||
col1, col2 = st.columns(2)
|
||||
with col1:
|
||||
st.metric("Total Results", total_results)
|
||||
with col2:
|
||||
st.metric("Average Relevance Score", f"{avg_relevance:.2f}")
|
||||
|
||||
# Display AI-generated answers if available
|
||||
if 'tavily_answer' in metaphor_response or 'metaphor_answer' in metaphor_response:
|
||||
st.subheader("🤖 AI-Generated Answers")
|
||||
|
||||
if 'tavily_answer' in metaphor_response:
|
||||
st.markdown("**Tavily AI Answer:**")
|
||||
st.write(metaphor_response['tavily_answer'])
|
||||
|
||||
if 'metaphor_answer' in metaphor_response:
|
||||
st.markdown("**Metaphor AI Answer:**")
|
||||
st.write(metaphor_response['metaphor_answer'])
|
||||
|
||||
# Get Search Insights button
|
||||
if st.button("Generate Search Insights", key="metaphor_generate_insights_button"):
|
||||
st.session_state.insights_generated = True
|
||||
st.rerun()
|
||||
|
||||
# Display insights if they exist in session state
|
||||
if st.session_state.search_insights:
|
||||
st.subheader("🔍 Search Insights")
|
||||
st.write(st.session_state.search_insights)
|
||||
|
||||
# Display search results in a data editor
|
||||
st.subheader("📊 Detailed Results")
|
||||
|
||||
# Prepare data for display
|
||||
results_data = []
|
||||
for result in results:
|
||||
result_data = {
|
||||
'Title': result.get('title', ''),
|
||||
'URL': result.get('url', ''),
|
||||
'Snippet': result.get('summary', ''),
|
||||
'Relevance Score': result.get('score', 0),
|
||||
'Published Date': result.get('publishedDate', '')
|
||||
}
|
||||
results_data.append(result_data)
|
||||
|
||||
# Create DataFrame
|
||||
df = pd.DataFrame(results_data)
|
||||
|
||||
# Display the DataFrame if it's not empty
|
||||
if not df.empty:
|
||||
# Configure columns
|
||||
st.dataframe(
|
||||
df,
|
||||
column_config={
|
||||
"Title": st.column_config.TextColumn(
|
||||
"Title",
|
||||
help="Title of the search result",
|
||||
width="large",
|
||||
),
|
||||
"URL": st.column_config.LinkColumn(
|
||||
"URL",
|
||||
help="Link to the search result",
|
||||
width="medium",
|
||||
display_text="Visit Article",
|
||||
),
|
||||
"Snippet": st.column_config.TextColumn(
|
||||
"Snippet",
|
||||
help="Summary of the search result",
|
||||
width="large",
|
||||
),
|
||||
"Relevance Score": st.column_config.NumberColumn(
|
||||
"Relevance Score",
|
||||
help="Relevance score of the search result",
|
||||
format="%.2f",
|
||||
width="small",
|
||||
),
|
||||
"Published Date": st.column_config.DateColumn(
|
||||
"Published Date",
|
||||
help="Publication date of the search result",
|
||||
width="medium",
|
||||
),
|
||||
},
|
||||
hide_index=True,
|
||||
)
|
||||
|
||||
# Add popover for snippets
|
||||
st.markdown("""
|
||||
<style>
|
||||
.snippet-popover {
|
||||
position: relative;
|
||||
display: inline-block;
|
||||
}
|
||||
.snippet-popover .snippet-content {
|
||||
visibility: hidden;
|
||||
width: 300px;
|
||||
background-color: #f9f9f9;
|
||||
color: #333;
|
||||
text-align: left;
|
||||
border-radius: 6px;
|
||||
padding: 10px;
|
||||
position: absolute;
|
||||
z-index: 1;
|
||||
bottom: 125%;
|
||||
left: 50%;
|
||||
margin-left: -150px;
|
||||
opacity: 0;
|
||||
transition: opacity 0.3s;
|
||||
box-shadow: 0 2px 5px rgba(0,0,0,0.2);
|
||||
}
|
||||
.snippet-popover:hover .snippet-content {
|
||||
visibility: visible;
|
||||
opacity: 1;
|
||||
}
|
||||
</style>
|
||||
""", unsafe_allow_html=True)
|
||||
|
||||
# Display snippets with popover
|
||||
st.subheader("📝 Snippets")
|
||||
for i, result in enumerate(results):
|
||||
snippet = result.get('summary', '')
|
||||
if snippet:
|
||||
st.markdown(f"""
|
||||
<div class="snippet-popover">
|
||||
<strong>{result.get('title', '')}</strong>
|
||||
<div class="snippet-content">
|
||||
{snippet}
|
||||
</div>
|
||||
</div>
|
||||
""", unsafe_allow_html=True)
|
||||
else:
|
||||
st.info("No detailed results available.")
|
||||
|
||||
# Add a collapsible section for the raw JSON data
|
||||
with st.expander("Research Results (JSON)", expanded=False):
|
||||
st.json(metaphor_response)
|
||||
|
||||
|
||||
def metaphor_news_summarizer(news_keywords):
|
||||
""" build a LLM-based news summarizer app with the Exa API to keep us up-to-date
|
||||
with the latest news on a given topic.
|
||||
"""
|
||||
exa = get_metaphor_client()
|
||||
|
||||
# FIXME: Needs to be user defined.
|
||||
one_week_ago = (datetime.now() - timedelta(days=7))
|
||||
date_cutoff = one_week_ago.strftime("%Y-%m-%d")
|
||||
|
||||
search_response = exa.search_and_contents(
|
||||
news_keywords, use_autoprompt=True, start_published_date=date_cutoff
|
||||
)
|
||||
|
||||
urls = [result.url for result in search_response.results]
|
||||
print("URLs:")
|
||||
for url in urls:
|
||||
print(url)
|
||||
|
||||
|
||||
def print_search_result(contents_response):
|
||||
# Define the Result namedtuple
|
||||
Result = namedtuple("Result", ["url", "title", "text"])
|
||||
# Tabulate the data
|
||||
table_headers = ["URL", "Title", "Summary"]
|
||||
table_data = [(result.url, result.title, result.text) for result in contents_response]
|
||||
|
||||
table = tabulate(table_data,
|
||||
headers=table_headers,
|
||||
tablefmt="fancy_grid",
|
||||
colalign=["left", "left", "left"],
|
||||
maxcolwidths=[20, 20, 70])
|
||||
|
||||
# Convert table_data to DataFrame
|
||||
import pandas as pd
|
||||
df = pd.DataFrame(table_data, columns=["URL", "Title", "Summary"])
|
||||
import streamlit as st
|
||||
st.table(df)
|
||||
print(table)
|
||||
# Save the combined table to a file
|
||||
try:
|
||||
save_in_file(table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"Failed to save search results: {save_results_err}")
|
||||
|
||||
|
||||
def metaphor_scholar_search(query, include_domains=None, time_range="anytime"):
|
||||
"""
|
||||
Search for papers using the Metaphor API.
|
||||
|
||||
Args:
|
||||
query (str): The search query.
|
||||
include_domains (list): List of domains to include.
|
||||
time_range (str): Time range for published articles ("day", "week", "month", "year", "anytime").
|
||||
|
||||
Returns:
|
||||
MetaphorResponse: The response from the Metaphor API.
|
||||
"""
|
||||
client = get_metaphor_client()
|
||||
try:
|
||||
if time_range == "day":
|
||||
start_published_date = (datetime.utcnow() - timedelta(days=1)).strftime('%Y-%m-%dT%H:%M:%SZ')
|
||||
elif time_range == "week":
|
||||
start_published_date = (datetime.utcnow() - timedelta(weeks=1)).strftime('%Y-%m-%dT%H:%M:%SZ')
|
||||
elif time_range == "month":
|
||||
start_published_date = (datetime.utcnow() - timedelta(weeks=4)).strftime('%Y-%m-%dT%H:%M:%SZ')
|
||||
elif time_range == "year":
|
||||
start_published_date = (datetime.utcnow() - timedelta(days=365)).strftime('%Y-%m-%dT%H:%M:%SZ')
|
||||
else:
|
||||
start_published_date = None
|
||||
|
||||
response = client.search(query, include_domains=include_domains, start_published_date=start_published_date, use_autoprompt=True)
|
||||
return response
|
||||
except Exception as e:
|
||||
logger.error(f"Error in searching papers: {e}")
|
||||
|
||||
def get_exa_answer(query: str, system_prompt: str = None) -> dict:
|
||||
"""
|
||||
Get an AI-generated answer for a query using Exa's answer endpoint.
|
||||
|
||||
Args:
|
||||
query (str): The search query to get an answer for
|
||||
system_prompt (str, optional): Custom system prompt for the LLM. If None, uses default prompt.
|
||||
|
||||
Returns:
|
||||
dict: Response containing answer, citations, and cost information
|
||||
{
|
||||
"answer": str,
|
||||
"citations": list[dict],
|
||||
"costDollars": dict
|
||||
}
|
||||
"""
|
||||
exa = get_metaphor_client()
|
||||
try:
|
||||
# Use default system prompt if none provided
|
||||
if system_prompt is None:
|
||||
system_prompt = (
|
||||
"I am doing research to write factual content. "
|
||||
"Help me find answers for content generation task. "
|
||||
"Provide detailed, well-structured answers with clear citations."
|
||||
)
|
||||
|
||||
logger.info(f"Getting Exa answer for query: {query}")
|
||||
logger.debug(f"Using system prompt: {system_prompt}")
|
||||
|
||||
# Make API call to get answer with system_prompt parameter
|
||||
result = exa.answer(
|
||||
query,
|
||||
model="exa",
|
||||
text=True # Include full text in citations
|
||||
)
|
||||
|
||||
if not result or not result.get('answer'):
|
||||
logger.warning("No answer received from Exa")
|
||||
return None
|
||||
|
||||
# Format response to match expected structure
|
||||
response = {
|
||||
"answer": result.get('answer'),
|
||||
"citations": result.get('citations', []),
|
||||
"costDollars": result.get('costDollars', {"total": 0})
|
||||
}
|
||||
|
||||
return response
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting Exa answer: {e}")
|
||||
return None
|
||||
218
ToBeMigrated/ai_web_researcher/tavily_ai_search.py
Normal file
218
ToBeMigrated/ai_web_researcher/tavily_ai_search.py
Normal file
@@ -0,0 +1,218 @@
|
||||
"""
|
||||
This Python script uses the Tavily AI service to perform advanced searches based on specified keywords and options. It retrieves Tavily AI search results, pretty-prints them using Rich and Tabulate, and provides additional information such as the answer to the search query and follow-up questions.
|
||||
|
||||
Features:
|
||||
- Utilizes the Tavily AI service for advanced searches.
|
||||
- Retrieves API keys from the environment variables loaded from a .env file.
|
||||
- Configures logging with Loguru for informative messages.
|
||||
- Implements a retry mechanism using Tenacity to handle transient failures during Tavily searches.
|
||||
- Displays search results, including titles, snippets, and links, in a visually appealing table using Tabulate and Rich.
|
||||
|
||||
Usage:
|
||||
- Ensure the necessary API keys are set in the .env file.
|
||||
- Run the script to perform a Tavily AI search with specified keywords and options.
|
||||
- The search results, including titles, snippets, and links, are displayed in a formatted table.
|
||||
- Additional information, such as the answer to the search query and follow-up questions, is presented in separate tables.
|
||||
|
||||
Modifications:
|
||||
- To modify the script, update the environment variables in the .env file with the required API keys.
|
||||
- Adjust the search parameters, such as keywords and search depth, in the `do_tavily_ai_search` function as needed.
|
||||
- Customize logging configurations and table formatting according to preferences.
|
||||
|
||||
To-Do (TBD):
|
||||
- Consider adding further enhancements or customization based on specific use cases.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sys
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from tavily import TavilyClient
|
||||
from rich import print
|
||||
from tabulate import tabulate
|
||||
# Load environment variables from .env file
|
||||
load_dotenv(Path('../../.env'))
|
||||
from rich import print
|
||||
import streamlit as st
|
||||
# Configure logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
from .common_utils import save_in_file, cfg_search_param
|
||||
from tenacity import retry, stop_after_attempt, wait_random_exponential
|
||||
|
||||
|
||||
@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
|
||||
def do_tavily_ai_search(keywords, max_results=5, include_domains=None, search_depth="advanced", **kwargs):
|
||||
"""
|
||||
Get Tavily AI search results based on specified keywords and options.
|
||||
"""
|
||||
# Run Tavily search
|
||||
logger.info(f"Running Tavily search on: {keywords}")
|
||||
|
||||
# Retrieve API keys
|
||||
api_key = os.getenv('TAVILY_API_KEY')
|
||||
if not api_key:
|
||||
raise ValueError("API keys for Tavily is Not set.")
|
||||
|
||||
# Initialize Tavily client
|
||||
try:
|
||||
client = TavilyClient(api_key=api_key)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to create Tavily client. Check TAVILY_API_KEY: {err}")
|
||||
raise
|
||||
|
||||
try:
|
||||
# Create search parameters exactly matching Tavily's API format
|
||||
tavily_search_result = client.search(
|
||||
query=keywords,
|
||||
search_depth="advanced",
|
||||
time_range="year",
|
||||
include_answer="advanced",
|
||||
include_domains=[""] if not include_domains else include_domains,
|
||||
max_results=max_results
|
||||
)
|
||||
|
||||
if tavily_search_result:
|
||||
print_result_table(tavily_search_result)
|
||||
streamlit_display_results(tavily_search_result)
|
||||
return tavily_search_result
|
||||
return None
|
||||
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to do Tavily Research: {err}")
|
||||
raise
|
||||
|
||||
|
||||
def streamlit_display_results(output_data):
|
||||
"""Display Tavily AI search results in Streamlit UI with enhanced visualization."""
|
||||
|
||||
# Display the 'answer' in Streamlit with enhanced styling
|
||||
answer = output_data.get("answer", "No answer available")
|
||||
st.markdown("### 🤖 AI-Generated Answer")
|
||||
st.markdown(f"""
|
||||
<div style="background-color: #f0f2f6; padding: 20px; border-radius: 10px; border-left: 5px solid #4CAF50;">
|
||||
{answer}
|
||||
</div>
|
||||
""", unsafe_allow_html=True)
|
||||
|
||||
# Display follow-up questions if available
|
||||
follow_up_questions = output_data.get("follow_up_questions", [])
|
||||
if follow_up_questions:
|
||||
st.markdown("### ❓ Follow-up Questions")
|
||||
for i, question in enumerate(follow_up_questions, 1):
|
||||
st.markdown(f"**{i}.** {question}")
|
||||
|
||||
# Prepare data for display with dataeditor
|
||||
st.markdown("### 📊 Search Results")
|
||||
|
||||
# Create a DataFrame for the results
|
||||
import pandas as pd
|
||||
results_data = []
|
||||
|
||||
for item in output_data.get("results", []):
|
||||
title = item.get("title", "")
|
||||
snippet = item.get("content", "")
|
||||
link = item.get("url", "")
|
||||
results_data.append({
|
||||
"Title": title,
|
||||
"Content": snippet,
|
||||
"Link": link
|
||||
})
|
||||
|
||||
if results_data:
|
||||
df = pd.DataFrame(results_data)
|
||||
|
||||
# Display the data editor
|
||||
st.data_editor(
|
||||
df,
|
||||
column_config={
|
||||
"Title": st.column_config.TextColumn(
|
||||
"Title",
|
||||
help="Article title",
|
||||
width="medium",
|
||||
),
|
||||
"Content": st.column_config.TextColumn(
|
||||
"Content",
|
||||
help="Click the button below to view full content",
|
||||
width="large",
|
||||
),
|
||||
"Link": st.column_config.LinkColumn(
|
||||
"Link",
|
||||
help="Click to visit the website",
|
||||
width="small",
|
||||
display_text="Visit Site"
|
||||
),
|
||||
},
|
||||
hide_index=True,
|
||||
use_container_width=True,
|
||||
)
|
||||
|
||||
# Add popovers for full content display
|
||||
for item in output_data.get("results", []):
|
||||
with st.popover(f"View content: {item.get('title', '')[:50]}..."):
|
||||
st.markdown(item.get("content", ""))
|
||||
else:
|
||||
st.info("No results found for your search query.")
|
||||
|
||||
|
||||
def print_result_table(output_data):
|
||||
""" Pretty print the tavily AI search result. """
|
||||
# Prepare data for tabulate
|
||||
table_data = []
|
||||
for item in output_data.get("results"):
|
||||
title = item.get("title", "")
|
||||
snippet = item.get("content", "")
|
||||
link = item.get("url", "")
|
||||
table_data.append([title, snippet, link])
|
||||
|
||||
# Define table headers
|
||||
table_headers = ["Title", "Snippet", "Link"]
|
||||
# Display the table using tabulate
|
||||
table = tabulate(table_data,
|
||||
headers=table_headers,
|
||||
tablefmt="fancy_grid",
|
||||
colalign=["left", "left", "left"],
|
||||
maxcolwidths=[30, 60, 30])
|
||||
# Print the table
|
||||
print(table)
|
||||
|
||||
# Save the combined table to a file
|
||||
try:
|
||||
save_in_file(table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"Failed to save search results: {save_results_err}")
|
||||
|
||||
# Display the 'answer' in a table
|
||||
table_headers = [f"The answer to search query: {output_data.get('query')}"]
|
||||
table_data = [[output_data.get("answer")]]
|
||||
table = tabulate(table_data,
|
||||
headers=table_headers,
|
||||
tablefmt="fancy_grid",
|
||||
maxcolwidths=[80])
|
||||
print(table)
|
||||
# Save the combined table to a file
|
||||
try:
|
||||
save_in_file(table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"Failed to save search results: {save_results_err}")
|
||||
|
||||
# Display the 'follow_up_questions' in a table
|
||||
if output_data.get("follow_up_questions"):
|
||||
table_headers = [f"Search Engine follow up questions for query: {output_data.get('query')}"]
|
||||
table_data = [[output_data.get("follow_up_questions")]]
|
||||
table = tabulate(table_data,
|
||||
headers=table_headers,
|
||||
tablefmt="fancy_grid",
|
||||
maxcolwidths=[80])
|
||||
print(table)
|
||||
try:
|
||||
save_in_file(table)
|
||||
except Exception as save_results_err:
|
||||
logger.error(f"Failed to save search results: {save_results_err}")
|
||||
184
ToBeMigrated/ai_writers/ai_essay_writer.py
Normal file
184
ToBeMigrated/ai_writers/ai_essay_writer.py
Normal file
@@ -0,0 +1,184 @@
|
||||
#####################################################
|
||||
#
|
||||
# Alwrity, AI essay writer - Essay_Writing_with_Prompt_Chaining
|
||||
#
|
||||
#####################################################
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
from dotenv import load_dotenv
|
||||
from pprint import pprint
|
||||
from loguru import logger
|
||||
import sys
|
||||
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
def generate_with_retry(prompt, system_prompt=None):
|
||||
"""
|
||||
Generates content using the llm_text_gen function with retry handling for errors.
|
||||
|
||||
Parameters:
|
||||
prompt (str): The prompt to generate content from.
|
||||
system_prompt (str, optional): Custom system prompt to use instead of the default one.
|
||||
|
||||
Returns:
|
||||
str: The generated content.
|
||||
"""
|
||||
try:
|
||||
# Use llm_text_gen instead of directly calling the model
|
||||
return llm_text_gen(prompt, system_prompt)
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating content: {e}")
|
||||
return ""
|
||||
|
||||
|
||||
def ai_essay_generator(essay_title, selected_essay_type, selected_education_level, selected_num_pages):
|
||||
"""
|
||||
Write an Essay using prompt chaining and iterative generation.
|
||||
|
||||
Parameters:
|
||||
essay_title (str): The title or topic of the essay.
|
||||
selected_essay_type (str): The type of essay to write.
|
||||
selected_education_level (str): The education level of the target audience.
|
||||
selected_num_pages (int): The number of pages or words for the essay.
|
||||
"""
|
||||
logger.info(f"Starting to write Essay on {essay_title}..")
|
||||
try:
|
||||
# Define persona and writing guidelines
|
||||
guidelines = f'''\
|
||||
Writing Guidelines
|
||||
|
||||
As an expert Essay writer and academic researcher, demostrate your world class essay writing skills.
|
||||
|
||||
Follow the below writing guidelines for writing your essay:
|
||||
1). You specialize in {selected_essay_type} essay writing.
|
||||
2). Your target audiences include readers from {selected_education_level} level.
|
||||
3). The title of the essay is {essay_title}.
|
||||
5). The final essay should of {selected_num_pages} words/pages.
|
||||
3). Plant the seeds of subplots or potential character arc shifts that can be expanded later.
|
||||
|
||||
Remember, your main goal is to write as much as you can. If you get through
|
||||
the story too fast, that is bad. Expand, never summarize.
|
||||
'''
|
||||
# Generate prompts
|
||||
premise_prompt = f'''\
|
||||
As an expert essay writer, specilizing in {selected_essay_type} essay writing.
|
||||
|
||||
Write an Essay title for given keywords {essay_title}.
|
||||
The title should appeal to audience level of {selected_education_level}.
|
||||
'''
|
||||
|
||||
outline_prompt = f'''\
|
||||
As an expert essay writer, specilizing in {selected_essay_type} essay writing.
|
||||
|
||||
Your Essay title is:
|
||||
|
||||
{{premise}}
|
||||
|
||||
Write an outline for the essay.
|
||||
'''
|
||||
|
||||
starting_prompt = f'''\
|
||||
As an expert essay writer, specilizing in {selected_essay_type} essay writing.
|
||||
|
||||
Your essay title is:
|
||||
|
||||
{{premise}}
|
||||
|
||||
The outline of the Essay is:
|
||||
|
||||
{{outline}}
|
||||
|
||||
First, silently review the outline and the essay title. Consider how to start the Essay.
|
||||
Start to write the very beginning of the Essay. You are not expected to finish
|
||||
the whole Essay now. Your writing should be detailed enough that you are only
|
||||
scratching the surface of the first bullet of your outline. Try to write AT
|
||||
MINIMUM 1000 WORDS.
|
||||
|
||||
{guidelines}
|
||||
'''
|
||||
|
||||
continuation_prompt = f'''\
|
||||
As an expert essay writer, specilizing in {selected_essay_type} essay writing.
|
||||
|
||||
Your essay title is:
|
||||
|
||||
{{premise}}
|
||||
|
||||
The outline of the Essay is:
|
||||
|
||||
{{outline}}
|
||||
|
||||
You've begun to write the essay and continue to do so.
|
||||
Here's what you've written so far:
|
||||
|
||||
{{story_text}}
|
||||
|
||||
=====
|
||||
|
||||
First, silently review the outline and essay so far.
|
||||
Identify what the single next part of your outline you should write.
|
||||
|
||||
Your task is to continue where you left off and write the next part of the Essay.
|
||||
You are not expected to finish the whole essay now. Your writing should be
|
||||
detailed enough that you are only scratching the surface of the next part of
|
||||
your outline. Try to write AT MINIMUM 1000 WORDS. However, only once the essay
|
||||
is COMPLETELY finished, write IAMDONE. Remember, do NOT write a whole chapter
|
||||
right now.
|
||||
|
||||
{guidelines}
|
||||
'''
|
||||
|
||||
# Generate prompts
|
||||
try:
|
||||
premise = generate_with_retry(premise_prompt)
|
||||
logger.info(f"The title of the Essay is: {premise}")
|
||||
except Exception as err:
|
||||
logger.error(f"Essay title Generation Error: {err}")
|
||||
return
|
||||
|
||||
outline = generate_with_retry(outline_prompt.format(premise=premise))
|
||||
logger.info(f"The Outline of the essay is: {outline}\n\n")
|
||||
if not outline:
|
||||
logger.error("Failed to generate Essay outline. Exiting...")
|
||||
return
|
||||
|
||||
try:
|
||||
starting_draft = generate_with_retry(
|
||||
starting_prompt.format(premise=premise, outline=outline))
|
||||
pprint(starting_draft)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to Generate Essay draft: {err}")
|
||||
return
|
||||
|
||||
try:
|
||||
draft = starting_draft
|
||||
continuation = generate_with_retry(
|
||||
continuation_prompt.format(premise=premise, outline=outline, story_text=draft))
|
||||
pprint(continuation)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to write the initial draft: {err}")
|
||||
|
||||
# Add the continuation to the initial draft, keep building the story until we see 'IAMDONE'
|
||||
try:
|
||||
draft += '\n\n' + continuation
|
||||
except Exception as err:
|
||||
logger.error(f"Failed as: {err} and {continuation}")
|
||||
while 'IAMDONE' not in continuation:
|
||||
try:
|
||||
continuation = generate_with_retry(
|
||||
continuation_prompt.format(premise=premise, outline=outline, story_text=draft))
|
||||
draft += '\n\n' + continuation
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to continually write the Essay: {err}")
|
||||
return
|
||||
|
||||
# Remove 'IAMDONE' and print the final story
|
||||
final = draft.replace('IAMDONE', '').strip()
|
||||
pprint(final)
|
||||
return final
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Main Essay writing: An error occurred: {e}")
|
||||
return ""
|
||||
102
ToBeMigrated/ai_writers/ai_news_article_writer.py
Normal file
102
ToBeMigrated/ai_writers/ai_news_article_writer.py
Normal file
@@ -0,0 +1,102 @@
|
||||
######################################################
|
||||
#
|
||||
# Alwrity, as an AI news writer, will have to be factually correct.
|
||||
# We will do multiple rounds of web research and cite our sources.
|
||||
# 'include_urls' will focus news articles only from well known sources.
|
||||
# Choosing a country will help us get better results.
|
||||
#
|
||||
######################################################
|
||||
|
||||
import sys
|
||||
import os
|
||||
import json
|
||||
from textwrap import dedent
|
||||
from pathlib import Path
|
||||
from datetime import datetime
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(Path('../../.env'))
|
||||
from loguru import logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
from ..ai_web_researcher.google_serp_search import perform_serper_news_search
|
||||
|
||||
|
||||
def ai_news_generation(news_keywords, news_country, news_language):
|
||||
""" Generate news aritcle based on given keywords. """
|
||||
# Use to store the blog in a string, to save in a *.md file.
|
||||
blog_markdown_str = ""
|
||||
|
||||
logger.info(f"Researching and Writing News Article on keywords: {news_keywords}")
|
||||
# Call on the got-researcher, tavily apis for this. Do google search for organic competition.
|
||||
try:
|
||||
google_news_result = perform_serper_news_search(news_keywords, news_country, news_language)
|
||||
blog_markdown_str = write_news_google_search(news_keywords, news_country, news_language, google_news_result)
|
||||
#print(blog_markdown_str)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed in Google News web research: {err}")
|
||||
logger.info("\n######### Draft1: Finished News article from Google web search: ###########\n\n")
|
||||
return blog_markdown_str
|
||||
|
||||
|
||||
def write_news_google_search(news_keywords, news_country, news_language, search_results):
|
||||
"""Combine the given online research and gpt blog content"""
|
||||
news_language = get_language_name(news_language)
|
||||
news_country = get_country_name(news_country)
|
||||
|
||||
prompt = f"""
|
||||
As an experienced {news_language} news journalist and editor,
|
||||
I will provide you with my 'News keywords' and its 'google search results'.
|
||||
Your goal is to write a News report, backed by given google search results.
|
||||
Important, as a news report, its imperative that your content is factually correct and cited.
|
||||
|
||||
Follow below guidelines:
|
||||
1). Understand and utilize the provided google search result json.
|
||||
2). Always provide in-line citations and provide referance links.
|
||||
3). Understand the given news item and adapt your tone accordingly.
|
||||
4). Always include the dates when then news was reported.
|
||||
6). Do not explain, describe your response.
|
||||
7). Your blog should be highly formatted in markdown style and highly readable.
|
||||
8). Important: Please read the entire prompt before writing anything. Follow the prompt exactly as I instructed.
|
||||
|
||||
\n\nNews Keywords: "{news_keywords}"\n\n
|
||||
Google search Result: "{search_results}"
|
||||
"""
|
||||
logger.info("Generating blog and FAQs from Google web search results.")
|
||||
try:
|
||||
response = llm_text_gen(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
logger.error(f"Exit: Failed to get response from LLM: {err}")
|
||||
exit(1)
|
||||
|
||||
|
||||
def get_language_name(language_code):
|
||||
languages = {
|
||||
"es": "Spanish",
|
||||
"vn": "Vietnamese",
|
||||
"en": "English",
|
||||
"ar": "Arabic",
|
||||
"hi": "Hindi",
|
||||
"de": "German",
|
||||
"zh-cn": "Chinese (Simplified)"
|
||||
# Add more language codes and corresponding names as needed
|
||||
}
|
||||
return languages.get(language_code, "Unknown")
|
||||
|
||||
def get_country_name(country_code):
|
||||
countries = {
|
||||
"es": "Spain",
|
||||
"vn": "Vietnam",
|
||||
"pk": "Pakistan",
|
||||
"in": "India",
|
||||
"de": "Germany",
|
||||
"cn": "China"
|
||||
# Add more country codes and corresponding names as needed
|
||||
}
|
||||
return countries.get(country_code, "Unknown")
|
||||
115
ToBeMigrated/ai_writers/ai_product_description_writer.py
Normal file
115
ToBeMigrated/ai_writers/ai_product_description_writer.py
Normal file
@@ -0,0 +1,115 @@
|
||||
import streamlit as st
|
||||
import json
|
||||
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
def generate_product_description(title, details, audience, tone, length, keywords):
|
||||
"""
|
||||
Generates a product description using OpenAI's API.
|
||||
|
||||
Args:
|
||||
title (str): The title of the product.
|
||||
details (list): A list of product details (features, benefits, etc.).
|
||||
audience (list): A list of target audience segments.
|
||||
tone (str): The desired tone of the description (e.g., "Formal", "Informal").
|
||||
length (str): The desired length of the description (e.g., "short", "medium", "long").
|
||||
keywords (str): Keywords related to the product (comma-separated).
|
||||
|
||||
Returns:
|
||||
str: The generated product description.
|
||||
"""
|
||||
prompt = f"""
|
||||
Write a compelling product description for {title}.
|
||||
|
||||
Highlight these key features: {', '.join(details)}
|
||||
|
||||
Emphasize the benefits of these features for the target audience ({audience}).
|
||||
Maintain a {tone} tone and aim for a length of approximately {length} words.
|
||||
|
||||
Use these keywords naturally throughout the description: {', '.join(keywords)}.
|
||||
|
||||
Remember to be persuasive and focus on the value proposition.
|
||||
"""
|
||||
|
||||
try:
|
||||
response = llm_text_gen(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
logger.error(f"Exit: Failed to get response from LLM: {err}")
|
||||
exit(1)
|
||||
|
||||
|
||||
def display_inputs():
|
||||
st.title("📝 AI Product Description Writer 🚀")
|
||||
st.markdown("**Generate compelling and accurate product descriptions with AI.**")
|
||||
|
||||
col1, col2 = st.columns(2)
|
||||
|
||||
with col1:
|
||||
product_title = st.text_input("🏷️ **Product Title**", placeholder="Enter the product title (e.g., Wireless Bluetooth Headphones)")
|
||||
with col2:
|
||||
product_details = st.text_area("📄 **Product Details**", placeholder="Enter features, benefits, specifications, materials, etc. (e.g., Noise Cancellation, Long Battery Life, Water Resistant, Comfortable Design)")
|
||||
|
||||
col3, col4 = st.columns(2)
|
||||
|
||||
with col3:
|
||||
keywords = st.text_input("🔑 **Keywords**", placeholder="Enter keywords, comma-separated (e.g., wireless headphones, noise cancelling, Bluetooth 5.0)")
|
||||
with col4:
|
||||
target_audience = st.multiselect(
|
||||
"🎯 **Target Audience**",
|
||||
["Teens", "Adults", "Seniors", "Music Lovers", "Fitness Enthusiasts", "Tech Savvy", "Busy Professionals", "Travelers", "Casual Users"],
|
||||
placeholder="Select target audience (optional)"
|
||||
)
|
||||
|
||||
col5, col6 = st.columns(2)
|
||||
|
||||
with col5:
|
||||
description_length = st.selectbox(
|
||||
"📏 **Desired Description Length**",
|
||||
["Short (1-2 sentences)", "Medium (3-5 sentences)", "Long (6+ sentences)"],
|
||||
help="Select the desired length of the product description"
|
||||
)
|
||||
with col6:
|
||||
brand_tone = st.selectbox(
|
||||
"🎨 **Brand Tone**",
|
||||
["Formal", "Informal", "Fun & Energetic"],
|
||||
help="Select the desired tone for the description"
|
||||
)
|
||||
|
||||
return product_title, product_details, target_audience, brand_tone, description_length, keywords
|
||||
|
||||
|
||||
def display_output(description):
|
||||
if description:
|
||||
st.subheader("✨ Generated Product Description:")
|
||||
st.write(description)
|
||||
|
||||
json_ld = {
|
||||
"@context": "https://schema.org",
|
||||
"@type": "Product",
|
||||
"name": product_title,
|
||||
"description": description,
|
||||
"audience": target_audience,
|
||||
"brand": {
|
||||
"@type": "Brand",
|
||||
"name": "Your Brand Name"
|
||||
},
|
||||
"keywords": keywords.split(", ")
|
||||
}
|
||||
|
||||
|
||||
def write_ai_prod_desc():
|
||||
product_title, product_details, target_audience, brand_tone, description_length, keywords = display_inputs()
|
||||
|
||||
if st.button("Generate Product Description 🚀"):
|
||||
with st.spinner("Generating description..."):
|
||||
description = generate_product_description(
|
||||
product_title,
|
||||
product_details.split(", "), # Split details into a list
|
||||
target_audience,
|
||||
brand_tone,
|
||||
description_length.split(" ")[0].lower(), # Extract length from selectbox
|
||||
keywords
|
||||
)
|
||||
display_output(description)
|
||||
220
ToBeMigrated/ai_writers/ai_writer_dashboard.py
Normal file
220
ToBeMigrated/ai_writers/ai_writer_dashboard.py
Normal file
@@ -0,0 +1,220 @@
|
||||
import streamlit as st
|
||||
from lib.utils.alwrity_utils import (essay_writer, ai_news_writer, ai_finance_ta_writer)
|
||||
|
||||
from lib.ai_writers.ai_story_writer.story_writer import story_input_section
|
||||
from lib.ai_writers.ai_product_description_writer import write_ai_prod_desc
|
||||
from lib.ai_writers.ai_copywriter.copywriter_dashboard import copywriter_dashboard
|
||||
from lib.ai_writers.linkedin_writer import LinkedInAIWriter
|
||||
from lib.ai_writers.blog_rewriter_updater.ai_blog_rewriter import write_blog_rewriter
|
||||
from lib.ai_writers.ai_blog_faqs_writer.faqs_ui import main as faqs_generator
|
||||
from lib.ai_writers.ai_blog_writer.ai_blog_generator import ai_blog_writer_page
|
||||
from lib.ai_writers.ai_outline_writer.outline_ui import main as outline_generator
|
||||
from lib.alwrity_ui.dashboard_styles import apply_dashboard_style, render_dashboard_header, render_category_header, render_card
|
||||
from loguru import logger
|
||||
|
||||
# Try to import AI Content Performance Predictor (AI-first approach)
|
||||
try:
|
||||
from lib.content_performance_predictor.ai_performance_predictor import render_ai_predictor_ui as render_content_performance_predictor
|
||||
AI_PREDICTOR_AVAILABLE = True
|
||||
logger.info("AI Content Performance Predictor loaded successfully")
|
||||
except ImportError:
|
||||
logger.warning("AI Content Performance Predictor not available")
|
||||
render_content_performance_predictor = None
|
||||
AI_PREDICTOR_AVAILABLE = False
|
||||
|
||||
# Try to import Bootstrap AI Competitive Suite
|
||||
try:
|
||||
from lib.ai_competitive_suite.bootstrap_ai_suite import render_bootstrap_ai_suite
|
||||
BOOTSTRAP_SUITE_AVAILABLE = True
|
||||
logger.info("Bootstrap AI Competitive Suite loaded successfully")
|
||||
except ImportError:
|
||||
logger.warning("Bootstrap AI Competitive Suite not available")
|
||||
render_bootstrap_ai_suite = None
|
||||
BOOTSTRAP_SUITE_AVAILABLE = False
|
||||
|
||||
def list_ai_writers():
|
||||
"""Return a list of available AI writers with their metadata (no UI rendering)."""
|
||||
writers = []
|
||||
|
||||
# Add Content Performance Predictor if available
|
||||
if render_content_performance_predictor:
|
||||
# AI-first approach description
|
||||
if AI_PREDICTOR_AVAILABLE:
|
||||
description = "🎯 AI-powered content performance prediction with competitive intelligence - perfect for solo entrepreneurs"
|
||||
name = "AI Content Performance Predictor"
|
||||
else:
|
||||
description = "Predict content success before publishing with AI-powered performance analysis"
|
||||
name = "Content Performance Predictor"
|
||||
|
||||
writers.append({
|
||||
"name": name,
|
||||
"icon": "🎯",
|
||||
"description": description,
|
||||
"category": "⭐ Featured",
|
||||
"function": render_content_performance_predictor,
|
||||
"path": "performance_predictor",
|
||||
"featured": True
|
||||
})
|
||||
|
||||
# Add Bootstrap AI Competitive Suite if available
|
||||
if render_bootstrap_ai_suite:
|
||||
writers.append({
|
||||
"name": "Bootstrap AI Competitive Suite",
|
||||
"icon": "🚀",
|
||||
"description": "🥷 Complete AI-powered competitive toolkit: content performance prediction + competitive intelligence for solo entrepreneurs",
|
||||
"category": "⭐ Featured",
|
||||
"function": render_bootstrap_ai_suite,
|
||||
"path": "bootstrap_ai_suite",
|
||||
"featured": True
|
||||
})
|
||||
|
||||
# Add existing writers
|
||||
writers.extend([
|
||||
{
|
||||
"name": "AI Blog Writer",
|
||||
"icon": "📝",
|
||||
"description": "Generate comprehensive blog posts from keywords, URLs, or uploaded content",
|
||||
"category": "Content Creation",
|
||||
"function": ai_blog_writer_page,
|
||||
"path": "ai_blog_writer"
|
||||
},
|
||||
{
|
||||
"name": "AI Blog Rewriter",
|
||||
"icon": "🔄",
|
||||
"description": "Rewrite and update existing blog content with improved quality and SEO optimization",
|
||||
"category": "Content Creation",
|
||||
"function": write_blog_rewriter,
|
||||
"path": "blog_rewriter"
|
||||
},
|
||||
{
|
||||
"name": "Story Writer",
|
||||
"icon": "📚",
|
||||
"description": "Create engaging stories and narratives with AI assistance",
|
||||
"category": "Creative Writing",
|
||||
"function": story_input_section,
|
||||
"path": "story_writer"
|
||||
},
|
||||
{
|
||||
"name": "Essay writer",
|
||||
"icon": "✍️",
|
||||
"description": "Generate well-structured essays on any topic",
|
||||
"category": "Academic",
|
||||
"function": essay_writer,
|
||||
"path": "essay_writer"
|
||||
},
|
||||
{
|
||||
"name": "Write News reports",
|
||||
"icon": "📰",
|
||||
"description": "Create professional news articles and reports",
|
||||
"category": "Journalism",
|
||||
"function": ai_news_writer,
|
||||
"path": "news_writer"
|
||||
},
|
||||
{
|
||||
"name": "Write Financial TA report",
|
||||
"icon": "📊",
|
||||
"description": "Generate technical analysis reports for financial markets",
|
||||
"category": "Finance",
|
||||
"function": ai_finance_ta_writer,
|
||||
"path": "financial_writer"
|
||||
},
|
||||
{
|
||||
"name": "AI Product Description Writer",
|
||||
"icon": "🛍️",
|
||||
"description": "Create compelling product descriptions that drive sales",
|
||||
"category": "E-commerce",
|
||||
"function": write_ai_prod_desc,
|
||||
"path": "product_writer"
|
||||
},
|
||||
{
|
||||
"name": "AI Copywriter",
|
||||
"icon": "✒️",
|
||||
"description": "Generate persuasive copy for marketing and advertising",
|
||||
"category": "Marketing",
|
||||
"function": copywriter_dashboard,
|
||||
"path": "copywriter"
|
||||
},
|
||||
{
|
||||
"name": "LinkedIn AI Writer",
|
||||
"icon": "💼",
|
||||
"description": "Create professional LinkedIn content that engages your network",
|
||||
"category": "Professional",
|
||||
"function": lambda: LinkedInAIWriter().run(),
|
||||
"path": "linkedin_writer"
|
||||
},
|
||||
{
|
||||
"name": "FAQ Generator",
|
||||
"icon": "❓",
|
||||
"description": "Generate comprehensive, well-researched FAQs from any content source with customizable options",
|
||||
"category": "Content Creation",
|
||||
"function": faqs_generator,
|
||||
"path": "faqs_generator"
|
||||
},
|
||||
{
|
||||
"name": "Blog Outline Generator",
|
||||
"icon": "📋",
|
||||
"description": "Create detailed blog outlines with AI-powered content generation and image integration",
|
||||
"category": "Content Creation",
|
||||
"function": outline_generator,
|
||||
"path": "outline_generator"
|
||||
}
|
||||
])
|
||||
|
||||
return writers
|
||||
|
||||
def get_ai_writers():
|
||||
"""Main function to display AI writers dashboard with premium glassmorphic design."""
|
||||
logger.info("Starting AI Writers Dashboard")
|
||||
|
||||
# Apply common dashboard styling
|
||||
apply_dashboard_style()
|
||||
|
||||
# Render dashboard header
|
||||
render_dashboard_header(
|
||||
"🤖 AI Content Writers",
|
||||
"Choose from our collection of specialized AI writers, each designed for specific content types and industries. Create engaging, high-quality content with just a few clicks."
|
||||
)
|
||||
|
||||
writers = list_ai_writers()
|
||||
logger.info(f"Found {len(writers)} AI writers")
|
||||
|
||||
# Group writers by category for better organization
|
||||
categories = {}
|
||||
for writer in writers:
|
||||
category = writer["category"]
|
||||
if category not in categories:
|
||||
categories[category] = []
|
||||
categories[category].append(writer)
|
||||
|
||||
# Render writers by category with common cards
|
||||
for category_name, category_writers in categories.items():
|
||||
render_category_header(category_name)
|
||||
|
||||
# Create columns for this category
|
||||
cols = st.columns(min(len(category_writers), 3))
|
||||
|
||||
for idx, writer in enumerate(category_writers):
|
||||
with cols[idx % 3]:
|
||||
# Use the common card renderer
|
||||
if render_card(
|
||||
icon=writer['icon'],
|
||||
title=writer['name'],
|
||||
description=writer['description'],
|
||||
category=writer['category'],
|
||||
key_suffix=f"{writer['path']}_{category_name}",
|
||||
help_text=f"Launch {writer['name']} - {writer['description']}"
|
||||
):
|
||||
logger.info(f"Selected writer: {writer['name']} with path: {writer['path']}")
|
||||
st.session_state.selected_writer = writer
|
||||
st.query_params["writer"] = writer['path']
|
||||
logger.info(f"Updated query params with writer: {writer['path']}")
|
||||
st.rerun()
|
||||
|
||||
# Add spacing between categories
|
||||
st.markdown('<div class="category-spacer"></div>', unsafe_allow_html=True)
|
||||
|
||||
logger.info("Finished rendering AI Writers Dashboard")
|
||||
|
||||
return writers
|
||||
|
||||
# Remove the old ai_writers function since it's now integrated into get_ai_writers
|
||||
247
ToBeMigrated/ai_writers/long_form_ai_writer.py
Normal file
247
ToBeMigrated/ai_writers/long_form_ai_writer.py
Normal file
@@ -0,0 +1,247 @@
|
||||
#####################################################
|
||||
#
|
||||
# Alwrity, AI Long form writer - Writing_with_Prompt_Chaining
|
||||
# and generative AI.
|
||||
#
|
||||
#####################################################
|
||||
|
||||
import os
|
||||
import re
|
||||
import time #iwish
|
||||
import sys
|
||||
import yaml
|
||||
from pathlib import Path
|
||||
from dotenv import load_dotenv
|
||||
from configparser import ConfigParser
|
||||
import streamlit as st
|
||||
|
||||
from pprint import pprint
|
||||
from textwrap import dedent
|
||||
|
||||
from loguru import logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
from ..utils.read_main_config_params import read_return_config_section
|
||||
from ..ai_web_researcher.gpt_online_researcher import do_metaphor_ai_research
|
||||
from ..ai_web_researcher.gpt_online_researcher import do_google_serp_search, do_tavily_ai_search
|
||||
from ..blog_metadata.get_blog_metadata import get_blog_metadata_longform
|
||||
from ..blog_postprocessing.save_blog_to_file import save_blog_to_file
|
||||
from ..gpt_providers.text_generation.main_text_generation import llm_text_gen
|
||||
|
||||
|
||||
def generate_with_retry(prompt, system_prompt=None):
|
||||
"""
|
||||
Generates content from the model with retry handling for errors.
|
||||
|
||||
Parameters:
|
||||
prompt (str): The prompt to generate content from.
|
||||
system_prompt (str, optional): Custom system prompt to use instead of the default one.
|
||||
|
||||
Returns:
|
||||
str: The generated content.
|
||||
"""
|
||||
try:
|
||||
# FIXME: Need a progress bar here.
|
||||
return llm_text_gen(prompt, system_prompt)
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating content: {e}")
|
||||
st.error(f"Error generating content: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def long_form_generator(keywords, search_params=None, blog_params=None):
|
||||
"""
|
||||
Generate a long-form blog post based on the given keywords
|
||||
|
||||
Args:
|
||||
keywords (str): Topic or keywords for the blog post
|
||||
search_params (dict, optional): Search parameters for research
|
||||
blog_params (dict, optional): Blog content characteristics
|
||||
"""
|
||||
|
||||
# Initialize default parameters if not provided
|
||||
if blog_params is None:
|
||||
blog_params = {
|
||||
"blog_length": 3000, # Default longer for long-form content
|
||||
"blog_tone": "Professional",
|
||||
"blog_demographic": "Professional",
|
||||
"blog_type": "Informational",
|
||||
"blog_language": "English"
|
||||
}
|
||||
else:
|
||||
# Ensure we have a higher word count for long-form content
|
||||
if blog_params.get("blog_length", 0) < 2500:
|
||||
blog_params["blog_length"] = max(3000, blog_params.get("blog_length", 0))
|
||||
|
||||
# Extract parameters with defaults
|
||||
blog_length = blog_params.get("blog_length", 3000)
|
||||
blog_tone = blog_params.get("blog_tone", "Professional")
|
||||
blog_demographic = blog_params.get("blog_demographic", "Professional")
|
||||
blog_type = blog_params.get("blog_type", "Informational")
|
||||
blog_language = blog_params.get("blog_language", "English")
|
||||
|
||||
st.subheader(f"Long-form {blog_type} Blog ({blog_length}+ words)")
|
||||
|
||||
with st.status("Generating comprehensive long-form content...", expanded=True) as status:
|
||||
# Step 1: Generate outline
|
||||
status.update(label="Creating detailed content outline...")
|
||||
|
||||
# Use a customized prompt based on the blog parameters
|
||||
outline_prompt = f"""
|
||||
As an expert content strategist writing in a {blog_tone} tone for {blog_demographic} audience,
|
||||
create a detailed outline for a comprehensive {blog_type} blog post about "{keywords}"
|
||||
that will be approximately {blog_length} words in {blog_language}.
|
||||
|
||||
The outline should include:
|
||||
1. An engaging headline
|
||||
2. 5-7 main sections with descriptive headings
|
||||
3. 2-3 subsections under each main section
|
||||
4. Key points to cover in each section
|
||||
5. Ideas for relevant examples or case studies
|
||||
6. Suggestions for data points or statistics to include
|
||||
|
||||
Format the outline in markdown with proper headings and bullet points.
|
||||
"""
|
||||
|
||||
try:
|
||||
outline = llm_text_gen(outline_prompt)
|
||||
st.markdown("### Content Outline")
|
||||
st.markdown(outline)
|
||||
status.update(label="Outline created successfully ✓")
|
||||
|
||||
# Step 2: Research the topic using the search parameters
|
||||
status.update(label="Researching topic details...")
|
||||
research_results = research_topic(keywords, search_params)
|
||||
status.update(label="Research completed ✓")
|
||||
|
||||
# Step 3: Generate the full content
|
||||
status.update(label=f"Writing {blog_length}+ word {blog_tone} {blog_type} content...")
|
||||
|
||||
full_content_prompt = f"""
|
||||
You are a professional content writer who specializes in {blog_type} content with a {blog_tone} tone
|
||||
for {blog_demographic} audiences. Write a comprehensive, in-depth blog post in {blog_language} about:
|
||||
|
||||
"{keywords}"
|
||||
|
||||
Use this outline as your structure:
|
||||
{outline}
|
||||
|
||||
And incorporate these research findings where relevant:
|
||||
{research_results}
|
||||
|
||||
The blog post should:
|
||||
- Be approximately {blog_length} words
|
||||
- Include an engaging introduction and strong conclusion
|
||||
- Use appropriate subheadings for all sections in the outline
|
||||
- Include examples, data points, and actionable insights
|
||||
- Be formatted in markdown with proper headings, bullet points, and emphasis
|
||||
- Maintain a {blog_tone} tone throughout
|
||||
- Address the needs and interests of a {blog_demographic} audience
|
||||
|
||||
Do not include phrases like "according to research" or "based on the outline" in your content.
|
||||
"""
|
||||
|
||||
full_content = llm_text_gen(full_content_prompt)
|
||||
status.update(label="Long-form content generated successfully! ✓", state="complete")
|
||||
|
||||
# Display the full content
|
||||
st.markdown("### Your Complete Long-form Blog Post")
|
||||
st.markdown(full_content)
|
||||
|
||||
return full_content
|
||||
|
||||
except Exception as e:
|
||||
status.update(label=f"Error generating long-form content: {str(e)}", state="error")
|
||||
st.error(f"Failed to generate long-form content: {str(e)}")
|
||||
return None
|
||||
|
||||
def research_topic(keywords, search_params=None):
|
||||
"""
|
||||
Research a topic using search parameters and return a summary
|
||||
|
||||
Args:
|
||||
keywords (str): Topic to research
|
||||
search_params (dict, optional): Search parameters
|
||||
|
||||
Returns:
|
||||
str: Research summary
|
||||
"""
|
||||
# Display a placeholder for research results
|
||||
placeholder = st.empty()
|
||||
placeholder.info("Researching topic... Please wait.")
|
||||
|
||||
try:
|
||||
from .ai_blog_writer.keywords_to_blog_streamlit import do_tavily_ai_search
|
||||
|
||||
# Use provided search params or defaults
|
||||
if search_params is None:
|
||||
search_params = {
|
||||
"max_results": 10,
|
||||
"search_depth": "advanced",
|
||||
"time_range": "year"
|
||||
}
|
||||
|
||||
# Conduct research using Tavily
|
||||
tavily_results = do_tavily_ai_search(
|
||||
keywords,
|
||||
max_results=search_params.get("max_results", 10),
|
||||
search_depth=search_params.get("search_depth", "advanced"),
|
||||
include_domains=search_params.get("include_domains", []),
|
||||
time_range=search_params.get("time_range", "year")
|
||||
)
|
||||
|
||||
# Extract research data
|
||||
research_data = ""
|
||||
if tavily_results and len(tavily_results) == 3:
|
||||
results, titles, answer = tavily_results
|
||||
|
||||
if answer and len(answer) > 50:
|
||||
research_data += f"Summary: {answer}\n\n"
|
||||
|
||||
if results and 'results' in results and len(results['results']) > 0:
|
||||
research_data += "Key Sources:\n"
|
||||
for i, result in enumerate(results['results'][:7], 1):
|
||||
title = result.get('title', 'Untitled Source')
|
||||
content_snippet = result.get('content', '')[:300] + "..."
|
||||
research_data += f"{i}. {title}\n{content_snippet}\n\n"
|
||||
|
||||
# If research data is empty or too short, provide a generic response
|
||||
if not research_data or len(research_data) < 100:
|
||||
research_data = f"No specific research data found for '{keywords}'. Please provide more specific information in your content."
|
||||
|
||||
placeholder.success("Research completed successfully!")
|
||||
return research_data
|
||||
|
||||
except Exception as e:
|
||||
placeholder.error(f"Research failed: {str(e)}")
|
||||
return f"Unable to gather research for '{keywords}'. Please continue with the content based on your knowledge."
|
||||
finally:
|
||||
# Remove the placeholder after a short delay
|
||||
import time
|
||||
time.sleep(1)
|
||||
placeholder.empty()
|
||||
|
||||
|
||||
def generate_long_form_content(content_keywords):
|
||||
"""
|
||||
Main function to generate long-form content based on the provided keywords.
|
||||
|
||||
Parameters:
|
||||
content_keywords (str): The main keywords or topic for the long-form content.
|
||||
|
||||
Returns:
|
||||
str: The generated long-form content.
|
||||
"""
|
||||
return long_form_generator(content_keywords)
|
||||
|
||||
|
||||
# Example usage
|
||||
if __name__ == "__main__":
|
||||
# Example usage of the function
|
||||
content_keywords = "artificial intelligence in healthcare"
|
||||
generated_content = generate_long_form_content(content_keywords)
|
||||
print(f"Generated content: {generated_content[:100]}...")
|
||||
202
ToBeMigrated/ai_writers/scholar_blogs/main_arxiv_to_blog.py
Normal file
202
ToBeMigrated/ai_writers/scholar_blogs/main_arxiv_to_blog.py
Normal file
@@ -0,0 +1,202 @@
|
||||
import sys
|
||||
import os
|
||||
import datetime
|
||||
|
||||
import tiktoken
|
||||
|
||||
from .arxiv_schlorly_research import fetch_arxiv_data, create_dataframe, get_arxiv_main_content
|
||||
from .arxiv_schlorly_research import arxiv_bibtex, scrape_images_from_arxiv, download_image
|
||||
from .arxiv_schlorly_research import read_written_ids, extract_arxiv_ids_from_line, append_id_to_file
|
||||
from .write_research_review_blog import review_research_paper
|
||||
from .combine_research_and_blog import blog_with_research
|
||||
from .write_blog_scholar_paper import write_blog_from_paper
|
||||
from .gpt_providers.gemini_pro_text import gemini_text_response
|
||||
from .generate_image_from_prompt import generate_image
|
||||
from .convert_content_to_markdown import convert_tomarkdown_format
|
||||
from .get_blog_metadata import blog_metadata
|
||||
from .get_code_examples import gemini_get_code_samples
|
||||
from .save_blog_to_file import save_blog_to_file
|
||||
from .take_url_screenshot import screenshot_api
|
||||
|
||||
from loguru import logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
|
||||
def blog_arxiv_keyword(query):
|
||||
""" Write blog on given arxiv paper."""
|
||||
arxiv_id = None
|
||||
arxiv_url = None
|
||||
bibtex = None
|
||||
research_review = None
|
||||
column_names = ['Title', 'Date', 'Id', 'Summary', 'PDF URL']
|
||||
papers = fetch_arxiv_data(query)
|
||||
df = create_dataframe(papers, column_names)
|
||||
|
||||
for paper in papers:
|
||||
# Extracting the arxiv_id
|
||||
arxiv_id = paper[2].split('/')[-1]
|
||||
arxiv_url = "https://browse.arxiv.org/html/" + arxiv_id
|
||||
bibtex = arxiv_bibtex(arxiv_id)
|
||||
logger.info(f"Get research paper text from the url: {arxiv_url}")
|
||||
research_content = get_arxiv_main_content(arxiv_url)
|
||||
|
||||
num_tokens = num_tokens_from_string(research_content, "cl100k_base")
|
||||
logger.info(f"Number of tokens sent: {num_tokens}")
|
||||
# If the number of tokens is below the threshold, process and print the review
|
||||
if 1000 < num_tokens < 30000:
|
||||
logger.info(f"Writing research review on {paper[0]}")
|
||||
research_review = review_research_paper(research_content)
|
||||
research_review = f"\n{research_review}\n\n" + f"```{bibtex}```"
|
||||
#research_review = research_review + "\n\n\n" + f"{df.to_markdown()}"
|
||||
research_review = convert_tomarkdown_format(research_review, "gemini")
|
||||
break
|
||||
else:
|
||||
# Skip to the next iteration if the condition is not met
|
||||
continue
|
||||
|
||||
logger.info(f"Final scholar article: \n\n{research_review}\n")
|
||||
|
||||
# TBD: Scrape images from research reports and pass to vision to get conclusions out of it.
|
||||
#image_urls = scrape_images_from_arxiv(arxiv_url)
|
||||
#print("Downloading images found on the page:")
|
||||
#for img_url in image_urls:
|
||||
# download_image(img_url, arxiv_url)
|
||||
try:
|
||||
blog_postprocessing(arxiv_id, research_review)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed in blog post processing: {err}")
|
||||
sys.exit(1)
|
||||
|
||||
logger.info(f"\n\n ################ Finished writing Blog for : #################### \n")
|
||||
|
||||
|
||||
def blog_arxiv_url_list(file_path):
|
||||
""" Write blogs on all the arxiv links given in a file. """
|
||||
extracted_ids = []
|
||||
try:
|
||||
with open(file_path, 'r', encoding="utf-8") as file:
|
||||
for line in file:
|
||||
arxiv_id = extract_arxiv_ids_from_line(line)
|
||||
if arxiv_id:
|
||||
extracted_ids.append(arxiv_id)
|
||||
except FileNotFoundError:
|
||||
logger.error(f"File not found: {file_path}")
|
||||
raise FileNotFoundError
|
||||
except Exception as e:
|
||||
logger.error(f"Error while reading the file: {e}")
|
||||
raise e
|
||||
|
||||
# Read already written IDs
|
||||
written_ids = read_written_ids('papers_already_written_on.txt')
|
||||
|
||||
# Loop through extracted IDs
|
||||
for arxiv_id in extracted_ids:
|
||||
if arxiv_id not in written_ids:
|
||||
# This ID has not been written on yet
|
||||
arxiv_url = "https://browse.arxiv.org/html/" + arxiv_id
|
||||
logger.info(f"Get research paper text from the url: {arxiv_url}")
|
||||
research_content = get_arxiv_main_content(arxiv_url)
|
||||
try:
|
||||
num_tokens = num_tokens_from_string(research_content, "cl100k_base")
|
||||
except Exception as err:
|
||||
logger.error(f"Failed in counting tokens: {err}")
|
||||
sys.exit(1)
|
||||
logger.info(f"Number of tokens sent: {num_tokens}")
|
||||
# If the number of tokens is below the threshold, process and print the review
|
||||
# FIXME: Docs over 30k tokens, need to be chunked and summarized.
|
||||
if 1000 < num_tokens < 30000:
|
||||
try:
|
||||
logger.info(f"Getting bibtex for arxiv ID: {arxiv_id}")
|
||||
bibtex = arxiv_bibtex(arxiv_id)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to get Bibtex: {err}")
|
||||
|
||||
try:
|
||||
logger.info(f"Writing a research review..")
|
||||
research_review = review_research_paper(research_content, "gemini")
|
||||
logger.info(f"Research Review: \n{research_review}\n\n")
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to write review on research paper: {arxiv_id}{err}")
|
||||
|
||||
research_blog = write_blog_from_paper(research_content, "gemini")
|
||||
logger.info(f"\n\nResearch Blog: {research_blog}\n\n")
|
||||
research_blog = f"\n{research_review}\n\n" + f"```\n{bibtex}\n```"
|
||||
#research_review = blog_with_research(research_review, research_blog, "gemini")
|
||||
#logger.info(f"\n\n\nBLOG_WITH_RESEARCh: {research_review}\n\n\n")
|
||||
research_review = convert_tomarkdown_format(research_review, "gemini")
|
||||
research_review = f"\n{research_review}\n\n" + f"```{bibtex}```"
|
||||
logger.info(f"Final blog from research paper: \n\n{research_review}\n\n\n")
|
||||
|
||||
try:
|
||||
blog_postprocessing(arxiv_id, research_review)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed in blog post processing: {err}")
|
||||
sys.exit(1)
|
||||
|
||||
logger.info(f"\n\n ################ Finished writing Blog for : #################### \n")
|
||||
else:
|
||||
# Skip to the next iteration if the condition is not met
|
||||
logger.error("FIXME: Docs over 30k tokens, need to be chunked and summarized.")
|
||||
continue
|
||||
else:
|
||||
logger.warning(f"Already written, skip writing on Arxiv paper ID: {arxiv_id}")
|
||||
|
||||
|
||||
def blog_postprocessing(arxiv_id, research_review):
|
||||
""" Common function to do blog postprocessing. """
|
||||
try:
|
||||
append_id_to_file(arxiv_id, "papers_already_written_on.txt")
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to write/append ID to papers_already_written_on.txt: {err}")
|
||||
raise err
|
||||
|
||||
try:
|
||||
blog_title, blog_meta_desc, blog_tags, blog_categories = blog_metadata(research_review)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to get blog metadata: {err}")
|
||||
raise err
|
||||
|
||||
try:
|
||||
arxiv_url_scrnsht = f"https://arxiv.org/abs/{arxiv_id}"
|
||||
generated_image_filepath = take_paper_screenshot(arxiv_url_scrnsht)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to tsk paper screenshot: {err}")
|
||||
raise err
|
||||
|
||||
try:
|
||||
save_blog_to_file(research_review, blog_title, blog_meta_desc, blog_tags,\
|
||||
blog_categories, generated_image_filepath)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to save blog to a file: {err}")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
def take_paper_screenshot(arxiv_url):
|
||||
""" Common function to take paper screenshot. """
|
||||
# fixme: Remove the hardcoding, need add another option OR in config ?
|
||||
image_dir = os.path.join(os.getcwd(), "blog_images")
|
||||
generated_image_name = f"generated_image_{datetime.datetime.now():%Y-%m-%d-%H-%M-%S}.png"
|
||||
generated_image_filepath = os.path.join(image_dir, generated_image_name)
|
||||
|
||||
if arxiv_url:
|
||||
try:
|
||||
generated_image_filepath = screenshot_api(arxiv_url, generated_image_filepath)
|
||||
except Exception as err:
|
||||
logger.error(f"Failed in taking url screenshot: {err}")
|
||||
|
||||
return generated_image_filepath
|
||||
|
||||
|
||||
def num_tokens_from_string(string, encoding_name):
|
||||
"""Returns the number of tokens in a text string."""
|
||||
try:
|
||||
encoding = tiktoken.get_encoding(encoding_name)
|
||||
num_tokens = len(encoding.encode(string))
|
||||
return num_tokens
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to count tokens: {err}")
|
||||
sys.exit(1)
|
||||
@@ -0,0 +1,49 @@
|
||||
import sys
|
||||
|
||||
from .gpt_providers.openai_chat_completion import openai_chatgpt
|
||||
from .gpt_providers.gemini_pro_text import gemini_text_response
|
||||
|
||||
from loguru import logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
|
||||
def write_blog_from_paper(paper_content):
|
||||
""" Write blog from given paper url. """
|
||||
prompt = f"""As an expert in NLP and AI, I will provide you with a content of a research paper.
|
||||
Your task is to write a highly detailed blog(at least 2000 words), breaking down complex concepts for beginners.
|
||||
Take your time and do not rush to respond.
|
||||
Do not provide explanations, suggestions in your response.
|
||||
|
||||
Include the below section in your blog:
|
||||
Highlights: Include a list of 5 most important and unique claims of the given research paper.
|
||||
Abstract: Start by reading the abstract, which provides a concise summary of the research, including its purpose, methodology, and key findings.
|
||||
Introduction: This section will give you background information and set the context for the research. It often ends with a statement of the research question or hypothesis.
|
||||
Methodology: Include description of how authors conducted the research. This can include data sources, experimental setup, analytical techniques, etc.
|
||||
Results: This section presents the data or findings of the research. Pay attention to figures, tables, and any statistical analysis provided.
|
||||
Discussion/Analysis: In this section, Explain how research paper answers the research questions or how they fit with existing knowledge.
|
||||
Conclusion: This part summarizes the main findings and their implications. It might also suggest areas for further research.
|
||||
References: The cited works can provide additional context or background reading.
|
||||
Remember, Please use MLA format and markdown syntax.
|
||||
Do not provide description, explanations for your response.
|
||||
Take your time in crafting your blog content, do not rush to give the response.
|
||||
Using the blog structure above, please write a detailed and original blog on given research paper: \n'{paper_content}'\n\n"""
|
||||
|
||||
if 'gemini' in gpt_providers:
|
||||
try:
|
||||
response = gemini_text_response(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to get response from gemini: {err}")
|
||||
raise err
|
||||
elif 'openai' in gpt_providers:
|
||||
try:
|
||||
logger.info("Calling OpenAI LLM.")
|
||||
response = openai_chatgpt(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
logger.error(f"failed to get response from Openai: {err}")
|
||||
raise err
|
||||
@@ -0,0 +1,89 @@
|
||||
import sys
|
||||
|
||||
from .gpt_providers.openai_chat_completion import openai_chatgpt
|
||||
from .gpt_providers.gemini_pro_text import gemini_text_response
|
||||
from .gpt_providers.mistral_chat_completion import mistral_text_response
|
||||
|
||||
from loguru import logger
|
||||
logger.remove()
|
||||
logger.add(sys.stdout,
|
||||
colorize=True,
|
||||
format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
|
||||
)
|
||||
|
||||
|
||||
def review_research_paper(research_blog):
|
||||
""" """
|
||||
prompt = f"""As world's top researcher and academician, I will provide you with research paper.
|
||||
Your task is to write a highly detailed review report.
|
||||
Important, your report should be factual, original and demostrate your expertise.
|
||||
|
||||
Review guidelines:
|
||||
1). Read the Abstract and Introduction Carefully:
|
||||
Begin by thoroughly reading the abstract and introduction of the paper.
|
||||
Try to understand the research question, the objectives, and the background information.
|
||||
Identify the central argument or hypothesis that the study is examining.
|
||||
|
||||
2). Examine the Methodology and Methods:
|
||||
Read closely at the research design, whether it is experimental, observational, qualitative, or a combination of methods.
|
||||
Check the sampling strategy and the size of the sample.
|
||||
Review the methods of data collection and the instruments used for this purpose.
|
||||
Think about any ethical issues and possible biases in the study.
|
||||
|
||||
3). Analyze the Results and Discussion:
|
||||
Review how the results are presented, including any tables, graphs, and statistical analysis.
|
||||
Evaluate the findings' validity and reliability.
|
||||
Analyze whether the results support or contradict the research question and hypothesis.
|
||||
Read the discussion section where the authors interpret their findings and their significance.
|
||||
|
||||
4). Consider the Limitations and Strengths:
|
||||
Spot any limitations or potential weaknesses in the study.
|
||||
Evaluate the strengths and contributions that the research makes.
|
||||
Think about how generalizable the findings are to other populations or situations.
|
||||
|
||||
5). Assess the Writing and Organization:
|
||||
Judge the clarity and structure of the report.
|
||||
Consider the use of language, grammar, and the overall formatting.
|
||||
Assess how well the arguments are logically organized and how coherent the report is.
|
||||
|
||||
6). Evaluate the Literature Review:
|
||||
Examine how comprehensive and relevant the literature review is.
|
||||
Consider how the study adds to or builds upon existing research.
|
||||
Evaluate the timeliness and quality of the sources cited in the research.
|
||||
|
||||
7). Review the Conclusion and Implications:
|
||||
Look at the conclusions drawn from the study and how well they align with the findings.
|
||||
Think about the practical implications and potential applications of the research.
|
||||
Evaluate the suggestions for further research or policy actions.
|
||||
|
||||
8). Overall Assessment:
|
||||
Formulate an overall opinion about the research report's quality and thoroughness.
|
||||
Consider the significance and impact of the findings.
|
||||
Evaluate how the study contributes to its field of research.
|
||||
|
||||
9). Provide Constructive Feedback:
|
||||
Offer constructive criticism and suggestions for improvement, where necessary.
|
||||
Think about possible biases or alternative ways to interpret the findings.
|
||||
Suggest ideas for future research or for replicating the study.
|
||||
|
||||
Do not provide description, explanations for your response.
|
||||
Using the above review guidelines, write a detailed review report on the below research paper.
|
||||
Research Paper: '{research_blog}'
|
||||
"""
|
||||
|
||||
if 'gemini' in gpt_providers:
|
||||
try:
|
||||
response = gemini_text_response(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
logger.error(f"Failed to get response from gemini: {err}")
|
||||
response = mistral_text_response(prompt)
|
||||
return response
|
||||
|
||||
elif 'openai' in gpt_providers:
|
||||
try:
|
||||
logger.info("Calling OpenAI LLM.")
|
||||
response = openai_chatgpt(prompt)
|
||||
return response
|
||||
except Exception as err:
|
||||
SystemError(f"Failed to get response from Openai: {err}")
|
||||
@@ -1,51 +0,0 @@
|
||||
# Changelog
|
||||
|
||||
All notable changes to the ALwrity project will be documented in this file.
|
||||
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Added
|
||||
|
||||
#### Auto-Dubbing Feature (Podcast Maker)
|
||||
- **Translation Service** (`backend/services/translation/`)
|
||||
- Common translation module for use across the entire application
|
||||
- DeepL integration for low-cost, high-quality text translation (500k chars/month free)
|
||||
- WaveSpeed integration for high-quality video/audio translation
|
||||
- Support for 34+ languages
|
||||
- Batch translation support
|
||||
- Factory pattern for provider selection
|
||||
- Cost estimation utilities
|
||||
|
||||
- **Audio Dubbing Service** (`backend/services/dubbing/`)
|
||||
- Audio dubbing with STT → Translate → TTS pipeline
|
||||
- Voice cloning support to preserve original speaker's voice
|
||||
- Low-quality (DeepL) and high-quality (WaveSpeed) modes
|
||||
- Batch dubbing support
|
||||
- Cost estimation
|
||||
|
||||
- **Podcast API Endpoints** (`backend/api/podcast/`)
|
||||
- `POST /api/podcast/dub/audio` - Create audio dubbing task
|
||||
- `GET /api/podcast/dub/{task_id}/result` - Get dubbing result
|
||||
- `POST /api/podcast/dub/voices/clone` - Clone voice from audio sample
|
||||
- `GET /api/podcast/dub/voices/{task_id}/result` - Get voice clone result
|
||||
- `POST /api/podcast/dub/estimate` - Estimate dubbing cost
|
||||
- `GET /api/podcast/dub/languages` - List supported languages
|
||||
- `GET /api/podcast/dub/voices` - List available TTS voices
|
||||
|
||||
- **Bug Fixes**
|
||||
- Fixed missing `Path` import in `scene_animation.py`
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated `backend/services/__init__.py` to export translation and dubbing services
|
||||
- Updated `.env` with DeepL API key placeholder
|
||||
|
||||
### Documentation
|
||||
|
||||
- Added `backend/docs/AUTO_DUBBING.md` with comprehensive feature documentation
|
||||
|
||||
## [Previous Releases]
|
||||
|
||||
See git history for previous changelog entries.
|
||||
@@ -1,2 +0,0 @@
|
||||
# Use start_alwrity_backend.py for deployment
|
||||
web: python start_alwrity_backend.py --production
|
||||
@@ -350,28 +350,4 @@ If you encounter issues:
|
||||
|
||||
---
|
||||
|
||||
**Happy coding! 🎉**
|
||||
|
||||
## Backlink Outreach Migration Map
|
||||
|
||||
Canonical migrated backlinking module paths:
|
||||
|
||||
- Router: `backend/routers/backlink_outreach.py`
|
||||
- Service: `backend/services/backlink_outreach_service.py`
|
||||
- Frontend API client: `frontend/src/api/backlinkOutreachApi.ts`
|
||||
- Frontend store: `frontend/src/stores/backlinkOutreachStore.ts`
|
||||
- Frontend UI integration: `frontend/src/components/SEODashboard/BacklinkOutreachModuleList.tsx`
|
||||
|
||||
Invoke from backend:
|
||||
|
||||
- `GET /api/backlink-outreach/modules`
|
||||
- `GET /api/backlink-outreach/query-templates?keyword=<keyword>`
|
||||
- `GET /api/backlink-outreach/migration-coverage`
|
||||
- `POST /api/backlink-outreach/discover` with JSON body: `{ "keyword": "...", "max_results": 10 }`
|
||||
- `POST /api/backlink-outreach/policy-validate` to enforce compliance/suppression/throttles before send
|
||||
- `GET /api/backlink-outreach/reporting` for send-volume and conversion snapshot
|
||||
- `POST /api/backlink-outreach/campaigns` and `GET /api/backlink-outreach/campaigns` for persisted campaign records (campaign-creator style storage flow)
|
||||
|
||||
The modules endpoint returns migration identifiers: `backlink`, `outreach`, and `guest_post`.
|
||||
The query-template endpoint mirrors legacy `generate_search_queries(...)` behavior from `ToBeMigrated/ai_marketing_tools/ai_backlinker/ai_backlinking.py`.
|
||||
The migration-coverage endpoint summarizes what is already implemented vs planned from the legacy prototype roadmap.
|
||||
**Happy coding! 🎉**
|
||||
@@ -1,157 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
# Add _get_all_historical_usage method to usage_tracking_service.py
|
||||
|
||||
with open('services/subscription/usage_tracking_service.py', 'r', encoding='utf-8') as f:
|
||||
lines = f.readlines()
|
||||
|
||||
# Find where to insert (before get_usage_trends)
|
||||
insert_idx = None
|
||||
for i, line in enumerate(lines):
|
||||
if ' def get_usage_trends(' in line:
|
||||
insert_idx = i
|
||||
break
|
||||
|
||||
if insert_idx is None:
|
||||
print("Error: Could not find insertion point")
|
||||
exit(1)
|
||||
|
||||
print(f"Inserting at line {insert_idx + 1}")
|
||||
|
||||
# Method to insert
|
||||
new_method = ''' def _get_all_historical_usage(self, user_id: str) -> Dict[str, Any]:
|
||||
"""Get ALL historical usage data aggregated across all billing periods."""
|
||||
|
||||
# Get all usage summaries for the user
|
||||
all_summaries = self.db.query(UsageSummary).filter(
|
||||
UsageSummary.user_id == user_id
|
||||
).order_by(UsageSummary.billing_period.desc()).all()
|
||||
|
||||
if not all_summaries:
|
||||
return {
|
||||
'billing_period': 'all',
|
||||
'usage_status': 'active',
|
||||
'total_calls': 0,
|
||||
'total_tokens': 0,
|
||||
'total_cost': 0.0,
|
||||
'avg_response_time': 0.0,
|
||||
'error_rate': 0.0,
|
||||
'limits': self.pricing_service.get_user_limits(user_id),
|
||||
'provider_breakdown': {},
|
||||
'usage_percentages': {},
|
||||
'historical_breakdown': [],
|
||||
'last_updated': datetime.now().isoformat()
|
||||
}
|
||||
|
||||
# Aggregate all data from UsageSummary
|
||||
total_calls = sum(s.total_calls or 0 for s in all_summaries)
|
||||
total_tokens = sum(s.total_tokens or 0 for s in all_summaries)
|
||||
total_cost = sum(float(s.total_cost or 0) for s in all_summaries)
|
||||
|
||||
# Calculate weighted average response time
|
||||
total_weighted_time = sum((s.avg_response_time or 0) * (s.total_calls or 0) for s in all_summaries)
|
||||
avg_response_time = total_weighted_time / total_calls if total_calls > 0 else 0.0
|
||||
|
||||
# Calculate overall error rate
|
||||
total_errors = sum((s.total_calls or 0) * (s.error_rate or 0) / 100 for s in all_summaries)
|
||||
error_rate = (total_errors / total_calls * 100) if total_calls > 0 else 0.0
|
||||
|
||||
# Get user limits
|
||||
limits = self.pricing_service.get_user_limits(user_id)
|
||||
|
||||
# Map database columns to frontend keys
|
||||
provider_mapping = {
|
||||
'gemini_calls': 'gemini',
|
||||
'openai_calls': 'openai',
|
||||
'anthropic_calls': 'anthropic',
|
||||
'mistral_calls': 'huggingface',
|
||||
'wavespeed_calls': 'wavespeed',
|
||||
'exa_calls': 'exa',
|
||||
'video_calls': 'video',
|
||||
'image_edit_calls': 'image_edit',
|
||||
'audio_calls': 'audio',
|
||||
}
|
||||
|
||||
# Build provider_breakdown for frontend
|
||||
provider_breakdown = {}
|
||||
for db_col, frontend_key in provider_mapping.items():
|
||||
total_provider_calls = sum(getattr(s, db_col, 0) or 0 for s in all_summaries)
|
||||
provider_breakdown[frontend_key] = {
|
||||
'calls': total_provider_calls,
|
||||
'cost': 0,
|
||||
'tokens': 0
|
||||
}
|
||||
|
||||
# Calculate usage_percentages based on limits
|
||||
usage_percentages = {}
|
||||
if limits and limits.get('limits'):
|
||||
# Gemini calls percentage
|
||||
gemini_calls = provider_breakdown.get('gemini', {}).get('calls', 0)
|
||||
gemini_limit = limits.get('limits', {}).get('gemini_calls', 0) or 0
|
||||
if gemini_limit > 0:
|
||||
usage_percentages['gemini_calls'] = (gemini_calls / gemini_limit) * 100
|
||||
|
||||
# HuggingFace calls percentage (from mistral_calls)
|
||||
huggingface_calls = provider_breakdown.get('huggingface', {}).get('calls', 0)
|
||||
huggingface_limit = limits.get('limits', {}).get('mistral_calls', 0) or 0
|
||||
if huggingface_limit > 0:
|
||||
usage_percentages['huggingface_calls'] = (huggingface_calls / huggingface_limit) * 100
|
||||
|
||||
# Cost percentage
|
||||
cost_limit = limits.get('limits', {}).get('monthly_cost', 0) or 0
|
||||
if cost_limit > 0:
|
||||
usage_percentages['cost'] = (total_cost / cost_limit) * 100
|
||||
|
||||
# Build historical breakdown
|
||||
historical_breakdown = []
|
||||
for s in all_summaries:
|
||||
try:
|
||||
status_val = s.usage_status.value
|
||||
except:
|
||||
status_val = str(s.usage_status)
|
||||
historical_breakdown.append({
|
||||
'billing_period': s.billing_period,
|
||||
'total_calls': s.total_calls or 0,
|
||||
'total_tokens': s.total_tokens or 0,
|
||||
'total_cost': float(s.total_cost or 0),
|
||||
'usage_status': status_val,
|
||||
'updated_at': s.updated_at.isoformat() if s.updated_at else None
|
||||
})
|
||||
|
||||
# Determine overall status
|
||||
usage_status = 'active'
|
||||
for s in all_summaries:
|
||||
try:
|
||||
status = s.usage_status.value
|
||||
except:
|
||||
status = str(s.usage_status)
|
||||
if status == 'limit_reached':
|
||||
usage_status = 'limit_reached'
|
||||
break
|
||||
elif status == 'warning' and usage_status != 'limit_reached':
|
||||
usage_status = 'warning'
|
||||
|
||||
return {
|
||||
'billing_period': 'all',
|
||||
'usage_status': usage_status,
|
||||
'total_calls': total_calls,
|
||||
'total_tokens': total_tokens,
|
||||
'total_cost': round(total_cost, 2),
|
||||
'avg_response_time': round(avg_response_time, 2),
|
||||
'error_rate': round(error_rate, 2),
|
||||
'limits': limits,
|
||||
'provider_breakdown': provider_breakdown,
|
||||
'usage_percentages': usage_percentages,
|
||||
'historical_breakdown': historical_breakdown,
|
||||
'last_updated': datetime.now().isoformat()
|
||||
}
|
||||
|
||||
'''
|
||||
|
||||
# Insert the new method
|
||||
new_lines = lines[:insert_idx] + [new_method] + lines[insert_idx:]
|
||||
|
||||
# Write back
|
||||
with open('services/subscription/usage_tracking_service.py', 'w', encoding='utf-8') as f:
|
||||
f.writelines(new_lines)
|
||||
|
||||
print("Successfully added _get_all_historical_usage method")
|
||||
@@ -3,11 +3,6 @@ ALwrity Utilities Package
|
||||
Modular utilities for ALwrity backend startup and configuration.
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
# Check feature mode early to skip heavy imports
|
||||
_is_full_mode = os.getenv("ALWRITY_ENABLED_FEATURES", "").strip().lower() in ("", "all")
|
||||
|
||||
from .dependency_manager import DependencyManager
|
||||
from .environment_setup import EnvironmentSetup
|
||||
from .database_setup import DatabaseSetup
|
||||
@@ -16,20 +11,7 @@ from .health_checker import HealthChecker
|
||||
from .rate_limiter import RateLimiter
|
||||
from .frontend_serving import FrontendServing
|
||||
from .router_manager import RouterManager
|
||||
from .feature_runtime import (
|
||||
get_active_profiles,
|
||||
get_enabled_groups,
|
||||
get_enabled_optional_services,
|
||||
get_enabled_routers,
|
||||
get_enabled_startup_hooks,
|
||||
is_enabled,
|
||||
)
|
||||
|
||||
# Lazy load OnboardingManager - it triggers heavy imports (aiohttp, etc.)
|
||||
if _is_full_mode:
|
||||
from .onboarding_manager import OnboardingManager
|
||||
else:
|
||||
OnboardingManager = None
|
||||
from .onboarding_manager import OnboardingManager
|
||||
|
||||
__all__ = [
|
||||
'DependencyManager',
|
||||
@@ -40,11 +22,5 @@ __all__ = [
|
||||
'RateLimiter',
|
||||
'FrontendServing',
|
||||
'RouterManager',
|
||||
'OnboardingManager',
|
||||
'get_active_profiles',
|
||||
'get_enabled_groups',
|
||||
'get_enabled_optional_services',
|
||||
'get_enabled_routers',
|
||||
'get_enabled_startup_hooks',
|
||||
'is_enabled'
|
||||
'OnboardingManager'
|
||||
]
|
||||
|
||||
@@ -55,28 +55,22 @@ class EnvironmentSetup:
|
||||
print("🔧 Setting up environment variables...")
|
||||
|
||||
# Production environment variables
|
||||
# IMPORTANT: Don't override PORT if already set by Render cloud
|
||||
render_port = os.getenv("PORT")
|
||||
|
||||
if self.production_mode:
|
||||
env_vars = {
|
||||
"HOST": "0.0.0.0",
|
||||
"PORT": "8000",
|
||||
"RELOAD": "false",
|
||||
"LOG_LEVEL": "INFO",
|
||||
"DEBUG": "false"
|
||||
}
|
||||
# Only set PORT if not already provided by cloud (Render sets PORT)
|
||||
if not render_port:
|
||||
env_vars["PORT"] = "8000"
|
||||
else:
|
||||
env_vars = {
|
||||
"HOST": "0.0.0.0",
|
||||
"PORT": "8000",
|
||||
"RELOAD": "true",
|
||||
"LOG_LEVEL": "DEBUG",
|
||||
"DEBUG": "true"
|
||||
}
|
||||
if not render_port:
|
||||
env_vars["PORT"] = "8000"
|
||||
|
||||
for key, value in env_vars.items():
|
||||
os.environ.setdefault(key, value)
|
||||
|
||||
@@ -1,86 +0,0 @@
|
||||
"""Feature profile parsing and expansion logic."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from typing import Iterable, Tuple
|
||||
|
||||
from .feature_registry import FEATURE_GROUPS, PROFILE_GROUP_MAP
|
||||
|
||||
|
||||
ENV_ENABLED_FEATURES = "ALWRITY_ENABLED_FEATURES"
|
||||
DEFAULT_FEATURES = "all"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ExpandedFeatureProfile:
|
||||
"""Expanded profile data used by runtime helpers."""
|
||||
|
||||
profiles: Tuple[str, ...]
|
||||
groups: Tuple[str, ...]
|
||||
|
||||
|
||||
class UnknownFeatureProfileError(ValueError):
|
||||
"""Raised when ALWRITY_ENABLED_FEATURES contains unknown feature values."""
|
||||
|
||||
|
||||
def _get_env_value() -> str:
|
||||
"""Get the enabled features value from environment."""
|
||||
return os.getenv(ENV_ENABLED_FEATURES) or DEFAULT_FEATURES
|
||||
|
||||
|
||||
def _normalize_values(raw_value: str | None) -> Tuple[str, ...]:
|
||||
if not raw_value or not raw_value.strip():
|
||||
return (DEFAULT_FEATURES,)
|
||||
|
||||
normalized = tuple(
|
||||
value.strip().lower()
|
||||
for value in raw_value.split(",")
|
||||
if value.strip()
|
||||
)
|
||||
return normalized or (DEFAULT_FEATURES,)
|
||||
|
||||
|
||||
def parse_feature_profiles(raw_value: str | None = None) -> Tuple[str, ...]:
|
||||
"""Parse and validate feature names from env/raw input.
|
||||
|
||||
Supports comma-separated feature names, e.g. `podcast,core`.
|
||||
Raises UnknownFeatureProfileError when any feature is not registered.
|
||||
"""
|
||||
|
||||
selected_profiles = _normalize_values(raw_value if raw_value is not None else _get_env_value())
|
||||
|
||||
unknown = sorted({profile for profile in selected_profiles if profile not in PROFILE_GROUP_MAP and profile not in FEATURE_GROUPS})
|
||||
if unknown:
|
||||
supported = ", ".join(sorted(set(PROFILE_GROUP_MAP.keys()) | set(FEATURE_GROUPS.keys())))
|
||||
unknown_display = ", ".join(unknown)
|
||||
raise UnknownFeatureProfileError(
|
||||
f"Unknown {ENV_ENABLED_FEATURES} value(s): {unknown_display}. Supported: {supported}."
|
||||
)
|
||||
|
||||
return selected_profiles
|
||||
|
||||
|
||||
def _dedupe_stable(items: Iterable[str]) -> Tuple[str, ...]:
|
||||
return tuple(dict.fromkeys(items))
|
||||
|
||||
|
||||
def expand_profiles(profiles: Tuple[str, ...]) -> ExpandedFeatureProfile:
|
||||
"""Expand profile names into a deduplicated group list."""
|
||||
|
||||
# Handle "all" specially - include all groups
|
||||
if "all" in profiles:
|
||||
return ExpandedFeatureProfile(profiles=("all",), groups=tuple(FEATURE_GROUPS.keys()))
|
||||
|
||||
# Otherwise expand via PROFILE_GROUP_MAP
|
||||
groups = _dedupe_stable(
|
||||
group
|
||||
for profile in profiles
|
||||
for group in PROFILE_GROUP_MAP.get(profile, (profile,))
|
||||
)
|
||||
|
||||
# Include FEATURE_GROUPS keys directly
|
||||
all_groups = _dedupe_stable(list(groups) + [g for g in groups if g in FEATURE_GROUPS])
|
||||
|
||||
return ExpandedFeatureProfile(profiles=profiles, groups=all_groups)
|
||||
@@ -1,89 +0,0 @@
|
||||
"""Feature registry for profile-based capability toggles.
|
||||
|
||||
This module stores normalized feature-group definitions used by the
|
||||
feature profile runtime.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Dict, Tuple
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class FeatureGroup:
|
||||
"""Single feature group and the capabilities it enables."""
|
||||
|
||||
routers: Tuple[str, ...] = ()
|
||||
startup_hooks: Tuple[str, ...] = ()
|
||||
optional_services: Tuple[str, ...] = ()
|
||||
features: Tuple[str, ...] = field(default_factory=tuple)
|
||||
|
||||
|
||||
FEATURE_GROUPS: Dict[str, FeatureGroup] = {
|
||||
"core": FeatureGroup(
|
||||
features=("core", "health", "onboarding", "research"),
|
||||
routers=(
|
||||
"api.component_logic:router",
|
||||
"api.subscription:router",
|
||||
"api.onboarding_utils.step3_routes:router",
|
||||
"api.research.router:router",
|
||||
),
|
||||
startup_hooks=(
|
||||
"services.database:init_database",
|
||||
),
|
||||
optional_services=(
|
||||
"services.scheduler:get_scheduler",
|
||||
),
|
||||
),
|
||||
"podcast": FeatureGroup(
|
||||
features=("podcast",),
|
||||
routers=("api.podcast.router:router",),
|
||||
),
|
||||
"youtube": FeatureGroup(
|
||||
features=("youtube",),
|
||||
routers=("api.youtube.router:router",),
|
||||
),
|
||||
"content_planning": FeatureGroup(
|
||||
features=("content_planning", "strategy_copilot"),
|
||||
routers=(
|
||||
"api.content_planning.api.router:router",
|
||||
"api.content_planning.strategy_copilot:router",
|
||||
),
|
||||
),
|
||||
"blog_writer": FeatureGroup(
|
||||
features=("blog_writer",),
|
||||
routers=(
|
||||
"api.blog_writer.router:router",
|
||||
"api.blog_writer.seo_analysis:router",
|
||||
),
|
||||
),
|
||||
"backlinking": FeatureGroup(
|
||||
features=("backlinking",),
|
||||
routers=("routers.backlink_outreach:router",),
|
||||
),
|
||||
"linkedin": FeatureGroup(
|
||||
features=("linkedin",),
|
||||
routers=(
|
||||
"routers.linkedin:router",
|
||||
"api.linkedin_image_generation:router",
|
||||
),
|
||||
),
|
||||
"facebook": FeatureGroup(
|
||||
features=("facebook",),
|
||||
routers=("api.facebook_writer.routers:facebook_router",),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
PROFILE_GROUP_MAP: Dict[str, Tuple[str, ...]] = {
|
||||
"all": tuple(FEATURE_GROUPS.keys()),
|
||||
"core": ("core",),
|
||||
"podcast": ("core", "podcast"),
|
||||
"youtube": ("core", "youtube"),
|
||||
"blog_writer": ("core", "blog_writer"),
|
||||
"backlinking": ("core", "backlinking"),
|
||||
"linkedin": ("core", "linkedin"),
|
||||
"facebook": ("core", "facebook"),
|
||||
"planning": ("core", "content_planning"),
|
||||
}
|
||||
@@ -1,71 +0,0 @@
|
||||
"""Runtime helpers for profile-driven feature toggles."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from functools import lru_cache
|
||||
from typing import Tuple
|
||||
|
||||
from .feature_profiles import expand_profiles, parse_feature_profiles
|
||||
from .feature_registry import FEATURE_GROUPS
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def _runtime_state() -> dict[str, Tuple[str, ...]]:
|
||||
profiles = parse_feature_profiles()
|
||||
expanded = expand_profiles(profiles)
|
||||
|
||||
routers = []
|
||||
startup_hooks = []
|
||||
optional_services = []
|
||||
enabled_features = set(expanded.groups)
|
||||
|
||||
for group in expanded.groups:
|
||||
feature_group = FEATURE_GROUPS[group]
|
||||
routers.extend(feature_group.routers)
|
||||
startup_hooks.extend(feature_group.startup_hooks)
|
||||
optional_services.extend(feature_group.optional_services)
|
||||
enabled_features.update(feature_group.features)
|
||||
|
||||
return {
|
||||
"profiles": expanded.profiles,
|
||||
"groups": expanded.groups,
|
||||
"routers": tuple(dict.fromkeys(routers)),
|
||||
"startup_hooks": tuple(dict.fromkeys(startup_hooks)),
|
||||
"optional_services": tuple(dict.fromkeys(optional_services)),
|
||||
"features": tuple(sorted(enabled_features)),
|
||||
}
|
||||
|
||||
|
||||
def get_active_profiles() -> Tuple[str, ...]:
|
||||
"""Return validated active profile names."""
|
||||
return _runtime_state()["profiles"]
|
||||
|
||||
|
||||
def get_enabled_groups() -> Tuple[str, ...]:
|
||||
"""Return resolved feature-group names."""
|
||||
return _runtime_state()["groups"]
|
||||
|
||||
|
||||
def get_enabled_routers() -> Tuple[str, ...]:
|
||||
"""Return enabled router import targets in `module:attribute` format."""
|
||||
return _runtime_state()["routers"]
|
||||
|
||||
|
||||
def get_enabled_startup_hooks() -> Tuple[str, ...]:
|
||||
"""Return enabled startup hook import targets in `module:attribute` format."""
|
||||
return _runtime_state()["startup_hooks"]
|
||||
|
||||
|
||||
def get_enabled_optional_services() -> Tuple[str, ...]:
|
||||
"""Return enabled optional service import targets in `module:attribute` format."""
|
||||
return _runtime_state()["optional_services"]
|
||||
|
||||
|
||||
def is_enabled(feature: str) -> bool:
|
||||
"""Return True when a feature/group name is enabled by active profiles."""
|
||||
return feature.strip().lower() in _runtime_state()["features"]
|
||||
|
||||
|
||||
def reset_feature_runtime_cache() -> None:
|
||||
"""Clear runtime cache (useful for tests)."""
|
||||
_runtime_state.cache_clear()
|
||||
@@ -39,10 +39,9 @@ class ProductionOptimizer:
|
||||
def _set_production_env_vars(self) -> None:
|
||||
"""Set production-specific environment variables."""
|
||||
production_vars = {
|
||||
# Note: PORT is NOT set here - it's provided by the deployment platform (e.g., Render)
|
||||
# Don't override PORT as it must come from the environment
|
||||
# Note: HOST is not set here - it's auto-detected by start_backend()
|
||||
# Based on deployment environment (cloud vs local)
|
||||
'PORT': '8000',
|
||||
'RELOAD': 'false',
|
||||
'LOG_LEVEL': 'INFO',
|
||||
'DEBUG': 'false',
|
||||
|
||||
@@ -3,77 +3,10 @@ Router Manager Module
|
||||
Handles FastAPI router inclusion and management.
|
||||
"""
|
||||
|
||||
from importlib import import_module
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
import os
|
||||
|
||||
from fastapi import FastAPI
|
||||
from loguru import logger
|
||||
|
||||
|
||||
CORE_ROUTER_REGISTRY = [
|
||||
{"name": "component_logic", "module": "api.component_logic", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "subscription", "module": "api.subscription", "attr": "router", "features": {"all", "core", "podcast", "blog_writer", "youtube"}},
|
||||
{"name": "step3_research", "module": "api.onboarding_utils.step3_routes", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "step4_assets", "module": "api.onboarding_utils.step4_asset_routes", "attr": "router", "features": {"all", "core", "podcast"}},
|
||||
{"name": "step4_persona", "module": "api.onboarding_utils.step4_persona_routes_optimized", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "gsc_auth", "module": "routers.gsc_auth", "attr": "router", "features": {"all", "core", "seo", "blog_writer"}},
|
||||
{"name": "ai_visibility", "module": "routers.ai_visibility", "attr": "router", "features": {"all", "core", "seo", "blog_writer"}},
|
||||
{"name": "wordpress", "module": "routers.wordpress", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "wordpress_oauth", "module": "routers.wordpress_oauth", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "bing_oauth", "module": "routers.bing_oauth", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "bing_analytics", "module": "routers.bing_analytics", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "bing_analytics_storage", "module": "routers.bing_analytics_storage", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "seo_tools", "module": "routers.seo_tools", "attr": "router", "features": {"all", "core", "seo"}},
|
||||
{"name": "facebook_writer", "module": "api.facebook_writer.routers", "attr": "facebook_router", "features": {"all", "core", "facebook"}},
|
||||
{"name": "linkedin", "module": "routers.linkedin", "attr": "router", "features": {"all", "core", "linkedin"}},
|
||||
{"name": "linkedin_image", "module": "api.linkedin_image_generation", "attr": "router", "features": {"all", "core", "linkedin"}},
|
||||
{"name": "brainstorm", "module": "api.brainstorm", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "hallucination_detector", "module": "api.hallucination_detector", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "writing_assistant", "module": "api.writing_assistant", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "content_planning", "module": "api.content_planning.api.router", "attr": "router", "features": {"all", "core", "content_planning"}},
|
||||
{"name": "user_data", "module": "api.user_data", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "user_environment", "module": "api.user_environment", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "strategy_copilot", "module": "api.content_planning.strategy_copilot", "attr": "router", "features": {"all", "core", "content_planning"}},
|
||||
{"name": "error_logging", "module": "routers.error_logging", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "frontend_env_manager", "module": "routers.frontend_env_manager", "attr": "router", "features": {"all", "core", "blog_writer"}},
|
||||
{"name": "platform_analytics", "module": "routers.platform_analytics", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "bing_insights", "module": "routers.bing_insights", "attr": "router", "features": {"all", "core", "seo"}},
|
||||
{"name": "background_jobs", "module": "routers.background_jobs", "attr": "router", "features": {"all", "core"}},
|
||||
]
|
||||
|
||||
OPTIONAL_ROUTER_REGISTRY = [
|
||||
{"name": "blog_writer", "module": "api.blog_writer.router", "attr": "router", "features": {"all", "blog_writer"}},
|
||||
{"name": "story_writer", "module": "api.story_writer.router", "attr": "router", "features": {"all", "story_writer"}},
|
||||
{"name": "wix", "module": "api.wix_routes", "attr": "router", "features": {"all", "blog_writer"}},
|
||||
{"name": "wix_test", "module": "api.wix_routes", "attr": "qa_router", "features": {"all"}},
|
||||
{"name": "blog_seo_analysis", "module": "api.blog_writer.seo_analysis", "attr": "router", "features": {"all", "blog_writer"}},
|
||||
{"name": "persona", "module": "api.persona_routes", "attr": "router", "features": {"all", "persona"}},
|
||||
{"name": "video_studio", "module": "api.video_studio.router", "attr": "router", "features": {"all", "video_studio"}},
|
||||
{"name": "stability", "module": "routers.stability", "attr": "router", "features": {"all", "image_studio"}},
|
||||
{"name": "stability_advanced", "module": "routers.stability_advanced", "attr": "router", "features": {"all", "image_studio"}},
|
||||
{"name": "stability_admin", "module": "routers.stability_admin", "attr": "router", "features": {"all", "image_studio"}},
|
||||
{"name": "images", "module": "api.images", "attr": "router", "features": {"all", "image_studio", "blog_writer"}},
|
||||
{"name": "image_studio", "module": "routers.image_studio", "attr": "router", "features": {"all", "image_studio"}},
|
||||
{"name": "product_marketing", "module": "routers.product_marketing", "attr": "router", "features": {"all", "product_marketing"}},
|
||||
{"name": "campaign_creator", "module": "routers.campaign_creator", "attr": "router", "features": {"all"}},
|
||||
{"name": "content_assets", "module": "api.content_assets.router", "attr": "router", "features": {"all"}},
|
||||
{"name": "podcast", "module": "api.podcast.router", "attr": "router", "features": {"all", "podcast"}},
|
||||
{"name": "youtube", "module": "api.youtube.router", "attr": "router", "features": {"all", "youtube"}, "include_kwargs": {"prefix": "/api"}},
|
||||
{"name": "research_config", "module": "api.research_config", "attr": "router", "features": {"all", "research"}, "include_kwargs": {"prefix": "/api/research", "tags": ["research"]}},
|
||||
{"name": "research_engine", "module": "api.research.router", "attr": "router", "features": {"all", "research"}, "include_kwargs": {"tags": ["Research Engine"]}},
|
||||
{"name": "scheduler_dashboard", "module": "api.scheduler_dashboard", "attr": "router", "features": {"all", "scheduler"}},
|
||||
{"name": "oauth_token_monitoring", "module": "api.oauth_token_monitoring_routes", "attr": "router", "features": {"all", "core"}},
|
||||
{"name": "agents", "module": "api.agents_api", "attr": "router", "features": {"all"}},
|
||||
{"name": "today_workflow", "module": "api.today_workflow", "attr": "router", "features": {"all"}},
|
||||
{"name": "backlink_outreach", "module": "routers.backlink_outreach", "attr": "router", "features": {"all", "backlinking"}},
|
||||
]
|
||||
|
||||
OPTIONAL_MODULE_MATRIX = {
|
||||
"all": [entry["name"] for entry in OPTIONAL_ROUTER_REGISTRY],
|
||||
"default": [entry["name"] for entry in OPTIONAL_ROUTER_REGISTRY],
|
||||
}
|
||||
from typing import List, Dict, Any, Optional
|
||||
import os
|
||||
|
||||
|
||||
class RouterManager:
|
||||
@@ -83,61 +16,14 @@ class RouterManager:
|
||||
self.app = app
|
||||
self.included_routers = []
|
||||
self.failed_routers = []
|
||||
self.skipped_routers = []
|
||||
|
||||
@staticmethod
|
||||
def get_enabled_features() -> set:
|
||||
"""Get enabled features from ALWRITY_ENABLED_FEATURES env var.
|
||||
|
||||
Values:
|
||||
- "all" - enable all features (default)
|
||||
- comma-separated: "podcast,blog-writer,youtube"
|
||||
- single feature: "podcast"
|
||||
"""
|
||||
env_value = os.getenv("ALWRITY_ENABLED_FEATURES", "all").strip().lower()
|
||||
|
||||
if not env_value or env_value == "all":
|
||||
return {"all"}
|
||||
|
||||
return {f.strip() for f in env_value.split(",") if f.strip()}
|
||||
|
||||
def _is_verbose(self) -> bool:
|
||||
return os.getenv("ALWRITY_VERBOSE", "false").lower() == "true"
|
||||
|
||||
def _get_profile(self) -> str:
|
||||
"""Legacy method - returns primary profile."""
|
||||
enabled = self.get_enabled_features()
|
||||
if "all" in enabled:
|
||||
return "all"
|
||||
# Return first feature as profile for backwards compatibility
|
||||
return list(enabled)[0] if enabled else "all"
|
||||
|
||||
def _should_include_router(self, registry_entry: Dict[str, Any], enabled_features: set) -> bool:
|
||||
"""Check if router should be included based on enabled features."""
|
||||
required_features = registry_entry.get("features", set())
|
||||
|
||||
# If "all" is enabled, include everything
|
||||
if "all" in enabled_features:
|
||||
return True
|
||||
|
||||
# If no required features specified, include by default
|
||||
if not required_features:
|
||||
return True
|
||||
|
||||
# Check if any required feature is enabled
|
||||
return bool(required_features & enabled_features)
|
||||
|
||||
def _load_router_from_registry(self, registry_entry: Dict[str, Any]):
|
||||
module = import_module(registry_entry["module"])
|
||||
return getattr(module, registry_entry["attr"])
|
||||
|
||||
def include_router_safely(self, router, router_name: Optional[str] = None, include_kwargs: Optional[Dict[str, Any]] = None) -> bool:
|
||||
def include_router_safely(self, router, router_name: str = None) -> bool:
|
||||
"""Include a router safely with error handling."""
|
||||
verbose = self._is_verbose()
|
||||
router_name = router_name or getattr(router, 'prefix', 'unknown')
|
||||
verbose = os.getenv("ALWRITY_VERBOSE", "false").lower() == "true"
|
||||
|
||||
try:
|
||||
self.app.include_router(router, **(include_kwargs or {}))
|
||||
self.app.include_router(router)
|
||||
router_name = router_name or getattr(router, 'prefix', 'unknown')
|
||||
self.included_routers.append(router_name)
|
||||
if verbose:
|
||||
logger.info(f"✅ Router included successfully: {router_name}")
|
||||
@@ -149,98 +35,210 @@ class RouterManager:
|
||||
logger.warning(f"❌ Router inclusion failed: {router_name} - {e}")
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def _demo_release_mode_enabled() -> bool:
|
||||
"""Return True when demo-release safety mode is enabled."""
|
||||
return os.getenv("ALWRITY_DEMO_RELEASE", "false").lower() in {"1", "true", "yes", "on"}
|
||||
|
||||
def _include_registry_group(self, registry: List[Dict[str, Any]], group_name: str) -> bool:
|
||||
verbose = self._is_verbose()
|
||||
enabled_features = self.get_enabled_features()
|
||||
|
||||
def include_core_routers(self) -> bool:
|
||||
"""Include core application routers."""
|
||||
# Import os locally to avoid UnboundLocalError if it's shadowed
|
||||
import os
|
||||
verbose = os.getenv("ALWRITY_VERBOSE", "false").lower() == "true"
|
||||
|
||||
try:
|
||||
if verbose:
|
||||
logger.info(f"Including {group_name} routers with features: {enabled_features}...")
|
||||
logger.info("Including core routers...")
|
||||
|
||||
# Component logic router
|
||||
from api.component_logic import router as component_logic_router
|
||||
self.include_router_safely(component_logic_router, "component_logic")
|
||||
|
||||
for entry in registry:
|
||||
if entry["name"] == "wix_test" and not self._should_include_wix_test_router():
|
||||
reason = "wix test routes disabled or running in production environment"
|
||||
self.skipped_routers.append({"name": entry["name"], "reason": reason})
|
||||
if verbose:
|
||||
logger.info(f"⏭️ Skipping {entry['name']}: {reason}")
|
||||
continue
|
||||
if not self._should_include_router(entry, enabled_features):
|
||||
reason = f"features {enabled_features} not matching {entry.get('features', set())}"
|
||||
self.skipped_routers.append({"name": entry["name"], "reason": reason})
|
||||
if verbose:
|
||||
logger.info(f"⏭️ Skipping {entry['name']}: {reason}")
|
||||
continue
|
||||
|
||||
try:
|
||||
router = self._load_router_from_registry(entry)
|
||||
self.include_router_safely(router, entry["name"], entry.get("include_kwargs"))
|
||||
except Exception as e:
|
||||
logger.warning(f"{entry['name']} router not mounted: {e}")
|
||||
# Subscription router
|
||||
from api.subscription import router as subscription_router
|
||||
self.include_router_safely(subscription_router, "subscription")
|
||||
|
||||
logger.info(f"✅ {group_name.capitalize()} routers processed for features: {enabled_features}")
|
||||
# Step 3 Research router (core onboarding functionality)
|
||||
from api.onboarding_utils.step3_routes import router as step3_research_router
|
||||
self.include_router_safely(step3_research_router, "step3_research")
|
||||
|
||||
# Step 4 Persona and Asset routers
|
||||
from api.onboarding_utils.step4_asset_routes import router as step4_asset_router
|
||||
self.include_router_safely(step4_asset_router, "step4_assets")
|
||||
|
||||
from api.onboarding_utils.step4_persona_routes_optimized import router as step4_persona_router
|
||||
self.include_router_safely(step4_persona_router, "step4_persona")
|
||||
|
||||
# GSC router
|
||||
from routers.gsc_auth import router as gsc_auth_router
|
||||
self.include_router_safely(gsc_auth_router, "gsc_auth")
|
||||
|
||||
# WordPress router
|
||||
from routers.wordpress_oauth import router as wordpress_oauth_router
|
||||
self.include_router_safely(wordpress_oauth_router, "wordpress_oauth")
|
||||
|
||||
# Bing Webmaster router
|
||||
from routers.bing_oauth import router as bing_oauth_router
|
||||
self.include_router_safely(bing_oauth_router, "bing_oauth")
|
||||
|
||||
# Bing Analytics router
|
||||
from routers.bing_analytics import router as bing_analytics_router
|
||||
self.include_router_safely(bing_analytics_router, "bing_analytics")
|
||||
|
||||
# Bing Analytics Storage router
|
||||
from routers.bing_analytics_storage import router as bing_analytics_storage_router
|
||||
self.include_router_safely(bing_analytics_storage_router, "bing_analytics_storage")
|
||||
|
||||
# SEO tools router
|
||||
from routers.seo_tools import router as seo_tools_router
|
||||
self.include_router_safely(seo_tools_router, "seo_tools")
|
||||
|
||||
# Facebook Writer router
|
||||
from api.facebook_writer.routers import facebook_router
|
||||
self.include_router_safely(facebook_router, "facebook_writer")
|
||||
|
||||
# LinkedIn routers
|
||||
from routers.linkedin import router as linkedin_router
|
||||
self.include_router_safely(linkedin_router, "linkedin")
|
||||
|
||||
from api.linkedin_image_generation import router as linkedin_image_router
|
||||
self.include_router_safely(linkedin_image_router, "linkedin_image")
|
||||
|
||||
# Brainstorm router
|
||||
from api.brainstorm import router as brainstorm_router
|
||||
self.include_router_safely(brainstorm_router, "brainstorm")
|
||||
|
||||
# Hallucination detector and writing assistant
|
||||
from api.hallucination_detector import router as hallucination_detector_router
|
||||
self.include_router_safely(hallucination_detector_router, "hallucination_detector")
|
||||
|
||||
from api.writing_assistant import router as writing_assistant_router
|
||||
self.include_router_safely(writing_assistant_router, "writing_assistant")
|
||||
|
||||
# Content planning and user data
|
||||
from api.content_planning.api.router import router as content_planning_router
|
||||
self.include_router_safely(content_planning_router, "content_planning")
|
||||
|
||||
from api.user_data import router as user_data_router
|
||||
self.include_router_safely(user_data_router, "user_data")
|
||||
|
||||
from api.user_environment import router as user_environment_router
|
||||
self.include_router_safely(user_environment_router, "user_environment")
|
||||
|
||||
# Strategy copilot
|
||||
from api.content_planning.strategy_copilot import router as strategy_copilot_router
|
||||
self.include_router_safely(strategy_copilot_router, "strategy_copilot")
|
||||
|
||||
# Error logging router
|
||||
from routers.error_logging import router as error_logging_router
|
||||
self.include_router_safely(error_logging_router, "error_logging")
|
||||
|
||||
# Frontend environment manager router
|
||||
from routers.frontend_env_manager import router as frontend_env_router
|
||||
self.include_router_safely(frontend_env_router, "frontend_env_manager")
|
||||
|
||||
# Platform analytics router
|
||||
try:
|
||||
from routers.platform_analytics import router as platform_analytics_router
|
||||
self.include_router_safely(platform_analytics_router, "platform_analytics")
|
||||
logger.info("✅ Platform analytics router included successfully")
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Failed to include platform analytics router: {e}")
|
||||
# Continue with other routers
|
||||
|
||||
# Bing insights router
|
||||
try:
|
||||
from routers.bing_insights import router as bing_insights_router
|
||||
self.include_router_safely(bing_insights_router, "bing_insights")
|
||||
logger.info("✅ Bing insights router included successfully")
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Failed to include Bing insights router: {e}")
|
||||
# Continue with other routers
|
||||
|
||||
# Background jobs router
|
||||
try:
|
||||
from routers.background_jobs import router as background_jobs_router
|
||||
self.include_router_safely(background_jobs_router, "background_jobs")
|
||||
logger.info("✅ Background jobs router included successfully")
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Failed to include Background jobs router: {e}")
|
||||
# Continue with other routers
|
||||
|
||||
logger.info("✅ Core routers included successfully")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Error including {group_name} routers: {e}")
|
||||
logger.error(f"❌ Error including core routers: {e}")
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def _should_include_wix_test_router() -> bool:
|
||||
environment = (os.getenv("ENVIRONMENT") or os.getenv("APP_ENV") or "development").strip().lower()
|
||||
is_production = environment in {"prod", "production"}
|
||||
wix_test_enabled = os.getenv("WIX_TEST_ROUTES_ENABLED", "false").lower() in {"1", "true", "yes", "on"}
|
||||
return wix_test_enabled and not is_production
|
||||
|
||||
def include_core_routers(self) -> bool:
|
||||
"""Include core application routers."""
|
||||
return self._include_registry_group(CORE_ROUTER_REGISTRY, "core")
|
||||
|
||||
def include_optional_routers(self) -> bool:
|
||||
"""Include optional routers with error handling."""
|
||||
return self._include_registry_group(OPTIONAL_ROUTER_REGISTRY, "optional")
|
||||
try:
|
||||
logger.info("Including optional routers...")
|
||||
|
||||
# AI Blog Writer router
|
||||
try:
|
||||
from api.blog_writer.router import router as blog_writer_router
|
||||
self.include_router_safely(blog_writer_router, "blog_writer")
|
||||
except Exception as e:
|
||||
logger.warning(f"AI Blog Writer router not mounted: {e}")
|
||||
|
||||
# Story Writer router
|
||||
try:
|
||||
from api.story_writer.router import router as story_writer_router
|
||||
self.include_router_safely(story_writer_router, "story_writer")
|
||||
except Exception as e:
|
||||
logger.warning(f"Story Writer router not mounted: {e}")
|
||||
|
||||
# Wix Integration router
|
||||
try:
|
||||
from api.wix_routes import router as wix_router
|
||||
self.include_router_safely(wix_router, "wix")
|
||||
except Exception as e:
|
||||
logger.warning(f"Wix Integration router not mounted: {e}")
|
||||
|
||||
# Blog Writer SEO Analysis router
|
||||
try:
|
||||
from api.blog_writer.seo_analysis import router as blog_seo_analysis_router
|
||||
self.include_router_safely(blog_seo_analysis_router, "blog_seo_analysis")
|
||||
except Exception as e:
|
||||
logger.warning(f"Blog Writer SEO Analysis router not mounted: {e}")
|
||||
|
||||
# Persona router
|
||||
try:
|
||||
from api.persona_routes import router as persona_router
|
||||
self.include_router_safely(persona_router, "persona")
|
||||
except Exception as e:
|
||||
logger.warning(f"Persona router not mounted: {e}")
|
||||
|
||||
# Video Studio router
|
||||
try:
|
||||
from api.video_studio.router import router as video_studio_router
|
||||
self.include_router_safely(video_studio_router, "video_studio")
|
||||
except Exception as e:
|
||||
logger.warning(f"Video Studio router not mounted: {e}")
|
||||
|
||||
# Stability AI routers
|
||||
try:
|
||||
from routers.stability import router as stability_router
|
||||
self.include_router_safely(stability_router, "stability")
|
||||
|
||||
from routers.stability_advanced import router as stability_advanced_router
|
||||
self.include_router_safely(stability_advanced_router, "stability_advanced")
|
||||
|
||||
from routers.stability_admin import router as stability_admin_router
|
||||
self.include_router_safely(stability_admin_router, "stability_admin")
|
||||
except Exception as e:
|
||||
logger.warning(f"Stability AI routers not mounted: {e}")
|
||||
|
||||
|
||||
logger.info("✅ Optional routers processed")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Error including optional routers: {e}")
|
||||
return False
|
||||
|
||||
def get_router_status(self) -> Dict[str, Any]:
|
||||
"""Get the status of router inclusion."""
|
||||
return {
|
||||
"active_profile": self._get_profile(),
|
||||
"included_routers": self.included_routers,
|
||||
"failed_routers": self.failed_routers,
|
||||
"skipped_routers": self.skipped_routers,
|
||||
"total_included": len(self.included_routers),
|
||||
"total_failed": len(self.failed_routers),
|
||||
"total_skipped": len(self.skipped_routers)
|
||||
}
|
||||
|
||||
def log_startup_summary(self) -> None:
|
||||
"""Log startup summary including profile, enabled routers, and skipped items."""
|
||||
profile = self._get_profile()
|
||||
|
||||
logger.info("=" * 60)
|
||||
logger.info("📋 STARTUP SUMMARY")
|
||||
logger.info(f" Active profile: {profile}")
|
||||
logger.info(f" Enabled routers ({len(self.included_routers)}): {', '.join(self.included_routers)}")
|
||||
if self.skipped_routers:
|
||||
logger.info(f" Skipped routers ({len(self.skipped_routers)}):")
|
||||
for s in self.skipped_routers:
|
||||
logger.info(f" - {s['name']}: {s['reason']}")
|
||||
if self.failed_routers:
|
||||
logger.warning(f" Failed routers ({len(self.failed_routers)}):")
|
||||
for f in self.failed_routers:
|
||||
logger.warning(f" - {f['name']}: {f['error']}")
|
||||
logger.info("=" * 60)
|
||||
|
||||
def get_feature_profile_status(self) -> Dict[str, Any]:
|
||||
"""Get feature profile status and enabled modules."""
|
||||
profile = self._get_profile()
|
||||
enabled_modules = OPTIONAL_MODULE_MATRIX.get(profile, OPTIONAL_MODULE_MATRIX.get("all", []))
|
||||
|
||||
return {
|
||||
"active_profile": profile,
|
||||
"enabled_modules": enabled_modules,
|
||||
"available_profiles": list(OPTIONAL_MODULE_MATRIX.keys())
|
||||
"total_failed": len(self.failed_routers)
|
||||
}
|
||||
|
||||
@@ -5,59 +5,50 @@ The onboarding endpoints are re-exported from a stable module
|
||||
`onboarding.py`.
|
||||
"""
|
||||
|
||||
import os
|
||||
from .onboarding_endpoints import (
|
||||
health_check,
|
||||
get_onboarding_status,
|
||||
get_onboarding_progress_full,
|
||||
get_step_data,
|
||||
complete_step,
|
||||
skip_step,
|
||||
validate_step_access,
|
||||
get_api_keys,
|
||||
save_api_key,
|
||||
validate_api_keys,
|
||||
start_onboarding,
|
||||
complete_onboarding,
|
||||
reset_onboarding,
|
||||
get_resume_info,
|
||||
get_onboarding_config,
|
||||
generate_writing_personas,
|
||||
generate_writing_personas_async,
|
||||
get_persona_task_status,
|
||||
assess_persona_quality,
|
||||
regenerate_persona,
|
||||
get_persona_generation_options
|
||||
)
|
||||
|
||||
# In feature-only modes, don't import heavy onboarding endpoints
|
||||
# They trigger heavy dependencies (exa_py, etc.)
|
||||
_is_full_mode = os.getenv("ALWRITY_ENABLED_FEATURES", "").strip().lower() in ("", "all")
|
||||
|
||||
if not _is_full_mode:
|
||||
__all__ = []
|
||||
else:
|
||||
from .onboarding_endpoints import (
|
||||
health_check,
|
||||
get_onboarding_status,
|
||||
get_onboarding_progress_full,
|
||||
get_step_data,
|
||||
complete_step,
|
||||
skip_step,
|
||||
validate_step_access,
|
||||
get_api_keys,
|
||||
save_api_key,
|
||||
validate_api_keys,
|
||||
start_onboarding,
|
||||
complete_onboarding,
|
||||
reset_onboarding,
|
||||
get_resume_info,
|
||||
get_onboarding_config,
|
||||
generate_writing_personas,
|
||||
generate_writing_personas_async,
|
||||
get_persona_task_status,
|
||||
assess_persona_quality,
|
||||
regenerate_persona,
|
||||
get_persona_generation_options
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
'health_check',
|
||||
'get_onboarding_status',
|
||||
'get_onboarding_progress_full',
|
||||
'get_step_data',
|
||||
'complete_step',
|
||||
'skip_step',
|
||||
'validate_step_access',
|
||||
'get_api_keys',
|
||||
'save_api_key',
|
||||
'validate_api_keys',
|
||||
'start_onboarding',
|
||||
'complete_onboarding',
|
||||
'reset_onboarding',
|
||||
'get_resume_info',
|
||||
'get_onboarding_config',
|
||||
'generate_writing_personas',
|
||||
'generate_writing_personas_async',
|
||||
'get_persona_task_status',
|
||||
'assess_persona_quality',
|
||||
'regenerate_persona',
|
||||
'get_persona_generation_options'
|
||||
]
|
||||
__all__ = [
|
||||
'health_check',
|
||||
'get_onboarding_status',
|
||||
'get_onboarding_progress_full',
|
||||
'get_step_data',
|
||||
'complete_step',
|
||||
'skip_step',
|
||||
'validate_step_access',
|
||||
'get_api_keys',
|
||||
'save_api_key',
|
||||
'validate_api_keys',
|
||||
'start_onboarding',
|
||||
'complete_onboarding',
|
||||
'reset_onboarding',
|
||||
'get_resume_info',
|
||||
'get_onboarding_config',
|
||||
'generate_writing_personas',
|
||||
'generate_writing_personas_async',
|
||||
'get_persona_task_status',
|
||||
'assess_persona_quality',
|
||||
'regenerate_persona',
|
||||
'get_persona_generation_options'
|
||||
]
|
||||
@@ -1,140 +1,52 @@
|
||||
"""
|
||||
Assets Serving Router
|
||||
|
||||
Serves user-uploaded assets (avatars, voice samples) from workspace storage.
|
||||
Uses authenticated or query-token access for security.
|
||||
Audio MIME types are set correctly based on file extension so browsers
|
||||
can play voice clone previews without NotSupportedError.
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from fastapi.responses import FileResponse
|
||||
import os
|
||||
from pathlib import Path
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from fastapi.responses import FileResponse
|
||||
from loguru import logger
|
||||
from typing import Dict, Any
|
||||
|
||||
from middleware.auth_middleware import get_current_user_with_query_token
|
||||
from api.story_writer.utils.auth import require_authenticated_user
|
||||
from utils.storage_paths import get_repo_root, sanitize_user_id
|
||||
from services.database import WORKSPACE_DIR, get_user_db_path
|
||||
|
||||
router = APIRouter(prefix="/api/assets", tags=["Assets Serving"])
|
||||
|
||||
MIME_MAP = {
|
||||
".wav": "audio/wav",
|
||||
".mp3": "audio/mpeg",
|
||||
".ogg": "audio/ogg",
|
||||
".opus": "audio/opus",
|
||||
".webm": "audio/webm",
|
||||
".m4a": "audio/mp4",
|
||||
".aac": "audio/aac",
|
||||
".flac": "audio/flac",
|
||||
".png": "image/png",
|
||||
".jpg": "image/jpeg",
|
||||
".jpeg": "image/jpeg",
|
||||
".gif": "image/gif",
|
||||
".webp": "image/webp",
|
||||
".svg": "image/svg+xml",
|
||||
}
|
||||
|
||||
|
||||
def _verify_ownership(url_user_id: str, current_user: Dict[str, Any]) -> str:
|
||||
"""Verify the URL user_id matches the authenticated user. Returns sanitized user_id."""
|
||||
raw = current_user.get("id") or current_user.get("user_id") or current_user.get("clerk_user_id")
|
||||
authed_id = str(raw) if raw else ""
|
||||
if not authed_id or sanitize_user_id(url_user_id) != sanitize_user_id(authed_id):
|
||||
raise HTTPException(status_code=403, detail="Access denied: user mismatch")
|
||||
return sanitize_user_id(url_user_id)
|
||||
|
||||
|
||||
def _resolve_asset_path(user_id: str, category: str, filename: str) -> Path:
|
||||
"""Resolve asset path in user workspace with path-traversal protection."""
|
||||
safe_user_id = sanitize_user_id(user_id)
|
||||
repo_root = get_repo_root()
|
||||
|
||||
file_path = (repo_root / "workspace" / f"workspace_{safe_user_id}" / "assets" / category / filename).resolve()
|
||||
|
||||
workspace_dir = (repo_root / "workspace" / f"workspace_{safe_user_id}").resolve()
|
||||
if not str(file_path).startswith(str(workspace_dir)):
|
||||
raise HTTPException(status_code=403, detail="Access denied")
|
||||
|
||||
return file_path
|
||||
|
||||
|
||||
def _get_media_type(filename: str) -> str:
|
||||
"""Determine MIME type from file extension, with fallback."""
|
||||
ext = Path(filename).suffix.lower()
|
||||
return MIME_MAP.get(ext, "application/octet-stream")
|
||||
|
||||
|
||||
@router.get("/{user_id}/avatars/{filename}")
|
||||
async def serve_avatar(
|
||||
user_id: str,
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user_with_query_token),
|
||||
):
|
||||
"""Serve avatar images. Supports auth via Authorization header or ?token= query param.
|
||||
Falls back to images/ directory for backward compatibility with old asset library entries."""
|
||||
require_authenticated_user(current_user)
|
||||
_verify_ownership(user_id, current_user)
|
||||
|
||||
async def serve_avatar(user_id: str, filename: str):
|
||||
"""
|
||||
Serve avatar images directly.
|
||||
Public endpoint relying on unguessable filenames.
|
||||
"""
|
||||
# Sanitize user_id (simple check to prevent directory traversal)
|
||||
safe_user_id = "".join(c for c in user_id if c.isalnum() or c in ('-', '_'))
|
||||
if safe_user_id != user_id:
|
||||
raise HTTPException(status_code=400, detail="Invalid user ID")
|
||||
|
||||
# Sanitize filename
|
||||
safe_filename = os.path.basename(filename)
|
||||
file_path = _resolve_asset_path(user_id, "avatars", safe_filename)
|
||||
|
||||
|
||||
# Construct path
|
||||
# workspace/workspace_{user_id}/assets/avatars/{filename}
|
||||
file_path = Path(WORKSPACE_DIR) / f"workspace_{safe_user_id}" / "assets" / "avatars" / safe_filename
|
||||
|
||||
if not file_path.exists():
|
||||
alt_path = _resolve_asset_path(user_id, "images", safe_filename)
|
||||
if alt_path.exists():
|
||||
media_type = _get_media_type(safe_filename)
|
||||
return FileResponse(alt_path, media_type=media_type)
|
||||
raise HTTPException(status_code=404, detail="Asset not found")
|
||||
|
||||
media_type = _get_media_type(safe_filename)
|
||||
return FileResponse(file_path, media_type=media_type)
|
||||
|
||||
|
||||
return FileResponse(file_path)
|
||||
|
||||
@router.get("/{user_id}/voice_samples/{filename}")
|
||||
async def serve_voice_sample(
|
||||
user_id: str,
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user_with_query_token),
|
||||
):
|
||||
"""Serve voice sample audio files.
|
||||
|
||||
Supports auth via Authorization header or ?token= query param.
|
||||
The ?token= param is essential for <audio> elements and new Audio()
|
||||
which cannot send Authorization headers.
|
||||
async def serve_voice_sample(user_id: str, filename: str):
|
||||
"""
|
||||
require_authenticated_user(current_user)
|
||||
_verify_ownership(user_id, current_user)
|
||||
|
||||
Serve voice sample audio files directly.
|
||||
"""
|
||||
# Sanitize user_id
|
||||
safe_user_id = "".join(c for c in user_id if c.isalnum() or c in ('-', '_'))
|
||||
if safe_user_id != user_id:
|
||||
raise HTTPException(status_code=400, detail="Invalid user ID")
|
||||
|
||||
# Sanitize filename
|
||||
safe_filename = os.path.basename(filename)
|
||||
file_path = _resolve_asset_path(user_id, "voice_samples", safe_filename)
|
||||
|
||||
if not file_path.exists():
|
||||
logger.info(f"[Assets] Voice sample not found: {file_path}")
|
||||
raise HTTPException(status_code=404, detail="Asset not found")
|
||||
|
||||
media_type = _get_media_type(safe_filename)
|
||||
file_size = file_path.stat().st_size
|
||||
logger.warning(f"[Assets] Serving voice sample: {safe_filename} ({media_type}, {file_size} bytes)")
|
||||
return FileResponse(file_path, media_type=media_type)
|
||||
|
||||
|
||||
@router.get("/{user_id}/images/{filename}")
|
||||
async def serve_image(
|
||||
user_id: str,
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user_with_query_token),
|
||||
):
|
||||
"""Serve generated/uploaded images. Supports auth via Authorization header or ?token= query param."""
|
||||
require_authenticated_user(current_user)
|
||||
_verify_ownership(user_id, current_user)
|
||||
|
||||
safe_filename = os.path.basename(filename)
|
||||
file_path = _resolve_asset_path(user_id, "images", safe_filename)
|
||||
|
||||
|
||||
# Construct path
|
||||
# workspace/workspace_{user_id}/assets/voice_samples/{filename}
|
||||
file_path = Path(WORKSPACE_DIR) / f"workspace_{safe_user_id}" / "assets" / "voice_samples" / safe_filename
|
||||
|
||||
if not file_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Asset not found")
|
||||
|
||||
media_type = _get_media_type(safe_filename)
|
||||
return FileResponse(file_path, media_type=media_type)
|
||||
|
||||
return FileResponse(file_path)
|
||||
|
||||
@@ -9,12 +9,10 @@ from fastapi import APIRouter, HTTPException, Depends
|
||||
from typing import Any, Dict, List, Optional
|
||||
from pydantic import BaseModel, Field
|
||||
from loguru import logger
|
||||
from datetime import datetime
|
||||
from middleware.auth_middleware import get_current_user
|
||||
from sqlalchemy.orm import Session
|
||||
from services.database import get_db as get_db_dependency
|
||||
from utils.text_asset_tracker import save_and_track_text_content
|
||||
from models.content_asset_models import AssetType, AssetSource
|
||||
|
||||
from models.blog_models import (
|
||||
BlogResearchRequest,
|
||||
@@ -38,7 +36,6 @@ from models.blog_models import (
|
||||
from services.blog_writer.blog_service import BlogWriterService
|
||||
from services.blog_writer.seo.blog_seo_recommendation_applier import BlogSEORecommendationApplier
|
||||
from services.llm_providers.main_text_generation import llm_text_gen
|
||||
from services.content_asset_service import ContentAssetService
|
||||
from .task_manager import task_manager
|
||||
from .cache_manager import cache_manager
|
||||
from models.blog_models import MediumBlogGenerateRequest
|
||||
@@ -66,12 +63,10 @@ class RecommendationItem(BaseModel):
|
||||
|
||||
class SEOApplyRecommendationsRequest(BaseModel):
|
||||
title: str = Field(..., description="Current blog title")
|
||||
introduction: str | None = Field(default=None, description="Current blog introduction text")
|
||||
sections: List[Dict[str, Any]] = Field(..., description="Array of sections with id, heading, content")
|
||||
outline: List[Dict[str, Any]] = Field(default_factory=list, description="Outline structure for context")
|
||||
research: Dict[str, Any] = Field(default_factory=dict, description="Research data used for the blog")
|
||||
recommendations: List[RecommendationItem] = Field(..., description="Actionable recommendations to apply")
|
||||
competitive_advantage: str | None = Field(default=None, description="Selected competitive advantage for emphasis")
|
||||
persona: Dict[str, Any] = Field(default_factory=dict, description="Persona settings if available")
|
||||
tone: str | None = Field(default=None, description="Desired tone override")
|
||||
audience: str | None = Field(default=None, description="Target audience override")
|
||||
@@ -124,7 +119,7 @@ async def section_originality_tools(
|
||||
raise HTTPException(status_code=401, detail="User ID not found in authentication token")
|
||||
|
||||
from services.intelligence.sif_integration import SIFIntegrationService
|
||||
from services.intelligence.agents.specialized import ContentGuardianAgent
|
||||
from services.intelligence.sif_agents import ContentGuardianAgent
|
||||
|
||||
sif_service = SIFIntegrationService(user_id)
|
||||
intelligence = sif_service.intelligence_service
|
||||
@@ -689,11 +684,9 @@ async def get_section_continuity(section_id: str) -> Dict[str, Any]:
|
||||
|
||||
|
||||
@router.post("/flow-analysis/basic")
|
||||
async def analyze_flow_basic(request: Dict[str, Any], current_user: Dict[str, Any] = Depends(get_current_user)) -> Dict[str, Any]:
|
||||
async def analyze_flow_basic(request: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze flow metrics for entire blog using single AI call (cost-effective)."""
|
||||
try:
|
||||
user_id = str(current_user.get('id', '')) if current_user else None
|
||||
request['user_id'] = user_id
|
||||
result = await service.analyze_flow_basic(request)
|
||||
return result
|
||||
except Exception as e:
|
||||
@@ -702,11 +695,9 @@ async def analyze_flow_basic(request: Dict[str, Any], current_user: Dict[str, An
|
||||
|
||||
|
||||
@router.post("/flow-analysis/advanced")
|
||||
async def analyze_flow_advanced(request: Dict[str, Any], current_user: Dict[str, Any] = Depends(get_current_user)) -> Dict[str, Any]:
|
||||
async def analyze_flow_advanced(request: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Analyze flow metrics for each section individually (detailed but expensive)."""
|
||||
try:
|
||||
user_id = str(current_user.get('id', '')) if current_user else None
|
||||
request['user_id'] = user_id
|
||||
result = await service.analyze_flow_advanced(request)
|
||||
return result
|
||||
except Exception as e:
|
||||
@@ -813,12 +804,9 @@ async def seo_metadata(
|
||||
|
||||
|
||||
# Publishing Endpoints
|
||||
# NOTE: Real publishing bypasses this stub. Frontend calls platform-specific
|
||||
# endpoints directly: /api/wix/publish and /api/wordpress/publish.
|
||||
# This endpoint is kept as a placeholder for the future unified publish flow.
|
||||
@router.post("/publish", response_model=BlogPublishResponse)
|
||||
async def publish(request: BlogPublishRequest) -> BlogPublishResponse:
|
||||
"""Publish the blog post to the specified platform. [STUB - see note above]"""
|
||||
"""Publish the blog post to the specified platform."""
|
||||
try:
|
||||
return await service.publish(request)
|
||||
except Exception as e:
|
||||
@@ -1207,364 +1195,3 @@ async def generate_introductions(
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to generate introductions: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
# ---------------------------
|
||||
# Save Complete Blog Asset
|
||||
# ---------------------------
|
||||
|
||||
|
||||
class SaveCompleteBlogAssetRequest(BaseModel):
|
||||
title: str
|
||||
content: str
|
||||
platform: Optional[str] = None
|
||||
post_url: Optional[str] = None
|
||||
post_id: Optional[str] = None
|
||||
seo_title: Optional[str] = None
|
||||
meta_description: Optional[str] = None
|
||||
focus_keyword: Optional[str] = None
|
||||
tags: List[str] = Field(default_factory=list)
|
||||
categories: List[str] = Field(default_factory=list)
|
||||
|
||||
|
||||
@router.post("/save-complete-asset")
|
||||
async def save_complete_blog_asset(
|
||||
request: SaveCompleteBlogAssetRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> Dict[str, Any]:
|
||||
"""Save the complete blog content as a single asset in the asset library."""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = str(current_user.get('id', ''))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID in authentication token")
|
||||
|
||||
full_content = f"# {request.title}\n\n{request.content}"
|
||||
|
||||
asset_metadata = {
|
||||
"status": "published",
|
||||
"focus_keyword": request.focus_keyword,
|
||||
"categories": request.categories,
|
||||
"word_count": len(full_content.split()),
|
||||
}
|
||||
if request.platform:
|
||||
asset_metadata["platform"] = request.platform
|
||||
if request.post_url:
|
||||
asset_metadata["post_url"] = request.post_url
|
||||
if request.post_id:
|
||||
asset_metadata["post_id"] = request.post_id
|
||||
|
||||
asset_id = save_and_track_text_content(
|
||||
db=db,
|
||||
user_id=user_id,
|
||||
content=full_content,
|
||||
source_module="blog_writer",
|
||||
title=request.title[:100],
|
||||
description=request.meta_description or f"Complete published blog post: {request.title}",
|
||||
prompt=f"SEO Title: {request.seo_title or request.title}\nFocus Keyword: {request.focus_keyword or ''}",
|
||||
tags=["blog", "published"] + [t for t in (request.tags or []) if t],
|
||||
asset_metadata=asset_metadata,
|
||||
subdirectory="published",
|
||||
file_extension=".md"
|
||||
)
|
||||
|
||||
if asset_id:
|
||||
logger.info(f"✅ Complete blog asset saved to library: ID={asset_id}")
|
||||
return {"success": True, "asset_id": asset_id}
|
||||
else:
|
||||
logger.warning("save_and_track_text_content returned None for published blog")
|
||||
return {"success": False, "error": "Failed to save blog asset"}
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to save complete blog asset: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/publish-history")
|
||||
async def get_publish_history(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
limit: int = 50,
|
||||
offset: int = 0,
|
||||
) -> Dict[str, Any]:
|
||||
"""Get publish history for the current user from the asset library."""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = str(current_user.get('id', ''))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID in authentication token")
|
||||
|
||||
svc = ContentAssetService(db)
|
||||
assets, total = svc.get_user_assets(
|
||||
user_id=user_id,
|
||||
tags=["published"],
|
||||
source_module=AssetSource.BLOG_WRITER,
|
||||
sort_by="created_at",
|
||||
sort_order="desc",
|
||||
limit=limit,
|
||||
offset=offset,
|
||||
)
|
||||
|
||||
entries = []
|
||||
for a in assets:
|
||||
meta = a.asset_metadata or {}
|
||||
entries.append({
|
||||
"asset_id": a.id,
|
||||
"title": a.title,
|
||||
"platform": meta.get("platform", "unknown"),
|
||||
"post_url": meta.get("post_url"),
|
||||
"post_id": meta.get("post_id"),
|
||||
"word_count": meta.get("word_count", 0),
|
||||
"focus_keyword": meta.get("focus_keyword"),
|
||||
"categories": meta.get("categories", []),
|
||||
"published_at": a.created_at.isoformat() if a.created_at else None,
|
||||
})
|
||||
|
||||
return {"success": True, "entries": entries, "total": total}
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get publish history: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
# ---------------------------------------
|
||||
# Blog Asset API (phase-by-phase saving via ContentAsset)
|
||||
# ---------------------------------------
|
||||
|
||||
|
||||
class BlogAssetCreateRequest(BaseModel):
|
||||
research_keywords: str = Field(..., max_length=2000, description="Research keywords / topic")
|
||||
topic: Optional[str] = Field(default=None, max_length=500)
|
||||
word_count_target: Optional[int] = Field(default=None, ge=100, le=20000)
|
||||
|
||||
|
||||
class BlogAssetUpdateRequest(BaseModel):
|
||||
phase: Optional[str] = Field(default=None, pattern=r"^(research|outline|content|seo|publish)$")
|
||||
topic: Optional[str] = Field(default=None, max_length=500)
|
||||
selected_title: Optional[str] = Field(default=None, max_length=500)
|
||||
word_count_target: Optional[int] = Field(default=None, ge=100, le=20000)
|
||||
research_data: Optional[Dict[str, Any]] = None
|
||||
outline_data: Optional[Dict[str, Any]] = None
|
||||
content_data: Optional[Dict[str, Any]] = None
|
||||
seo_data: Optional[Dict[str, Any]] = None
|
||||
publish_data: Optional[Dict[str, Any]] = None
|
||||
|
||||
|
||||
def _normalize_keywords(kw: str) -> str:
|
||||
"""Normalize keywords for duplicate comparison."""
|
||||
return " ".join(sorted(kw.lower().split()))
|
||||
|
||||
|
||||
@router.post("/asset", response_model=Dict[str, Any])
|
||||
async def create_blog_asset(
|
||||
request: BlogAssetCreateRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Create a blog ContentAsset on research start.
|
||||
Returns existing asset if duplicate keywords found (unique topics only).
|
||||
"""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
user_id = str(current_user.get("id", ""))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID")
|
||||
|
||||
svc = ContentAssetService(db)
|
||||
normalized_kw = _normalize_keywords(request.research_keywords)
|
||||
|
||||
# Duplicate check — search existing blog assets for matching keywords
|
||||
existing_assets, _ = svc.get_user_assets(
|
||||
user_id=user_id,
|
||||
source_module=AssetSource.BLOG_WRITER,
|
||||
asset_type=AssetType.TEXT,
|
||||
limit=100,
|
||||
)
|
||||
for asset in existing_assets:
|
||||
meta = asset.asset_metadata or {}
|
||||
if meta.get("normalized_keywords") == normalized_kw:
|
||||
logger.info(f"Duplicate blog asset found: {asset.id}, returning existing")
|
||||
return {
|
||||
"success": True,
|
||||
"asset": _asset_to_response(asset),
|
||||
"existing": True,
|
||||
}
|
||||
|
||||
# Create new ContentAsset for this blog
|
||||
title = request.topic or request.research_keywords[:200]
|
||||
asset_metadata = {
|
||||
"phase": "research",
|
||||
"research_keywords": request.research_keywords,
|
||||
"normalized_keywords": normalized_kw,
|
||||
"word_count_target": request.word_count_target,
|
||||
"topic": request.topic,
|
||||
"research_data": None,
|
||||
"outline_data": None,
|
||||
"content_data": None,
|
||||
"seo_data": None,
|
||||
"publish_data": None,
|
||||
}
|
||||
asset = svc.create_asset(
|
||||
user_id=user_id,
|
||||
asset_type=AssetType.TEXT,
|
||||
source_module=AssetSource.BLOG_WRITER,
|
||||
filename=f"blog_{int(datetime.utcnow().timestamp())}.md",
|
||||
file_url=f"/api/blog/content/pending",
|
||||
title=title,
|
||||
description=f"Blog: {title}",
|
||||
tags=["blog", "research"],
|
||||
asset_metadata=asset_metadata,
|
||||
)
|
||||
logger.info(f"✅ Created blog asset: {asset.id}")
|
||||
return {
|
||||
"success": True,
|
||||
"asset": _asset_to_response(asset),
|
||||
"existing": False,
|
||||
}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create blog asset: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.put("/asset/{asset_id}", response_model=Dict[str, Any])
|
||||
async def update_blog_asset(
|
||||
asset_id: int,
|
||||
request: BlogAssetUpdateRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""Update a blog asset's phase, metadata, and tags."""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
user_id = str(current_user.get("id", ""))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID")
|
||||
|
||||
svc = ContentAssetService(db)
|
||||
asset = svc.get_asset_by_id(asset_id, user_id)
|
||||
if not asset:
|
||||
raise HTTPException(status_code=404, detail="Blog asset not found")
|
||||
|
||||
meta = dict(asset.asset_metadata or {})
|
||||
tags = list(asset.tags or [])
|
||||
|
||||
if request.phase is not None:
|
||||
meta["phase"] = request.phase
|
||||
# Update tags to reflect phase
|
||||
new_tags = [t for t in tags if t not in ("research", "outline", "content", "seo", "publish")]
|
||||
new_tags.append(request.phase)
|
||||
if "blog" not in new_tags:
|
||||
new_tags.append("blog")
|
||||
tags = new_tags
|
||||
|
||||
if request.topic is not None:
|
||||
meta["topic"] = request.topic
|
||||
if request.selected_title is not None:
|
||||
meta["selected_title"] = request.selected_title
|
||||
if request.word_count_target is not None:
|
||||
meta["word_count_target"] = request.word_count_target
|
||||
|
||||
for field in ("research_data", "outline_data", "content_data", "seo_data", "publish_data"):
|
||||
val = getattr(request, field, None)
|
||||
if val is not None:
|
||||
meta[field] = val
|
||||
|
||||
# Prefer seo_title from publish_data, then selected_title, then topic, then existing title
|
||||
publish_data = meta.get("publish_data") or {}
|
||||
if isinstance(publish_data, dict) and publish_data.get("seo_title"):
|
||||
new_title = publish_data["seo_title"]
|
||||
elif meta.get("selected_title"):
|
||||
new_title = meta["selected_title"]
|
||||
elif meta.get("topic"):
|
||||
new_title = meta["topic"]
|
||||
else:
|
||||
new_title = asset.title or "Blog Post"
|
||||
|
||||
updated = svc.update_asset(
|
||||
asset_id=asset_id,
|
||||
user_id=user_id,
|
||||
title=new_title[:500],
|
||||
tags=tags,
|
||||
asset_metadata=meta,
|
||||
)
|
||||
if not updated:
|
||||
raise HTTPException(status_code=500, detail="Failed to update asset")
|
||||
|
||||
logger.info(f"✅ Updated blog asset {asset_id}: phase={meta.get('phase')}")
|
||||
return {"success": True, "asset": _asset_to_response(updated)}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to update blog asset {asset_id}: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/asset/{asset_id}", response_model=Dict[str, Any])
|
||||
async def get_blog_asset(
|
||||
asset_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""Get a blog asset with all phase data."""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
user_id = str(current_user.get("id", ""))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID")
|
||||
|
||||
svc = ContentAssetService(db)
|
||||
asset = svc.get_asset_by_id(asset_id, user_id)
|
||||
if not asset:
|
||||
raise HTTPException(status_code=404, detail="Blog asset not found")
|
||||
|
||||
return {"success": True, "asset": _asset_to_response(asset, full=True)}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to get blog asset {asset_id}: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
def _asset_to_response(asset: Any, full: bool = False) -> Dict[str, Any]:
|
||||
"""Convert a ContentAsset to a blog asset response dict."""
|
||||
meta = asset.asset_metadata or {}
|
||||
resp: Dict[str, Any] = {
|
||||
"id": asset.id,
|
||||
"title": asset.title,
|
||||
"description": asset.description,
|
||||
"tags": asset.tags or [],
|
||||
"phase": meta.get("phase", "research"),
|
||||
"research_keywords": meta.get("research_keywords"),
|
||||
"topic": meta.get("topic"),
|
||||
"selected_title": meta.get("selected_title"),
|
||||
"word_count_target": meta.get("word_count_target"),
|
||||
"has_research": meta.get("research_data") is not None,
|
||||
"has_outline": meta.get("outline_data") is not None,
|
||||
"has_content": meta.get("content_data") is not None,
|
||||
"has_seo": meta.get("seo_data") is not None,
|
||||
"has_publish": meta.get("publish_data") is not None,
|
||||
"created_at": asset.created_at.isoformat() if asset.created_at else None,
|
||||
"updated_at": asset.updated_at.isoformat() if asset.updated_at else None,
|
||||
}
|
||||
if full:
|
||||
resp["research_data"] = meta.get("research_data")
|
||||
resp["outline_data"] = meta.get("outline_data")
|
||||
resp["content_data"] = meta.get("content_data")
|
||||
resp["seo_data"] = meta.get("seo_data")
|
||||
resp["publish_data"] = meta.get("publish_data")
|
||||
return resp
|
||||
|
||||
@@ -28,8 +28,6 @@ class SEOAnalysisRequest(BaseModel):
|
||||
blog_content: str
|
||||
blog_title: Optional[str] = None
|
||||
research_data: Dict[str, Any]
|
||||
outline: Optional[List[Dict[str, Any]]] = None
|
||||
competitive_advantage: Optional[str] = None
|
||||
user_id: Optional[str] = None
|
||||
session_id: Optional[str] = None
|
||||
|
||||
@@ -111,9 +109,7 @@ async def analyze_blog_seo(
|
||||
blog_content=request.blog_content,
|
||||
research_data=request.research_data,
|
||||
blog_title=request.blog_title,
|
||||
user_id=user_id,
|
||||
outline=request.outline,
|
||||
competitive_advantage=request.competitive_advantage,
|
||||
user_id=user_id
|
||||
)
|
||||
|
||||
# Check for errors
|
||||
|
||||
@@ -13,7 +13,7 @@ from typing import Any, Dict, List
|
||||
from fastapi import HTTPException
|
||||
from loguru import logger
|
||||
from sqlalchemy.orm import Session
|
||||
from services.database import get_session_for_user
|
||||
from services.database import SessionLocal, get_session_for_user
|
||||
|
||||
from models.blog_models import (
|
||||
BlogResearchRequest,
|
||||
@@ -256,8 +256,7 @@ class TaskManager:
|
||||
self.task_storage[task_id]["status"] = "running"
|
||||
self.task_storage[task_id]["progress_messages"] = []
|
||||
|
||||
await self.update_progress(task_id, "📝 Alwrity is preparing your blog content — this usually takes 20–40 seconds.")
|
||||
await self.update_progress(task_id, "📦 Packaging your outline sections and research data...")
|
||||
await self.update_progress(task_id, "📦 Packaging outline and metadata...")
|
||||
|
||||
# Basic guard: respect global target words
|
||||
total_target = int(request.globalTargetWords or 1000)
|
||||
@@ -265,7 +264,7 @@ class TaskManager:
|
||||
raise ValueError("Global target words exceed 1000; medium generation not allowed")
|
||||
|
||||
# Create a sync session for asset saving
|
||||
db_session = get_session_for_user(user_id)
|
||||
db_session = SessionLocal()
|
||||
try:
|
||||
result: MediumBlogGenerateResult = await self.service.generate_medium_blog_with_progress(
|
||||
request,
|
||||
@@ -282,22 +281,16 @@ class TaskManager:
|
||||
# Check if result came from cache
|
||||
cache_hit = getattr(result, 'cache_hit', False)
|
||||
if cache_hit:
|
||||
await self.update_progress(task_id, "⚡ Found existing content in cache — no need to regenerate!")
|
||||
await self.update_progress(task_id, "⚡ Found cached content - loading instantly!")
|
||||
else:
|
||||
await self.update_progress(task_id, "🧠 AI is writing each section with research-backed insights and natural flow...")
|
||||
await self.update_progress(task_id, "✨ Polishing content — improving structure, readability, and transitions...")
|
||||
await self.update_progress(task_id, "🤖 Generated fresh content with AI...")
|
||||
await self.update_progress(task_id, "✨ Post-processing and assembling sections...")
|
||||
|
||||
# Mark completed
|
||||
self.task_storage[task_id]["status"] = "completed"
|
||||
self.task_storage[task_id]["result"] = result.dict()
|
||||
section_count = len(result.sections)
|
||||
total_words = sum(getattr(s, 'wordCount', 0) or 0 for s in result.sections)
|
||||
await self.update_progress(
|
||||
task_id,
|
||||
f"✅ Content generation complete! {section_count} sections written ({total_words} words). "
|
||||
"Next up: SEO Analysis to optimize your blog for search engines."
|
||||
)
|
||||
|
||||
await self.update_progress(task_id, f"✅ Generated {len(result.sections)} sections successfully.")
|
||||
|
||||
# Note: Blog content tracking is handled in the status endpoint
|
||||
# to ensure we have proper database session and user context
|
||||
|
||||
@@ -333,7 +326,6 @@ class TaskManager:
|
||||
await self.update_progress(task_id, f"❌ Medium generation failed: {str(e)}")
|
||||
self.task_storage[task_id]["status"] = "failed"
|
||||
self.task_storage[task_id]["error"] = str(e)
|
||||
self.task_storage[task_id]["error_data"] = {"error_message": str(e), "error_type": type(e).__name__}
|
||||
|
||||
|
||||
# Global task manager instance
|
||||
|
||||
@@ -1,192 +0,0 @@
|
||||
"""
|
||||
Chart API — Shared chart generation endpoints for Blog Writer, Podcast Maker, etc.
|
||||
|
||||
Two modes:
|
||||
1. Explicit: POST /api/charts/generate with { chart_type, chart_data, title }
|
||||
2. AI-driven: POST /api/charts/generate with { text } → LLM infers chart_type + data
|
||||
|
||||
Both return { preview_url, chart_id, chart_type?, chart_data?, title? }
|
||||
"""
|
||||
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from fastapi.responses import FileResponse
|
||||
from pydantic import BaseModel, Field
|
||||
from loguru import logger
|
||||
|
||||
from middleware.auth_middleware import get_current_user, get_current_user_with_query_token
|
||||
from api.story_writer.utils.auth import require_authenticated_user
|
||||
from services.chart_service import get_chart_service, VALID_CHART_TYPES
|
||||
|
||||
|
||||
router = APIRouter(prefix="/api/charts", tags=["Charts"])
|
||||
|
||||
|
||||
class ChartGenerateRequest(BaseModel):
|
||||
"""Request for chart generation.
|
||||
|
||||
Provide either:
|
||||
- chart_type + chart_data (explicit mode), OR
|
||||
- text (AI inference mode — LLM determines chart_type + data)
|
||||
"""
|
||||
chart_data: Optional[Dict[str, Any]] = Field(
|
||||
default=None,
|
||||
description="Chart data dict (labels, values, before/after, etc.)"
|
||||
)
|
||||
chart_type: Optional[str] = Field(
|
||||
default=None,
|
||||
description=f"Chart type: {', '.join(VALID_CHART_TYPES)}"
|
||||
)
|
||||
title: str = Field(default="", description="Chart title")
|
||||
subtitle: Optional[str] = Field(default="", description="Optional subtitle")
|
||||
text: Optional[str] = Field(
|
||||
default=None,
|
||||
description="Text to infer chart from (AI mode). Mutually exclusive with chart_type+chart_data."
|
||||
)
|
||||
section_heading: Optional[str] = Field(
|
||||
default=None,
|
||||
description="Blog section heading for context (AI mode with research)"
|
||||
)
|
||||
section_key_points: Optional[list] = Field(
|
||||
default=None,
|
||||
description="Key points from the section (AI mode with research)"
|
||||
)
|
||||
|
||||
|
||||
class ChartGenerateResponse(BaseModel):
|
||||
"""Response for chart generation."""
|
||||
preview_url: str = ""
|
||||
chart_id: str = ""
|
||||
chart_type: Optional[str] = None
|
||||
chart_data: Optional[Dict[str, Any]] = None
|
||||
title: Optional[str] = None
|
||||
warnings: list = Field(default_factory=list, description="Pipeline warnings (e.g. Exa search failures)")
|
||||
|
||||
|
||||
@router.post("/generate", response_model=ChartGenerateResponse)
|
||||
async def generate_chart(
|
||||
request: ChartGenerateRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Generate a chart PNG preview.
|
||||
|
||||
Two modes:
|
||||
1. Explicit: Provide chart_type + chart_data
|
||||
2. AI-driven: Provide text, and the LLM infers chart_type + chart_data
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
chart_svc = get_chart_service(user_id=user_id)
|
||||
|
||||
if request.text and not request.chart_type:
|
||||
# AI inference mode
|
||||
logger.info(f"[Charts] AI inference mode for user {user_id}, text length={len(request.text)}")
|
||||
result = await chart_svc.generate_chart_from_text(
|
||||
text=request.text,
|
||||
user_id=user_id,
|
||||
section_heading=request.section_heading,
|
||||
section_key_points=request.section_key_points,
|
||||
)
|
||||
|
||||
if not result.get("path"):
|
||||
raise HTTPException(status_code=500, detail="Chart generation failed")
|
||||
|
||||
chart_id = result["chart_id"]
|
||||
filename = result.get("filename", f"chart_preview_{chart_id}.png")
|
||||
|
||||
return ChartGenerateResponse(
|
||||
preview_url=f"/api/charts/preview/{chart_id}/{filename}",
|
||||
chart_id=chart_id,
|
||||
chart_type=result.get("chart_type"),
|
||||
chart_data=result.get("chart_data"),
|
||||
title=result.get("title"),
|
||||
warnings=result.get("warnings", []),
|
||||
)
|
||||
|
||||
elif request.chart_type and request.chart_data:
|
||||
# Explicit mode
|
||||
chart_type = request.chart_type
|
||||
if chart_type not in VALID_CHART_TYPES:
|
||||
# Try normalizing aliases
|
||||
from services.chart_service import _normalize_chart_type
|
||||
chart_type = _normalize_chart_type(chart_type)
|
||||
if chart_type not in VALID_CHART_TYPES:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid chart_type. Must be one of: {VALID_CHART_TYPES}"
|
||||
)
|
||||
|
||||
logger.info(f"[Charts] Explicit mode: type={chart_type}, user={user_id}")
|
||||
|
||||
chart_id = uuid.uuid4().hex[:8]
|
||||
result = chart_svc.generate_chart(
|
||||
chart_data=request.chart_data,
|
||||
chart_type=chart_type,
|
||||
title=request.title,
|
||||
subtitle=request.subtitle or "",
|
||||
chart_id=chart_id,
|
||||
)
|
||||
|
||||
if not result.get("path"):
|
||||
raise HTTPException(status_code=500, detail="Chart generation failed — check chart_data format")
|
||||
|
||||
filename = result.get("filename", f"chart_preview_{chart_id}.png")
|
||||
|
||||
return ChartGenerateResponse(
|
||||
preview_url=f"/api/charts/preview/{chart_id}/{filename}",
|
||||
chart_id=chart_id,
|
||||
chart_type=chart_type,
|
||||
chart_data=request.chart_data,
|
||||
title=request.title,
|
||||
)
|
||||
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="Provide either 'text' (AI mode) or 'chart_type' + 'chart_data' (explicit mode)"
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"[Charts] Generation failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Chart generation failed: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/preview/{chart_id}/{filename}")
|
||||
async def serve_chart_preview(
|
||||
chart_id: str,
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user_with_query_token),
|
||||
):
|
||||
"""Serve chart preview PNG files. Auth via header or query token."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
if ".." in filename or "/" in filename or "\\" in filename:
|
||||
raise HTTPException(status_code=400, detail="Invalid filename")
|
||||
|
||||
chart_svc = get_chart_service(user_id=user_id)
|
||||
file_path = chart_svc.get_chart_preview_path(chart_id)
|
||||
|
||||
if not file_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Chart preview not found")
|
||||
|
||||
if not str(file_path.resolve()).startswith(str(chart_svc.output_dir.resolve())):
|
||||
raise HTTPException(status_code=403, detail="Access denied")
|
||||
|
||||
return FileResponse(
|
||||
path=str(file_path),
|
||||
media_type="image/png",
|
||||
filename=filename,
|
||||
)
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
async def charts_health():
|
||||
"""Health check for Charts service."""
|
||||
return {"status": "ok", "service": "charts"}
|
||||
@@ -344,43 +344,6 @@ async def update_asset(
|
||||
raise HTTPException(status_code=500, detail=f"Error updating asset: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/{asset_id}/content")
|
||||
async def get_asset_content(
|
||||
asset_id: int,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Serve the raw text content of a text asset by reading its file from disk."""
|
||||
try:
|
||||
user_id = current_user.get("user_id") or current_user.get("id")
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="User ID not found")
|
||||
|
||||
service = ContentAssetService(db)
|
||||
asset = service.get_asset_by_id(asset_id, user_id)
|
||||
if not asset:
|
||||
raise HTTPException(status_code=404, detail="Asset not found")
|
||||
|
||||
if asset.asset_type != AssetType.TEXT:
|
||||
raise HTTPException(status_code=400, detail="Asset is not a text file")
|
||||
|
||||
if not asset.file_path:
|
||||
raise HTTPException(status_code=404, detail="Asset file path not recorded")
|
||||
|
||||
from pathlib import Path
|
||||
file_path = Path(asset.file_path)
|
||||
if not file_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Asset file not found on disk")
|
||||
|
||||
content = file_path.read_text(encoding="utf-8")
|
||||
return {"success": True, "content": content}
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=f"Error reading asset content: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/statistics", response_model=Dict[str, Any])
|
||||
async def get_statistics(
|
||||
db: Session = Depends(get_db),
|
||||
|
||||
@@ -20,9 +20,6 @@ from ....services.enhanced_strategy_db_service import EnhancedStrategyDBService
|
||||
# Import educational content manager
|
||||
from .content_strategy.educational_content import EducationalContentManager
|
||||
|
||||
# Import authentication
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
# Import utilities
|
||||
from ....utils.error_handlers import ContentPlanningErrorHandler
|
||||
from ....utils.response_builders import ResponseBuilder
|
||||
@@ -43,14 +40,13 @@ _latest_strategies = {}
|
||||
|
||||
@router.post("/generate-comprehensive-strategy")
|
||||
async def generate_comprehensive_strategy(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int,
|
||||
strategy_name: Optional[str] = None,
|
||||
config: Optional[Dict[str, Any]] = None,
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Generate a comprehensive AI-powered content strategy."""
|
||||
try:
|
||||
user_id = current_user.get('id')
|
||||
logger.info(f"🚀 Generating comprehensive AI strategy for user: {user_id}")
|
||||
|
||||
# Get user context and onboarding data
|
||||
@@ -107,7 +103,7 @@ async def generate_comprehensive_strategy(
|
||||
|
||||
@router.post("/generate-strategy-component")
|
||||
async def generate_strategy_component(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int,
|
||||
component_type: str,
|
||||
base_strategy: Optional[Dict[str, Any]] = None,
|
||||
context: Optional[Dict[str, Any]] = None,
|
||||
@@ -115,7 +111,6 @@ async def generate_strategy_component(
|
||||
) -> Dict[str, Any]:
|
||||
"""Generate a specific strategy component using AI."""
|
||||
try:
|
||||
user_id = current_user.get('id')
|
||||
logger.info(f"🚀 Generating strategy component '{component_type}' for user: {user_id}")
|
||||
|
||||
# Validate component type
|
||||
@@ -192,12 +187,11 @@ async def generate_strategy_component(
|
||||
|
||||
@router.get("/strategy-generation-status")
|
||||
async def get_strategy_generation_status(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int,
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get the status of strategy generation for a user."""
|
||||
try:
|
||||
user_id = current_user.get('id')
|
||||
logger.info(f"Getting strategy generation status for user: {user_id}")
|
||||
|
||||
# Get user's strategies
|
||||
@@ -253,7 +247,6 @@ async def get_strategy_generation_status(
|
||||
async def optimize_existing_strategy(
|
||||
strategy_id: int,
|
||||
optimization_type: str = "comprehensive",
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Optimize an existing strategy using AI."""
|
||||
@@ -316,13 +309,12 @@ async def optimize_existing_strategy(
|
||||
@router.post("/generate-comprehensive-strategy-polling")
|
||||
async def generate_comprehensive_strategy_polling(
|
||||
request: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Generate a comprehensive AI-powered content strategy using polling approach."""
|
||||
try:
|
||||
# Extract parameters from request body
|
||||
user_id = current_user.get('id')
|
||||
user_id = request.get("user_id", 1)
|
||||
strategy_name = request.get("strategy_name")
|
||||
config = request.get("config", {})
|
||||
|
||||
@@ -619,7 +611,6 @@ async def generate_comprehensive_strategy_polling(
|
||||
@router.get("/strategy-generation-status/{task_id}")
|
||||
async def get_strategy_generation_status_by_task(
|
||||
task_id: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get the status of strategy generation for a specific task."""
|
||||
@@ -656,12 +647,11 @@ async def get_strategy_generation_status_by_task(
|
||||
|
||||
@router.get("/latest-strategy")
|
||||
async def get_latest_generated_strategy(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(1, description="User ID"),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get the latest generated strategy from the polling system or database."""
|
||||
try:
|
||||
user_id = current_user.get('id')
|
||||
logger.info(f"🔍 Getting latest generated strategy for user: {user_id}")
|
||||
|
||||
# First, try to get from database (most reliable)
|
||||
|
||||
@@ -19,9 +19,6 @@ from ....services.enhanced_strategy_db_service import EnhancedStrategyDBService
|
||||
# Import models
|
||||
from models.enhanced_strategy_models import EnhancedContentStrategy, EnhancedAIAnalysisResult
|
||||
|
||||
# Import authentication
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
# Import utilities
|
||||
from ....utils.error_handlers import ContentPlanningErrorHandler
|
||||
from ....utils.response_builders import ResponseBuilder
|
||||
@@ -40,7 +37,6 @@ def get_db():
|
||||
@router.get("/{strategy_id}/analytics")
|
||||
async def get_enhanced_strategy_analytics(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get comprehensive analytics for an enhanced strategy."""
|
||||
@@ -76,7 +72,6 @@ async def get_enhanced_strategy_analytics(
|
||||
async def get_enhanced_strategy_ai_analysis(
|
||||
strategy_id: int,
|
||||
limit: int = Query(10, description="Number of AI analysis results to return"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get AI analysis history for an enhanced strategy."""
|
||||
@@ -113,7 +108,6 @@ async def get_enhanced_strategy_ai_analysis(
|
||||
@router.get("/{strategy_id}/completion")
|
||||
async def get_enhanced_strategy_completion_stats(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get completion statistics for an enhanced strategy."""
|
||||
@@ -153,7 +147,6 @@ async def get_enhanced_strategy_completion_stats(
|
||||
@router.get("/{strategy_id}/onboarding-integration")
|
||||
async def get_enhanced_strategy_onboarding_integration(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Get onboarding data integration for an enhanced strategy."""
|
||||
@@ -184,7 +177,6 @@ async def get_enhanced_strategy_onboarding_integration(
|
||||
@router.post("/{strategy_id}/ai-recommendations")
|
||||
async def generate_enhanced_ai_recommendations(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Generate AI recommendations for an enhanced strategy."""
|
||||
@@ -224,7 +216,6 @@ async def generate_enhanced_ai_recommendations(
|
||||
async def regenerate_enhanced_strategy_ai_analysis(
|
||||
strategy_id: int,
|
||||
analysis_type: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Regenerate AI analysis for an enhanced strategy."""
|
||||
|
||||
@@ -21,9 +21,6 @@ from ....services.enhanced_strategy_service import EnhancedStrategyService
|
||||
from ....services.enhanced_strategy_db_service import EnhancedStrategyDBService
|
||||
from ....services.content_strategy.autofill.ai_refresh import AutoFillRefreshService
|
||||
|
||||
# Import authentication
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
# Import utilities
|
||||
from ....utils.error_handlers import ContentPlanningErrorHandler
|
||||
from ....utils.response_builders import ResponseBuilder
|
||||
@@ -52,13 +49,12 @@ async def stream_data(data_generator):
|
||||
async def accept_autofill_inputs(
|
||||
strategy_id: int,
|
||||
payload: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Persist end-user accepted auto-fill inputs and associate with the strategy."""
|
||||
try:
|
||||
logger.info(f"🚀 Accepting autofill inputs for strategy: {strategy_id}")
|
||||
user_id = str(current_user.get('id'))
|
||||
user_id = str(payload.get('user_id') or "")
|
||||
accepted_fields = payload.get('accepted_fields') or {}
|
||||
# Optional transparency bundles
|
||||
sources = payload.get('sources') or {}
|
||||
@@ -103,7 +99,7 @@ async def accept_autofill_inputs(
|
||||
|
||||
@router.get("/autofill/refresh/stream")
|
||||
async def stream_autofill_refresh(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: Optional[int] = Query(None, description="User ID to build auto-fill for"),
|
||||
use_ai: bool = Query(True, description="Use AI augmentation during refresh"),
|
||||
ai_only: bool = Query(False, description="AI-first refresh: return AI overrides when available"),
|
||||
db: Session = Depends(get_db)
|
||||
@@ -111,7 +107,7 @@ async def stream_autofill_refresh(
|
||||
"""SSE endpoint to stream steps while generating a fresh auto-fill payload (no DB writes)."""
|
||||
async def refresh_generator():
|
||||
try:
|
||||
actual_user_id = current_user.get('id', 1)
|
||||
actual_user_id = user_id or 1
|
||||
start_time = datetime.utcnow()
|
||||
logger.info(f"🚀 Starting auto-fill refresh stream for user: {actual_user_id}")
|
||||
yield {"type": "status", "phase": "init", "message": "Starting…", "progress": 5}
|
||||
@@ -207,14 +203,14 @@ async def stream_autofill_refresh(
|
||||
|
||||
@router.post("/autofill/refresh")
|
||||
async def refresh_autofill(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: Optional[int] = Query(None, description="User ID to build auto-fill for"),
|
||||
use_ai: bool = Query(True, description="Use AI augmentation during refresh"),
|
||||
ai_only: bool = Query(False, description="AI-first refresh: return AI overrides when available"),
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Non-stream endpoint to return a fresh auto-fill payload (no DB writes)."""
|
||||
try:
|
||||
actual_user_id = current_user.get('id', 1)
|
||||
actual_user_id = user_id or 1
|
||||
started = datetime.utcnow()
|
||||
refresh_service = AutoFillRefreshService(db)
|
||||
payload = await refresh_service.build_fresh_payload_with_transparency(actual_user_id, use_ai=use_ai, ai_only=ai_only)
|
||||
|
||||
@@ -4,7 +4,7 @@ Handles streaming endpoints for enhanced content strategies.
|
||||
"""
|
||||
|
||||
from typing import Dict, Any, Optional
|
||||
from fastapi import APIRouter, Depends, Query
|
||||
from fastapi import APIRouter, Depends, HTTPException, Query
|
||||
from fastapi.responses import StreamingResponse
|
||||
from starlette.requests import Request
|
||||
from sqlalchemy.orm import Session
|
||||
@@ -12,6 +12,8 @@ from loguru import logger
|
||||
import json
|
||||
import asyncio
|
||||
from datetime import datetime
|
||||
from collections import defaultdict
|
||||
import time
|
||||
|
||||
# Import database
|
||||
from services.database import get_db_session
|
||||
@@ -23,13 +25,31 @@ from middleware.auth_middleware import get_current_user, get_current_user_with_q
|
||||
from ....services.enhanced_strategy_service import EnhancedStrategyService
|
||||
from ....services.enhanced_strategy_db_service import EnhancedStrategyDBService
|
||||
|
||||
# Use bounded shared cache instead of process-local unbounded dict
|
||||
from ...services.content_strategy.performance.caching import CachingService
|
||||
# Import utilities
|
||||
from ....utils.error_handlers import ContentPlanningErrorHandler
|
||||
from ....utils.response_builders import ResponseBuilder
|
||||
from ....utils.constants import ERROR_MESSAGES, SUCCESS_MESSAGES
|
||||
|
||||
router = APIRouter(tags=["Strategy Streaming"])
|
||||
|
||||
# Shared bounded cache for streaming endpoints
|
||||
streaming_cache_service = CachingService()
|
||||
# Cache for streaming endpoints (5 minutes cache)
|
||||
streaming_cache = defaultdict(dict)
|
||||
CACHE_DURATION = 300 # 5 minutes
|
||||
|
||||
def get_cached_data(cache_key: str) -> Optional[Dict[str, Any]]:
|
||||
"""Get cached data if it exists and is not expired."""
|
||||
if cache_key in streaming_cache:
|
||||
cached_data = streaming_cache[cache_key]
|
||||
if time.time() - cached_data.get("timestamp", 0) < CACHE_DURATION:
|
||||
return cached_data.get("data")
|
||||
return None
|
||||
|
||||
def set_cached_data(cache_key: str, data: Dict[str, Any]):
|
||||
"""Set cached data with timestamp."""
|
||||
streaming_cache[cache_key] = {
|
||||
"data": data,
|
||||
"timestamp": time.time()
|
||||
}
|
||||
|
||||
# Helper function to get database session
|
||||
def get_db():
|
||||
@@ -103,7 +123,11 @@ async def stream_enhanced_strategies(
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive"
|
||||
"Connection": "keep-alive",
|
||||
"Access-Control-Allow-Origin": "*",
|
||||
"Access-Control-Allow-Headers": "*",
|
||||
"Access-Control-Allow-Methods": "GET, POST, OPTIONS",
|
||||
"Access-Control-Allow-Credentials": "true"
|
||||
}
|
||||
)
|
||||
|
||||
@@ -126,9 +150,9 @@ async def stream_strategic_intelligence(
|
||||
|
||||
logger.info(f"🚀 Starting strategic intelligence stream for authenticated user: {authenticated_user_id}")
|
||||
|
||||
# Check bounded shared cache first
|
||||
# Check cache first
|
||||
cache_key = f"strategic_intelligence_{authenticated_user_id}"
|
||||
cached_data = await streaming_cache_service.get_cached_data("streaming_intelligence", cache_key)
|
||||
cached_data = get_cached_data(cache_key)
|
||||
if cached_data:
|
||||
logger.info(f"✅ Returning cached strategic intelligence data for user: {authenticated_user_id}")
|
||||
yield {"type": "result", "status": "success", "data": cached_data, "progress": 100}
|
||||
@@ -143,6 +167,7 @@ async def stream_strategic_intelligence(
|
||||
# Send progress update
|
||||
yield {"type": "progress", "message": "Retrieving strategies...", "progress": 20}
|
||||
|
||||
# Use authenticated user_id to ensure users can only see their own strategies
|
||||
strategies_data = await enhanced_service.get_enhanced_strategies(authenticated_user_id, None, db)
|
||||
|
||||
# Send progress update
|
||||
@@ -169,29 +194,54 @@ async def stream_strategic_intelligence(
|
||||
# Send progress update
|
||||
yield {"type": "progress", "message": "Processing intelligence data...", "progress": 60}
|
||||
|
||||
# Build strategic intelligence from actual strategy data — no hardcoded fallback defaults
|
||||
strategic_intelligence = {
|
||||
"market_positioning": {
|
||||
"current_position": strategy.get("competitive_position") or None,
|
||||
"differentiation_factors": strategy.get("differentiation_factors") or None
|
||||
"current_position": strategy.get("competitive_position", "Challenger"),
|
||||
"target_position": "Market Leader",
|
||||
"differentiation_factors": [
|
||||
"AI-powered content optimization",
|
||||
"Data-driven strategy development",
|
||||
"Personalized user experience"
|
||||
]
|
||||
},
|
||||
"competitive_analysis": {
|
||||
"top_competitors": (strategy.get("top_competitors") or [None])[:3],
|
||||
"competitive_advantages": strategy.get("competitive_advantages") or None,
|
||||
"market_gaps": strategy.get("market_gaps") or None
|
||||
"top_competitors": strategy.get("top_competitors", [])[:3] or [
|
||||
"Competitor A", "Competitor B", "Competitor C"
|
||||
],
|
||||
"competitive_advantages": [
|
||||
"Advanced AI capabilities",
|
||||
"Comprehensive data integration",
|
||||
"User-centric design"
|
||||
],
|
||||
"market_gaps": strategy.get("market_gaps", []) or [
|
||||
"AI-driven content personalization",
|
||||
"Real-time performance optimization",
|
||||
"Predictive analytics"
|
||||
]
|
||||
},
|
||||
"ai_insights": ai_recommendations.get("strategic_insights") if ai_recommendations else None,
|
||||
"opportunities": strategy.get("opportunities") or None
|
||||
}
|
||||
|
||||
# Filter out null-only sections for cleaner responses
|
||||
strategic_intelligence = {
|
||||
k: v for k, v in strategic_intelligence.items()
|
||||
if v is not None and v != [None]
|
||||
"ai_insights": ai_recommendations.get("strategic_insights", []) or [
|
||||
"Focus on pillar content strategy",
|
||||
"Implement topic clustering",
|
||||
"Optimize for voice search"
|
||||
],
|
||||
"opportunities": [
|
||||
{
|
||||
"area": "Content Personalization",
|
||||
"potential_impact": "High",
|
||||
"implementation_timeline": "3-6 months",
|
||||
"estimated_roi": "25-40%"
|
||||
},
|
||||
{
|
||||
"area": "AI-Powered Optimization",
|
||||
"potential_impact": "Medium",
|
||||
"implementation_timeline": "6-12 months",
|
||||
"estimated_roi": "15-30%"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
# Cache the strategic intelligence data
|
||||
await streaming_cache_service.set_cached_data("streaming_intelligence", cache_key, strategic_intelligence)
|
||||
set_cached_data(cache_key, strategic_intelligence)
|
||||
|
||||
# Send progress update
|
||||
yield {"type": "progress", "message": "Finalizing strategic intelligence...", "progress": 80}
|
||||
@@ -210,7 +260,11 @@ async def stream_strategic_intelligence(
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive"
|
||||
"Connection": "keep-alive",
|
||||
"Access-Control-Allow-Origin": "*",
|
||||
"Access-Control-Allow-Headers": "*",
|
||||
"Access-Control-Allow-Methods": "GET, POST, OPTIONS",
|
||||
"Access-Control-Allow-Credentials": "true"
|
||||
}
|
||||
)
|
||||
|
||||
@@ -233,9 +287,9 @@ async def stream_keyword_research(
|
||||
|
||||
logger.info(f"🚀 Starting keyword research stream for authenticated user: {authenticated_user_id}")
|
||||
|
||||
# Check bounded shared cache first
|
||||
# Check cache first
|
||||
cache_key = f"keyword_research_{authenticated_user_id}"
|
||||
cached_data = await streaming_cache_service.get_cached_data("streaming_intelligence", cache_key)
|
||||
cached_data = get_cached_data(cache_key)
|
||||
if cached_data:
|
||||
logger.info(f"✅ Returning cached keyword research data for user: {authenticated_user_id}")
|
||||
yield {"type": "result", "status": "success", "data": cached_data, "progress": 100}
|
||||
@@ -279,24 +333,33 @@ async def stream_keyword_research(
|
||||
# Send progress update
|
||||
yield {"type": "progress", "message": "Processing keyword data...", "progress": 60}
|
||||
|
||||
# Build keyword data from actual analysis — no hardcoded fallback defaults
|
||||
keyword_data = {
|
||||
"trend_analysis": {
|
||||
"high_volume_keywords": (analysis_results.get("opportunities") or [None])[:3],
|
||||
"trending_keywords": analysis_results.get("trending_keywords") or None
|
||||
"high_volume_keywords": analysis_results.get("opportunities", [])[:3] or [
|
||||
{"keyword": "AI marketing automation", "volume": "10K-100K", "difficulty": "Medium"},
|
||||
{"keyword": "content strategy 2024", "volume": "1K-10K", "difficulty": "Low"},
|
||||
{"keyword": "digital marketing trends", "volume": "10K-100K", "difficulty": "High"}
|
||||
],
|
||||
"trending_keywords": [
|
||||
{"keyword": "AI content generation", "growth": "+45%", "opportunity": "High"},
|
||||
{"keyword": "voice search optimization", "growth": "+32%", "opportunity": "Medium"},
|
||||
{"keyword": "video marketing strategy", "growth": "+28%", "opportunity": "High"}
|
||||
]
|
||||
},
|
||||
"intent_analysis": analysis_results.get("intent_analysis") or None,
|
||||
"opportunities": analysis_results.get("opportunities") or None
|
||||
}
|
||||
|
||||
# Filter out null-only sections
|
||||
keyword_data = {
|
||||
k: v for k, v in keyword_data.items()
|
||||
if v is not None and v != [None]
|
||||
"intent_analysis": {
|
||||
"informational": ["how to", "what is", "guide to"],
|
||||
"navigational": ["company name", "brand name", "website"],
|
||||
"transactional": ["buy", "purchase", "download", "sign up"]
|
||||
},
|
||||
"opportunities": analysis_results.get("opportunities", []) or [
|
||||
{"keyword": "AI content tools", "search_volume": "5K-10K", "competition": "Low", "cpc": "$2.50"},
|
||||
{"keyword": "content marketing ROI", "search_volume": "1K-5K", "competition": "Medium", "cpc": "$4.20"},
|
||||
{"keyword": "social media strategy", "search_volume": "10K-50K", "competition": "High", "cpc": "$3.80"}
|
||||
]
|
||||
}
|
||||
|
||||
# Cache the keyword data
|
||||
await streaming_cache_service.set_cached_data("streaming_intelligence", cache_key, keyword_data)
|
||||
set_cached_data(cache_key, keyword_data)
|
||||
|
||||
# Send progress update
|
||||
yield {"type": "progress", "message": "Finalizing keyword research...", "progress": 80}
|
||||
@@ -315,71 +378,10 @@ async def stream_keyword_research(
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive"
|
||||
"Connection": "keep-alive",
|
||||
"Access-Control-Allow-Origin": "*",
|
||||
"Access-Control-Allow-Headers": "*",
|
||||
"Access-Control-Allow-Methods": "GET, POST, OPTIONS",
|
||||
"Access-Control-Allow-Credentials": "true"
|
||||
}
|
||||
)
|
||||
|
||||
@router.get("/stream/ai-generation-status")
|
||||
async def stream_ai_generation_status(
|
||||
request: Request,
|
||||
strategy_id: int = Query(..., description="Strategy ID"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user_with_query_token),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Stream AI generation status for a strategy with real-time updates."""
|
||||
|
||||
async def status_generator():
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
if not clerk_user_id:
|
||||
yield {"type": "error", "detail": "Invalid user ID", "progress": 0}
|
||||
return
|
||||
|
||||
authenticated_user_id = clerk_user_id
|
||||
|
||||
logger.info(f"🚀 Starting AI generation status stream for user: {authenticated_user_id}, strategy: {strategy_id}")
|
||||
|
||||
yield {"type": "progress", "detail": "Fetching AI generation status...", "progress": 10}
|
||||
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
enhanced_service = EnhancedStrategyService(db_service)
|
||||
|
||||
strategy = await enhanced_service.get_enhanced_strategy(strategy_id, authenticated_user_id, db)
|
||||
|
||||
if not strategy or strategy.get("status") == "not_found":
|
||||
yield {"type": "error", "detail": "Strategy not found", "progress": 0}
|
||||
return
|
||||
|
||||
yield {"type": "progress", "detail": "Checking AI analysis status...", "progress": 30}
|
||||
|
||||
ai_recommendations = strategy.get("ai_recommendations")
|
||||
if ai_recommendations:
|
||||
if isinstance(ai_recommendations, str):
|
||||
try:
|
||||
ai_recommendations = json.loads(ai_recommendations)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
ai_recommendations = {}
|
||||
|
||||
ai_status = "completed" if ai_recommendations else "pending"
|
||||
|
||||
if ai_status == "completed":
|
||||
yield {"type": "progress", "detail": "AI analysis completed", "progress": 80}
|
||||
yield {"type": "result", "status": "completed", "detail": "AI generation completed", "progress": 100}
|
||||
else:
|
||||
yield {"type": "progress", "detail": "AI analysis is pending", "progress": 50}
|
||||
yield {"type": "result", "status": "pending", "detail": "AI generation is in progress", "progress": 50}
|
||||
|
||||
logger.info(f"✅ AI generation status stream completed for user: {authenticated_user_id}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Error in AI generation status stream: {str(e)}")
|
||||
yield {"type": "error", "detail": str(e), "progress": 0}
|
||||
|
||||
return StreamingResponse(
|
||||
stream_data(status_generator()),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive"
|
||||
}
|
||||
)
|
||||
)
|
||||
|
||||
@@ -65,16 +65,12 @@ async def analyze_content_evolution(
|
||||
)
|
||||
|
||||
@router.post("/performance-trends", response_model=AIAnalyticsResponse)
|
||||
async def analyze_performance_trends(
|
||||
request: PerformanceTrendsRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def analyze_performance_trends(request: PerformanceTrendsRequest):
|
||||
"""
|
||||
Analyze performance trends for content strategy.
|
||||
"""
|
||||
try:
|
||||
user_id = current_user.get("user_id")
|
||||
logger.info(f"Starting performance trends analysis for strategy {request.strategy_id} (user {user_id})")
|
||||
logger.info(f"Starting performance trends analysis for strategy {request.strategy_id}")
|
||||
|
||||
result = await ai_analytics_service.analyze_performance_trends(
|
||||
strategy_id=request.strategy_id,
|
||||
@@ -91,16 +87,12 @@ async def analyze_performance_trends(
|
||||
)
|
||||
|
||||
@router.post("/predict-performance", response_model=AIAnalyticsResponse)
|
||||
async def predict_content_performance(
|
||||
request: ContentPerformancePredictionRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def predict_content_performance(request: ContentPerformancePredictionRequest):
|
||||
"""
|
||||
Predict content performance using AI models.
|
||||
"""
|
||||
try:
|
||||
user_id = current_user.get("user_id")
|
||||
logger.info(f"Starting content performance prediction for strategy {request.strategy_id} (user {user_id})")
|
||||
logger.info(f"Starting content performance prediction for strategy {request.strategy_id}")
|
||||
|
||||
result = await ai_analytics_service.predict_content_performance(
|
||||
strategy_id=request.strategy_id,
|
||||
@@ -145,13 +137,12 @@ async def generate_strategic_intelligence(
|
||||
|
||||
@router.get("/", response_model=Dict[str, Any])
|
||||
async def get_ai_analytics(
|
||||
user_id: Optional[int] = Query(None, description="User ID"),
|
||||
strategy_id: Optional[int] = Query(None, description="Strategy ID"),
|
||||
force_refresh: bool = Query(False, description="Force refresh AI analysis"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
force_refresh: bool = Query(False, description="Force refresh AI analysis")
|
||||
):
|
||||
"""Get AI analytics with real personalized insights - Database first approach."""
|
||||
try:
|
||||
user_id = current_user.get("user_id") or current_user.get("id")
|
||||
logger.info(f"🚀 Starting AI analytics for user: {user_id}, strategy: {strategy_id}, force_refresh: {force_refresh}")
|
||||
|
||||
result = await ai_analytics_service.get_ai_analytics(user_id, strategy_id, force_refresh)
|
||||
@@ -162,14 +153,11 @@ async def get_ai_analytics(
|
||||
raise HTTPException(status_code=500, detail=f"Error generating AI analytics: {str(e)}")
|
||||
|
||||
@router.get("/health")
|
||||
async def ai_analytics_health_check(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def ai_analytics_health_check():
|
||||
"""
|
||||
Health check for AI analytics services.
|
||||
"""
|
||||
try:
|
||||
logger.debug(f"AI analytics health check by user: {current_user.get('id')}")
|
||||
# Check AI analytics service
|
||||
service_status = {}
|
||||
|
||||
@@ -209,16 +197,14 @@ async def ai_analytics_health_check(
|
||||
async def get_user_ai_analysis_results(
|
||||
user_id: int,
|
||||
analysis_type: Optional[str] = Query(None, description="Filter by analysis type"),
|
||||
limit: int = Query(10, description="Number of results to return"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
limit: int = Query(10, description="Number of results to return")
|
||||
):
|
||||
"""Get AI analysis results for the authenticated user."""
|
||||
"""Get AI analysis results for a specific user."""
|
||||
try:
|
||||
authenticated_user_id = current_user.get("user_id") or current_user.get("id")
|
||||
logger.info(f"Fetching AI analysis results for authenticated user {authenticated_user_id}")
|
||||
logger.info(f"Fetching AI analysis results for user {user_id}")
|
||||
|
||||
result = await ai_analytics_service.get_user_ai_analysis_results(
|
||||
user_id=authenticated_user_id,
|
||||
user_id=user_id,
|
||||
analysis_type=analysis_type,
|
||||
limit=limit
|
||||
)
|
||||
@@ -233,16 +219,14 @@ async def get_user_ai_analysis_results(
|
||||
async def refresh_ai_analysis(
|
||||
user_id: int,
|
||||
analysis_type: str = Query(..., description="Type of analysis to refresh"),
|
||||
strategy_id: Optional[int] = Query(None, description="Strategy ID"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
strategy_id: Optional[int] = Query(None, description="Strategy ID")
|
||||
):
|
||||
"""Force refresh of AI analysis for the authenticated user."""
|
||||
"""Force refresh of AI analysis for a user."""
|
||||
try:
|
||||
authenticated_user_id = current_user.get("user_id") or current_user.get("id")
|
||||
logger.info(f"Force refreshing AI analysis for authenticated user {authenticated_user_id}, type: {analysis_type}")
|
||||
logger.info(f"Force refreshing AI analysis for user {user_id}, type: {analysis_type}")
|
||||
|
||||
result = await ai_analytics_service.refresh_ai_analysis(
|
||||
user_id=authenticated_user_id,
|
||||
user_id=user_id,
|
||||
analysis_type=analysis_type,
|
||||
strategy_id=strategy_id
|
||||
)
|
||||
@@ -256,16 +240,14 @@ async def refresh_ai_analysis(
|
||||
@router.delete("/cache/{user_id}")
|
||||
async def clear_ai_analysis_cache(
|
||||
user_id: int,
|
||||
analysis_type: Optional[str] = Query(None, description="Specific analysis type to clear"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
analysis_type: Optional[str] = Query(None, description="Specific analysis type to clear")
|
||||
):
|
||||
"""Clear AI analysis cache for the authenticated user."""
|
||||
"""Clear AI analysis cache for a user."""
|
||||
try:
|
||||
authenticated_user_id = current_user.get("user_id") or current_user.get("id")
|
||||
logger.info(f"Clearing AI analysis cache for authenticated user {authenticated_user_id}")
|
||||
logger.info(f"Clearing AI analysis cache for user {user_id}")
|
||||
|
||||
result = await ai_analytics_service.clear_ai_analysis_cache(
|
||||
user_id=authenticated_user_id,
|
||||
user_id=user_id,
|
||||
analysis_type=analysis_type
|
||||
)
|
||||
|
||||
@@ -277,15 +259,13 @@ async def clear_ai_analysis_cache(
|
||||
|
||||
@router.get("/statistics")
|
||||
async def get_ai_analysis_statistics(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: Optional[int] = Query(None, description="User ID for user-specific stats")
|
||||
):
|
||||
"""Get AI analysis statistics."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"📊 Getting AI analysis statistics for authenticated user: {clerk_user_id}")
|
||||
logger.info(f"📊 Getting AI analysis statistics for user: {user_id}")
|
||||
|
||||
result = await ai_analytics_service.get_ai_analysis_statistics(user_id or clerk_user_id)
|
||||
result = await ai_analytics_service.get_ai_analysis_statistics(user_id)
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
|
||||
@@ -9,9 +9,6 @@ from typing import Dict, Any, List, Optional
|
||||
from datetime import datetime
|
||||
from loguru import logger
|
||||
|
||||
# Import authentication
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
# Import database service
|
||||
from services.database import get_db_session, get_db
|
||||
from services.content_planning_db import ContentPlanningDBService
|
||||
@@ -37,16 +34,13 @@ router = APIRouter(prefix="/calendar-events", tags=["calendar-events"])
|
||||
@router.post("/", response_model=CalendarEventResponse)
|
||||
async def create_calendar_event(
|
||||
event: CalendarEventCreate,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Create a new calendar event."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Creating calendar event: {event.title} for user: {clerk_user_id}")
|
||||
logger.info(f"Creating calendar event: {event.title}")
|
||||
|
||||
event_data = event.dict()
|
||||
event_data['user_id'] = clerk_user_id
|
||||
created_event = await calendar_service.create_calendar_event(event_data, db)
|
||||
|
||||
return CalendarEventResponse(**created_event)
|
||||
@@ -60,13 +54,11 @@ async def create_calendar_event(
|
||||
@router.get("/", response_model=List[CalendarEventResponse])
|
||||
async def get_calendar_events(
|
||||
strategy_id: Optional[int] = Query(None, description="Filter by strategy ID"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get calendar events, optionally filtered by strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching calendar events for user: {clerk_user_id}")
|
||||
logger.info("Fetching calendar events")
|
||||
|
||||
events = await calendar_service.get_calendar_events(strategy_id, db)
|
||||
return [CalendarEventResponse(**event) for event in events]
|
||||
@@ -78,13 +70,11 @@ async def get_calendar_events(
|
||||
@router.get("/{event_id}", response_model=CalendarEventResponse)
|
||||
async def get_calendar_event(
|
||||
event_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get a specific calendar event by ID."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching calendar event: {event_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Fetching calendar event: {event_id}")
|
||||
|
||||
event = await calendar_service.get_calendar_event_by_id(event_id, db)
|
||||
return CalendarEventResponse(**event)
|
||||
@@ -99,13 +89,11 @@ async def get_calendar_event(
|
||||
async def update_calendar_event(
|
||||
event_id: int,
|
||||
update_data: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Update a calendar event."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Updating calendar event: {event_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Updating calendar event: {event_id}")
|
||||
|
||||
updated_event = await calendar_service.update_calendar_event(event_id, update_data, db)
|
||||
return CalendarEventResponse(**updated_event)
|
||||
@@ -119,13 +107,11 @@ async def update_calendar_event(
|
||||
@router.delete("/{event_id}")
|
||||
async def delete_calendar_event(
|
||||
event_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Delete a calendar event."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Deleting calendar event: {event_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Deleting calendar event: {event_id}")
|
||||
|
||||
deleted = await calendar_service.delete_calendar_event(event_id, db)
|
||||
|
||||
@@ -143,13 +129,11 @@ async def delete_calendar_event(
|
||||
@router.post("/schedule", response_model=Dict[str, Any])
|
||||
async def schedule_calendar_event(
|
||||
event: CalendarEventCreate,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Schedule a calendar event with conflict checking."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Scheduling calendar event: {event.title} for user: {clerk_user_id}")
|
||||
logger.info(f"Scheduling calendar event: {event.title}")
|
||||
|
||||
event_data = event.dict()
|
||||
result = await calendar_service.schedule_event(event_data, db)
|
||||
@@ -163,13 +147,11 @@ async def schedule_calendar_event(
|
||||
async def get_strategy_events(
|
||||
strategy_id: int,
|
||||
status: Optional[str] = Query(None, description="Filter by event status"),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get calendar events for a specific strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching events for strategy: {strategy_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Fetching events for strategy: {strategy_id}")
|
||||
|
||||
if status:
|
||||
events = await calendar_service.get_events_by_status(strategy_id, status, db)
|
||||
|
||||
@@ -114,23 +114,25 @@ async def generate_comprehensive_calendar(
|
||||
)
|
||||
|
||||
@router.post("/optimize-content", response_model=ContentOptimizationResponse)
|
||||
async def optimize_content_for_platform(
|
||||
request: ContentOptimizationRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def optimize_content_for_platform(request: ContentOptimizationRequest, db: Session = Depends(get_db)):
|
||||
"""
|
||||
Optimize content for specific platforms using database insights with user isolation.
|
||||
Optimize content for specific platforms using database insights.
|
||||
|
||||
This endpoint optimizes content based on:
|
||||
- Historical performance data for the platform
|
||||
- Audience preferences from onboarding data
|
||||
- Gap analysis insights for content improvement
|
||||
- Competitor analysis for differentiation
|
||||
- Active strategy data for optimal alignment
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
logger.info(f"🔧 Starting content optimization for authenticated user {clerk_user_id}")
|
||||
logger.info(f"🔧 Starting content optimization for user {request.user_id}")
|
||||
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
result = await calendar_service.optimize_content_for_platform(
|
||||
user_id=clerk_user_id,
|
||||
user_id=request.user_id,
|
||||
title=request.title,
|
||||
description=request.description,
|
||||
content_type=request.content_type,
|
||||
@@ -150,23 +152,24 @@ async def optimize_content_for_platform(
|
||||
)
|
||||
|
||||
@router.post("/performance-predictions", response_model=PerformancePredictionResponse)
|
||||
async def predict_content_performance(
|
||||
request: PerformancePredictionRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def predict_content_performance(request: PerformancePredictionRequest, db: Session = Depends(get_db)):
|
||||
"""
|
||||
Predict content performance using database insights with user isolation.
|
||||
Predict content performance using database insights.
|
||||
|
||||
This endpoint predicts performance based on:
|
||||
- Historical performance data
|
||||
- Audience demographics and preferences
|
||||
- Content type and platform patterns
|
||||
- Gap analysis opportunities
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
logger.info(f"📊 Starting performance prediction for authenticated user {clerk_user_id}")
|
||||
logger.info(f"📊 Starting performance prediction for user {request.user_id}")
|
||||
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
result = await calendar_service.predict_content_performance(
|
||||
user_id=clerk_user_id,
|
||||
user_id=request.user_id,
|
||||
content_type=request.content_type,
|
||||
platform=request.platform,
|
||||
content_data=request.content_data,
|
||||
@@ -183,23 +186,24 @@ async def predict_content_performance(
|
||||
)
|
||||
|
||||
@router.post("/repurpose-content", response_model=ContentRepurposingResponse)
|
||||
async def repurpose_content_across_platforms(
|
||||
request: ContentRepurposingRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def repurpose_content_across_platforms(request: ContentRepurposingRequest, db: Session = Depends(get_db)):
|
||||
"""
|
||||
Repurpose content across different platforms using database insights with user isolation.
|
||||
Repurpose content across different platforms using database insights.
|
||||
|
||||
This endpoint suggests content repurposing based on:
|
||||
- Existing content and strategy data
|
||||
- Gap analysis opportunities
|
||||
- Platform-specific requirements
|
||||
- Audience preferences
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
logger.info(f"🔄 Starting content repurposing for authenticated user {clerk_user_id}")
|
||||
logger.info(f"🔄 Starting content repurposing for user {request.user_id}")
|
||||
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
result = await calendar_service.repurpose_content_across_platforms(
|
||||
user_id=clerk_user_id,
|
||||
user_id=request.user_id,
|
||||
original_content=request.original_content,
|
||||
target_platforms=request.target_platforms,
|
||||
strategy_id=request.strategy_id
|
||||
@@ -308,16 +312,12 @@ async def get_comprehensive_user_data(
|
||||
)
|
||||
|
||||
@router.get("/health")
|
||||
async def calendar_generation_health_check(
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def calendar_generation_health_check(db: Session = Depends(get_db)):
|
||||
"""
|
||||
Health check for calendar generation services.
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
logger.info(f"🏥 Performing calendar generation health check for user {clerk_user_id}")
|
||||
logger.info("🏥 Performing calendar generation health check")
|
||||
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
@@ -337,17 +337,12 @@ async def calendar_generation_health_check(
|
||||
}
|
||||
|
||||
@router.get("/progress/{session_id}")
|
||||
async def get_calendar_generation_progress(
|
||||
session_id: str,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def get_calendar_generation_progress(session_id: str, db: Session = Depends(get_db)):
|
||||
"""
|
||||
Get real-time progress of calendar generation for a specific session.
|
||||
This endpoint is polled by the frontend modal to show progress updates.
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
@@ -438,16 +433,11 @@ async def start_calendar_generation(
|
||||
raise HTTPException(status_code=500, detail="Failed to start calendar generation")
|
||||
|
||||
@router.delete("/cancel/{session_id}")
|
||||
async def cancel_calendar_generation(
|
||||
session_id: str,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def cancel_calendar_generation(session_id: str, db: Session = Depends(get_db)):
|
||||
"""
|
||||
Cancel an ongoing calendar generation session.
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
@@ -473,13 +463,9 @@ async def cancel_calendar_generation(
|
||||
|
||||
# Cache Management Endpoints
|
||||
@router.get("/cache/stats")
|
||||
async def get_cache_stats(
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
) -> Dict[str, Any]:
|
||||
async def get_cache_stats(db: Session = Depends(get_db)) -> Dict[str, Any]:
|
||||
"""Get comprehensive user data cache statistics."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
from services.comprehensive_user_data_cache_service import ComprehensiveUserDataCacheService
|
||||
cache_service = ComprehensiveUserDataCacheService(db)
|
||||
stats = cache_service.get_cache_stats()
|
||||
@@ -492,21 +478,19 @@ async def get_cache_stats(
|
||||
async def invalidate_user_cache(
|
||||
user_id: str,
|
||||
strategy_id: Optional[int] = Query(None, description="Strategy ID to invalidate (optional)"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
db: Session = Depends(get_db)
|
||||
) -> Dict[str, Any]:
|
||||
"""Invalidate cache for the authenticated user."""
|
||||
"""Invalidate cache for a specific user/strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
from services.comprehensive_user_data_cache_service import ComprehensiveUserDataCacheService
|
||||
cache_service = ComprehensiveUserDataCacheService(db)
|
||||
success = cache_service.invalidate_cache(clerk_user_id, strategy_id)
|
||||
success = cache_service.invalidate_cache(user_id, strategy_id)
|
||||
|
||||
if success:
|
||||
return {
|
||||
"status": "success",
|
||||
"message": f"Cache invalidated for user {clerk_user_id}" + (f" and strategy {strategy_id}" if strategy_id else ""),
|
||||
"user_id": clerk_user_id,
|
||||
"message": f"Cache invalidated for user {user_id}" + (f" and strategy {strategy_id}" if strategy_id else ""),
|
||||
"user_id": user_id,
|
||||
"strategy_id": strategy_id
|
||||
}
|
||||
else:
|
||||
@@ -517,13 +501,9 @@ async def invalidate_user_cache(
|
||||
raise HTTPException(status_code=500, detail="Failed to invalidate cache")
|
||||
|
||||
@router.post("/cache/cleanup")
|
||||
async def cleanup_expired_cache(
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
) -> Dict[str, Any]:
|
||||
async def cleanup_expired_cache(db: Session = Depends(get_db)) -> Dict[str, Any]:
|
||||
"""Clean up expired cache entries."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
from services.comprehensive_user_data_cache_service import ComprehensiveUserDataCacheService
|
||||
cache_service = ComprehensiveUserDataCacheService(db)
|
||||
deleted_count = cache_service.cleanup_expired_cache()
|
||||
@@ -539,22 +519,16 @@ async def cleanup_expired_cache(
|
||||
raise HTTPException(status_code=500, detail="Failed to clean up cache")
|
||||
|
||||
@router.get("/sessions")
|
||||
async def list_active_sessions(
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def list_active_sessions(db: Session = Depends(get_db)):
|
||||
"""
|
||||
List active calendar generation sessions for the authenticated user.
|
||||
List all active calendar generation sessions.
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
sessions = []
|
||||
for session_id, session_data in calendar_service.orchestrator_sessions.items():
|
||||
if str(session_data.get("user_id", "")) != clerk_user_id:
|
||||
continue
|
||||
sessions.append({
|
||||
"session_id": session_id,
|
||||
"user_id": session_data.get("user_id"),
|
||||
@@ -574,15 +548,11 @@ async def list_active_sessions(
|
||||
raise HTTPException(status_code=500, detail="Failed to list sessions")
|
||||
|
||||
@router.delete("/sessions/cleanup")
|
||||
async def cleanup_old_sessions(
|
||||
db: Session = Depends(get_db),
|
||||
current_user: dict = Depends(get_current_user)
|
||||
):
|
||||
async def cleanup_old_sessions(db: Session = Depends(get_db)):
|
||||
"""
|
||||
Clean up old sessions for the authenticated user.
|
||||
Clean up old sessions.
|
||||
"""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id'))
|
||||
# Initialize service with database session for active strategy access
|
||||
calendar_service = CalendarGenerationService(db)
|
||||
|
||||
|
||||
@@ -38,16 +38,13 @@ router = APIRouter(prefix="/gap-analysis", tags=["gap-analysis"])
|
||||
@router.post("/", response_model=ContentGapAnalysisResponse)
|
||||
async def create_content_gap_analysis(
|
||||
analysis: ContentGapAnalysisCreate,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Create a new content gap analysis."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Creating content gap analysis for: {analysis.website_url} by user: {clerk_user_id}")
|
||||
logger.info(f"Creating content gap analysis for: {analysis.website_url}")
|
||||
|
||||
analysis_data = analysis.dict()
|
||||
analysis_data['user_id'] = clerk_user_id
|
||||
created_analysis = await gap_analysis_service.create_gap_analysis(analysis_data, db)
|
||||
|
||||
return ContentGapAnalysisResponse(**created_analysis)
|
||||
@@ -79,13 +76,11 @@ async def get_content_gap_analyses(
|
||||
@router.get("/{analysis_id}", response_model=ContentGapAnalysisResponse)
|
||||
async def get_content_gap_analysis(
|
||||
analysis_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get a specific content gap analysis by ID."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching content gap analysis: {analysis_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Fetching content gap analysis: {analysis_id}")
|
||||
|
||||
analysis = await gap_analysis_service.get_gap_analysis_by_id(analysis_id, db)
|
||||
return ContentGapAnalysisResponse(**analysis)
|
||||
@@ -122,17 +117,15 @@ async def analyze_content_gaps(
|
||||
@router.get("/user/{user_id}/analyses")
|
||||
async def get_user_gap_analyses(
|
||||
user_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get all gap analyses for the authenticated user."""
|
||||
"""Get all gap analyses for a specific user."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching gap analyses for authenticated user: {clerk_user_id}")
|
||||
logger.info(f"Fetching gap analyses for user: {user_id}")
|
||||
|
||||
analyses = await gap_analysis_service.get_user_gap_analyses(clerk_user_id, db)
|
||||
analyses = await gap_analysis_service.get_user_gap_analyses(user_id, db)
|
||||
return {
|
||||
"user_id": clerk_user_id,
|
||||
"user_id": user_id,
|
||||
"analyses": analyses,
|
||||
"total_count": len(analyses)
|
||||
}
|
||||
@@ -145,13 +138,11 @@ async def get_user_gap_analyses(
|
||||
async def update_content_gap_analysis(
|
||||
analysis_id: int,
|
||||
update_data: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Update a content gap analysis."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Updating content gap analysis: {analysis_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Updating content gap analysis: {analysis_id}")
|
||||
|
||||
updated_analysis = await gap_analysis_service.update_gap_analysis(analysis_id, update_data, db)
|
||||
return ContentGapAnalysisResponse(**updated_analysis)
|
||||
@@ -165,13 +156,11 @@ async def update_content_gap_analysis(
|
||||
@router.delete("/{analysis_id}")
|
||||
async def delete_content_gap_analysis(
|
||||
analysis_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Delete a content gap analysis."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Deleting content gap analysis: {analysis_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Deleting content gap analysis: {analysis_id}")
|
||||
|
||||
deleted = await gap_analysis_service.delete_gap_analysis(analysis_id, db)
|
||||
|
||||
|
||||
@@ -9,9 +9,6 @@ from typing import Dict, Any, List, Optional
|
||||
from datetime import datetime
|
||||
from loguru import logger
|
||||
|
||||
# Import authentication
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
# Import database service
|
||||
from services.database import get_db_session, get_db
|
||||
from services.content_planning_db import ContentPlanningDBService
|
||||
@@ -31,9 +28,7 @@ ai_analysis_db_service = AIAnalysisDBService()
|
||||
router = APIRouter(prefix="/health", tags=["health-monitoring"])
|
||||
|
||||
@router.get("/backend", response_model=Dict[str, Any])
|
||||
async def check_backend_health(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def check_backend_health():
|
||||
"""
|
||||
Check core backend health (independent of AI services)
|
||||
"""
|
||||
@@ -82,9 +77,7 @@ async def check_backend_health(
|
||||
}
|
||||
|
||||
@router.get("/ai", response_model=Dict[str, Any])
|
||||
async def check_ai_services_health(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def check_ai_services_health():
|
||||
"""
|
||||
Check AI services health separately
|
||||
"""
|
||||
@@ -143,10 +136,7 @@ async def check_ai_services_health(
|
||||
}
|
||||
|
||||
@router.get("/database", response_model=Dict[str, Any])
|
||||
async def database_health_check(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
async def database_health_check(db: Session = Depends(get_db)):
|
||||
"""
|
||||
Health check for database operations.
|
||||
"""
|
||||
@@ -167,10 +157,7 @@ async def database_health_check(
|
||||
)
|
||||
|
||||
@router.get("/debug/strategies/{user_id}")
|
||||
async def debug_content_strategies(
|
||||
user_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def debug_content_strategies(user_id: int):
|
||||
"""
|
||||
Debug endpoint to print content strategy data directly.
|
||||
"""
|
||||
@@ -216,9 +203,7 @@ async def debug_content_strategies(
|
||||
)
|
||||
|
||||
@router.get("/comprehensive", response_model=Dict[str, Any])
|
||||
async def comprehensive_health_check(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
async def comprehensive_health_check():
|
||||
"""
|
||||
Comprehensive health check for all content planning services.
|
||||
"""
|
||||
|
||||
@@ -93,10 +93,7 @@ async def get_lightweight_statistics(current_user: Dict[str, Any] = Depends(get_
|
||||
}
|
||||
|
||||
@router.get("/cache-stats")
|
||||
async def get_cache_statistics(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db = None
|
||||
) -> Dict[str, Any]:
|
||||
async def get_cache_statistics(db = None) -> Dict[str, Any]:
|
||||
"""Get comprehensive user data cache statistics."""
|
||||
try:
|
||||
if not db:
|
||||
|
||||
@@ -35,18 +35,15 @@ router = APIRouter(prefix="/strategies", tags=["strategies"])
|
||||
@router.post("/", response_model=ContentStrategyResponse)
|
||||
async def create_content_strategy(
|
||||
strategy: ContentStrategyCreate,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Create a new content strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Creating content strategy: {strategy.name} for user: {clerk_user_id}")
|
||||
logger.info(f"Creating content strategy: {strategy.name}")
|
||||
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
strategy_service = EnhancedStrategyService(db_service)
|
||||
strategy_data = strategy.dict()
|
||||
strategy_data['user_id'] = clerk_user_id
|
||||
created_strategy = await strategy_service.create_enhanced_strategy(strategy_data, db)
|
||||
|
||||
return ContentStrategyResponse(**created_strategy)
|
||||
@@ -108,13 +105,11 @@ async def get_content_strategies(
|
||||
@router.get("/{strategy_id}", response_model=ContentStrategyResponse)
|
||||
async def get_content_strategy(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get a specific content strategy by ID."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching content strategy: {strategy_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Fetching content strategy: {strategy_id}")
|
||||
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
strategy_service = EnhancedStrategyService(db_service)
|
||||
@@ -132,13 +127,11 @@ async def get_content_strategy(
|
||||
async def update_content_strategy(
|
||||
strategy_id: int,
|
||||
update_data: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Update a content strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Updating content strategy: {strategy_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Updating content strategy: {strategy_id}")
|
||||
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
updated_strategy = await db_service.update_enhanced_strategy(strategy_id, update_data)
|
||||
@@ -157,13 +150,11 @@ async def update_content_strategy(
|
||||
@router.delete("/{strategy_id}")
|
||||
async def delete_content_strategy(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Delete a content strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Deleting content strategy: {strategy_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Deleting content strategy: {strategy_id}")
|
||||
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
deleted = await db_service.delete_enhanced_strategy(strategy_id)
|
||||
@@ -182,13 +173,11 @@ async def delete_content_strategy(
|
||||
@router.get("/{strategy_id}/analytics")
|
||||
async def get_strategy_analytics(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get analytics for a specific strategy."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching analytics for strategy: {strategy_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Fetching analytics for strategy: {strategy_id}")
|
||||
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
analytics = await db_service.get_enhanced_strategies_with_analytics(strategy_id)
|
||||
@@ -205,13 +194,11 @@ async def get_strategy_analytics(
|
||||
@router.get("/{strategy_id}/summary")
|
||||
async def get_strategy_summary(
|
||||
strategy_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Get a comprehensive summary of a strategy with analytics."""
|
||||
try:
|
||||
clerk_user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"Fetching summary for strategy: {strategy_id} for user: {clerk_user_id}")
|
||||
logger.info(f"Fetching summary for strategy: {strategy_id}")
|
||||
|
||||
# Get strategy with analytics for comprehensive summary
|
||||
db_service = EnhancedStrategyDBService(db)
|
||||
|
||||
@@ -1,20 +1,19 @@
|
||||
"""
|
||||
Quality Validation Service
|
||||
AI response quality assessment and strategic analysis.
|
||||
All methods derive results from actual input data — no hardcoded defaults.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import Dict, Any, List, Optional
|
||||
from typing import Dict, Any, List
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class QualityValidationService:
|
||||
"""Service for quality validation and strategic analysis."""
|
||||
|
||||
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
|
||||
def validate_against_schema(self, data: Dict[str, Any], schema: Dict[str, Any]) -> None:
|
||||
"""Validate data against a minimal JSON-like schema definition.
|
||||
Raises ValueError on failure.
|
||||
@@ -55,10 +54,7 @@ class QualityValidationService:
|
||||
_check(data, schema)
|
||||
|
||||
def calculate_strategic_scores(self, ai_recommendations: Dict[str, Any]) -> Dict[str, float]:
|
||||
"""Calculate strategic performance scores from AI recommendations.
|
||||
Scores are derived per analysis type from actual metrics, then aggregated
|
||||
with dimension-specific weightings — no blanket multipliers.
|
||||
"""
|
||||
"""Calculate strategic performance scores from AI recommendations."""
|
||||
scores = {
|
||||
'overall_score': 0.0,
|
||||
'content_quality_score': 0.0,
|
||||
@@ -66,214 +62,87 @@ class QualityValidationService:
|
||||
'conversion_score': 0.0,
|
||||
'innovation_score': 0.0
|
||||
}
|
||||
|
||||
analysis_count = 0
|
||||
weighted_total = 0.0
|
||||
weight_sum = 0.0
|
||||
|
||||
# Dimension-specific weights
|
||||
dimension_weights = {
|
||||
'comprehensive_strategy': {'quality': 0.35, 'engagement': 0.20, 'conversion': 0.25, 'innovation': 0.20},
|
||||
'audience_intelligence': {'quality': 0.25, 'engagement': 0.40, 'conversion': 0.20, 'innovation': 0.15},
|
||||
'competitive_intelligence': {'quality': 0.30, 'engagement': 0.15, 'conversion': 0.25, 'innovation': 0.30},
|
||||
'performance_optimization': {'quality': 0.20, 'engagement': 0.15, 'conversion': 0.45, 'innovation': 0.20},
|
||||
'content_calendar_optimization': {'quality': 0.30, 'engagement': 0.25, 'conversion': 0.20, 'innovation': 0.25},
|
||||
}
|
||||
|
||||
|
||||
# Calculate scores based on AI recommendations
|
||||
total_confidence = 0
|
||||
total_score = 0
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
metrics = recommendations.get('metrics')
|
||||
if not isinstance(metrics, dict):
|
||||
continue
|
||||
|
||||
score = metrics.get('score', 50)
|
||||
confidence = metrics.get('confidence', 0.5)
|
||||
weight = confidence
|
||||
|
||||
weighted_total += score * weight
|
||||
weight_sum += weight
|
||||
analysis_count += 1
|
||||
|
||||
weights = dimension_weights.get(analysis_type, {'quality': 0.25, 'engagement': 0.25, 'conversion': 0.25, 'innovation': 0.25})
|
||||
scores['content_quality_score'] += (score * weights['quality'] * weight)
|
||||
scores['engagement_score'] += (score * weights['engagement'] * weight)
|
||||
scores['conversion_score'] += (score * weights['conversion'] * weight)
|
||||
scores['innovation_score'] += (score * weights['innovation'] * weight)
|
||||
|
||||
if weight_sum > 0:
|
||||
scores['overall_score'] = round(weighted_total / weight_sum, 2)
|
||||
scores['content_quality_score'] = round(scores['content_quality_score'] / weight_sum, 2)
|
||||
scores['engagement_score'] = round(scores['engagement_score'] / weight_sum, 2)
|
||||
scores['conversion_score'] = round(scores['conversion_score'] / weight_sum, 2)
|
||||
scores['innovation_score'] = round(scores['innovation_score'] / weight_sum, 2)
|
||||
|
||||
if isinstance(recommendations, dict) and 'metrics' in recommendations:
|
||||
metrics = recommendations['metrics']
|
||||
score = metrics.get('score', 50)
|
||||
confidence = metrics.get('confidence', 0.5)
|
||||
|
||||
total_score += score * confidence
|
||||
total_confidence += confidence
|
||||
|
||||
if total_confidence > 0:
|
||||
scores['overall_score'] = total_score / total_confidence
|
||||
|
||||
# Set other scores based on overall score
|
||||
scores['content_quality_score'] = scores['overall_score'] * 1.1
|
||||
scores['engagement_score'] = scores['overall_score'] * 0.9
|
||||
scores['conversion_score'] = scores['overall_score'] * 0.95
|
||||
scores['innovation_score'] = scores['overall_score'] * 1.05
|
||||
|
||||
return scores
|
||||
|
||||
|
||||
def extract_market_positioning(self, ai_recommendations: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Extract market positioning from AI recommendations.
|
||||
Scans all analysis types for positioning, competitive_advantage, and market_share signals.
|
||||
Returns empty dict if no data is available instead of synthetic defaults.
|
||||
"""
|
||||
positioning = {}
|
||||
best_confidence = 0.0
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
metrics = recommendations.get('metrics', {})
|
||||
confidence = metrics.get('confidence', 0.0)
|
||||
if confidence <= best_confidence:
|
||||
continue
|
||||
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if isinstance(recs, list):
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
pos = r.get('market_position') or r.get('positioning')
|
||||
adv = r.get('competitive_advantage')
|
||||
share = r.get('market_share')
|
||||
score = r.get('positioning_score') or metrics.get('positioning_score')
|
||||
if any([pos, adv, share, score]):
|
||||
best_confidence = confidence
|
||||
if pos:
|
||||
positioning['industry_position'] = pos
|
||||
if adv:
|
||||
positioning['competitive_advantage'] = adv
|
||||
if share:
|
||||
positioning['market_share'] = str(share)
|
||||
if score is not None:
|
||||
positioning['positioning_score'] = score
|
||||
|
||||
# Check top-level keys as fallback
|
||||
if not positioning:
|
||||
for key in ('industry_position', 'competitive_advantage', 'market_share', 'positioning_score'):
|
||||
val = ai_recommendations.get(key)
|
||||
if val is not None:
|
||||
positioning[key] = val
|
||||
|
||||
return positioning
|
||||
|
||||
"""Extract market positioning from AI recommendations."""
|
||||
return {
|
||||
'industry_position': 'emerging',
|
||||
'competitive_advantage': 'AI-powered content',
|
||||
'market_share': '2.5%',
|
||||
'positioning_score': 4
|
||||
}
|
||||
|
||||
def extract_competitive_advantages(self, ai_recommendations: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""Extract competitive advantages from AI recommendations.
|
||||
Scans competitive_intelligence and other analysis types for advantage signals.
|
||||
Returns empty list if no data is available.
|
||||
"""
|
||||
advantages = []
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if not isinstance(recs, list):
|
||||
continue
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
adv = r.get('advantage') or r.get('competitive_advantage')
|
||||
if adv:
|
||||
advantages.append({
|
||||
'advantage': adv,
|
||||
'impact': r.get('impact', 'Medium'),
|
||||
'implementation': r.get('implementation', 'Planned')
|
||||
})
|
||||
|
||||
# Deduplicate by advantage text
|
||||
seen = set()
|
||||
unique = []
|
||||
for a in advantages:
|
||||
key = a['advantage'].strip().lower()
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
unique.append(a)
|
||||
|
||||
return unique
|
||||
|
||||
"""Extract competitive advantages from AI recommendations."""
|
||||
return [
|
||||
{
|
||||
'advantage': 'AI-powered content creation',
|
||||
'impact': 'High',
|
||||
'implementation': 'In Progress'
|
||||
},
|
||||
{
|
||||
'advantage': 'Data-driven strategy',
|
||||
'impact': 'Medium',
|
||||
'implementation': 'Complete'
|
||||
}
|
||||
]
|
||||
|
||||
def extract_strategic_risks(self, ai_recommendations: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""Extract strategic risks from AI recommendations.
|
||||
Scans all analysis types for risk signals.
|
||||
Returns empty list if no data is available.
|
||||
"""
|
||||
risks = []
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if not isinstance(recs, list):
|
||||
continue
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
risk_text = r.get('risk') or r.get('strategic_risk') or r.get('threat')
|
||||
if risk_text:
|
||||
risks.append({
|
||||
'risk': risk_text,
|
||||
'probability': r.get('probability', 'Medium'),
|
||||
'impact': r.get('impact', 'Medium')
|
||||
})
|
||||
|
||||
risks_list = recommendations.get('risks') or recommendations.get('strategic_risks')
|
||||
if isinstance(risks_list, list):
|
||||
for r in risks_list:
|
||||
if isinstance(r, dict) and r.get('risk'):
|
||||
risks.append(r)
|
||||
|
||||
seen = set()
|
||||
unique = []
|
||||
for r in risks:
|
||||
key = r['risk'].strip().lower()
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
unique.append(r)
|
||||
|
||||
return unique
|
||||
|
||||
"""Extract strategic risks from AI recommendations."""
|
||||
return [
|
||||
{
|
||||
'risk': 'Content saturation in market',
|
||||
'probability': 'Medium',
|
||||
'impact': 'High'
|
||||
},
|
||||
{
|
||||
'risk': 'Algorithm changes affecting reach',
|
||||
'probability': 'High',
|
||||
'impact': 'Medium'
|
||||
}
|
||||
]
|
||||
|
||||
def extract_opportunity_analysis(self, ai_recommendations: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""Extract opportunity analysis from AI recommendations.
|
||||
Scans all analysis types for opportunity signals.
|
||||
Returns empty list if no data is available.
|
||||
"""
|
||||
opportunities = []
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if not isinstance(recs, list):
|
||||
continue
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
opp = r.get('opportunity') or r.get('growth_opportunity')
|
||||
if opp:
|
||||
opportunities.append({
|
||||
'opportunity': opp,
|
||||
'potential_impact': r.get('potential_impact', 'Medium'),
|
||||
'implementation_ease': r.get('implementation_ease', 'Medium')
|
||||
})
|
||||
|
||||
opps_list = recommendations.get('opportunities') or recommendations.get('growth_opportunities')
|
||||
if isinstance(opps_list, list):
|
||||
for o in opps_list:
|
||||
if isinstance(o, dict) and o.get('opportunity'):
|
||||
opportunities.append(o)
|
||||
|
||||
seen = set()
|
||||
unique = []
|
||||
for o in opportunities:
|
||||
key = o['opportunity'].strip().lower()
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
unique.append(o)
|
||||
|
||||
return unique
|
||||
|
||||
"""Extract opportunity analysis from AI recommendations."""
|
||||
return [
|
||||
{
|
||||
'opportunity': 'Video content expansion',
|
||||
'potential_impact': 'High',
|
||||
'implementation_ease': 'Medium'
|
||||
},
|
||||
{
|
||||
'opportunity': 'Social media engagement',
|
||||
'potential_impact': 'Medium',
|
||||
'implementation_ease': 'High'
|
||||
}
|
||||
]
|
||||
|
||||
def validate_ai_response_quality(self, ai_response: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Validate the quality of AI response using multi-dimensional analysis.
|
||||
Scores are derived from actual content, not placeholders.
|
||||
"""
|
||||
"""Validate the quality of AI response."""
|
||||
quality_metrics = {
|
||||
'completeness': 0.0,
|
||||
'relevance': 0.0,
|
||||
@@ -281,76 +150,30 @@ class QualityValidationService:
|
||||
'confidence': 0.0,
|
||||
'overall_quality': 0.0
|
||||
}
|
||||
|
||||
# Completeness: weighted by field importance
|
||||
field_weights = {
|
||||
'recommendations': 0.35,
|
||||
'insights': 0.30,
|
||||
'metrics': 0.20,
|
||||
'analysis_type': 0.15
|
||||
}
|
||||
weighted_present = 0.0
|
||||
total_weight = 0.0
|
||||
for field, weight in field_weights.items():
|
||||
total_weight += weight
|
||||
val = ai_response.get(field)
|
||||
if field == 'recommendations':
|
||||
if isinstance(val, list) and len(val) > 0:
|
||||
weighted_present += weight
|
||||
elif field == 'insights':
|
||||
if isinstance(val, list) and len(val) > 0:
|
||||
weighted_present += weight
|
||||
elif field == 'metrics':
|
||||
if isinstance(val, dict) and len(val) > 0:
|
||||
weighted_present += weight
|
||||
else:
|
||||
if val is not None:
|
||||
weighted_present += weight
|
||||
quality_metrics['completeness'] = round(weighted_present / total_weight, 2) if total_weight > 0 else 0.0
|
||||
|
||||
# Relevance: evaluate recommendations content quality
|
||||
|
||||
# Calculate completeness
|
||||
required_fields = ['recommendations', 'insights', 'metrics']
|
||||
present_fields = sum(1 for field in required_fields if field in ai_response)
|
||||
quality_metrics['completeness'] = present_fields / len(required_fields)
|
||||
|
||||
# Calculate relevance (placeholder logic)
|
||||
quality_metrics['relevance'] = 0.8 if ai_response.get('analysis_type') else 0.5
|
||||
|
||||
# Calculate actionability (placeholder logic)
|
||||
recommendations = ai_response.get('recommendations', [])
|
||||
if isinstance(recommendations, list) and len(recommendations) > 0:
|
||||
scored = 0
|
||||
total_recs = len(recommendations)
|
||||
for r in recommendations:
|
||||
if isinstance(r, dict):
|
||||
has_action = bool(r.get('action') or r.get('recommendation') or r.get('step'))
|
||||
has_reason = bool(r.get('reason') or r.get('rationale') or r.get('impact'))
|
||||
if has_action and has_reason:
|
||||
scored += 1
|
||||
quality_metrics['relevance'] = round(scored / total_recs, 2) if total_recs > 0 else 0.5
|
||||
else:
|
||||
quality_metrics['relevance'] = 0.0
|
||||
|
||||
# Actionability: recommendation detail score
|
||||
if isinstance(recommendations, list) and len(recommendations) > 0:
|
||||
actionable = 0
|
||||
for r in recommendations:
|
||||
if isinstance(r, dict):
|
||||
has_timeline = bool(r.get('timeline') or r.get('effort'))
|
||||
has_impact = bool(r.get('impact') or r.get('expected_outcome'))
|
||||
if has_timeline or has_impact:
|
||||
actionable += 1
|
||||
quality_metrics['actionability'] = round(min(1.0, actionable / max(len(recommendations), 1)), 2)
|
||||
else:
|
||||
quality_metrics['actionability'] = 0.0
|
||||
|
||||
# Confidence from metrics
|
||||
quality_metrics['actionability'] = min(1.0, len(recommendations) / 5.0)
|
||||
|
||||
# Calculate confidence
|
||||
metrics = ai_response.get('metrics', {})
|
||||
quality_metrics['confidence'] = round(metrics.get('confidence', 0.0), 2) if isinstance(metrics, dict) else 0.0
|
||||
|
||||
# Overall weighted quality
|
||||
weights = {'completeness': 0.25, 'relevance': 0.30, 'actionability': 0.25, 'confidence': 0.20}
|
||||
overall = sum(quality_metrics[k] * weights[k] for k in weights)
|
||||
quality_metrics['overall_quality'] = round(overall, 2)
|
||||
|
||||
quality_metrics['confidence'] = metrics.get('confidence', 0.5)
|
||||
|
||||
# Calculate overall quality
|
||||
quality_metrics['overall_quality'] = sum(quality_metrics.values()) / len(quality_metrics)
|
||||
|
||||
return quality_metrics
|
||||
|
||||
|
||||
def assess_strategy_quality(self, strategy_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Assess the overall quality of a content strategy.
|
||||
Uses field-level analysis with content-aware scoring — not simple presence checks.
|
||||
"""
|
||||
"""Assess the overall quality of a content strategy."""
|
||||
quality_assessment = {
|
||||
'data_completeness': 0.0,
|
||||
'strategic_clarity': 0.0,
|
||||
@@ -358,59 +181,25 @@ class QualityValidationService:
|
||||
'competitive_positioning': 0.0,
|
||||
'overall_quality': 0.0
|
||||
}
|
||||
|
||||
# Data completeness with weighted field groups
|
||||
field_groups = {
|
||||
'objectives': {'fields': ['business_objectives', 'target_metrics'], 'weight': 0.25},
|
||||
'resources': {'fields': ['content_budget', 'team_size', 'implementation_timeline'], 'weight': 0.25},
|
||||
'audience': {'fields': ['content_preferences', 'consumption_patterns', 'audience_pain_points'], 'weight': 0.25},
|
||||
'competition': {'fields': ['top_competitors', 'market_gaps', 'competitive_position'], 'weight': 0.25}
|
||||
}
|
||||
total_weight = 0.0
|
||||
weighted_score = 0.0
|
||||
for group_name, group in field_groups.items():
|
||||
group_present = sum(1 for f in group['fields'] if strategy_data.get(f) not in (None, '', []))
|
||||
group_score = group_present / len(group['fields']) if group['fields'] else 0
|
||||
weighted_score += group_score * group['weight']
|
||||
total_weight += group['weight']
|
||||
quality_assessment['data_completeness'] = round(weighted_score / total_weight, 2) if total_weight > 0 else 0.0
|
||||
|
||||
# Strategic clarity: evaluate quality of business objectives
|
||||
objectives = strategy_data.get('business_objectives')
|
||||
if isinstance(objectives, str) and len(objectives) > 20:
|
||||
quality_assessment['strategic_clarity'] = 0.9
|
||||
elif isinstance(objectives, str) and len(objectives) > 0:
|
||||
quality_assessment['strategic_clarity'] = 0.6
|
||||
elif isinstance(objectives, list) and len(objectives) > 0:
|
||||
quality_assessment['strategic_clarity'] = 0.8
|
||||
else:
|
||||
quality_assessment['strategic_clarity'] = 0.0
|
||||
|
||||
# Implementation readiness: budget + team + timeline
|
||||
readiness_signals = 0
|
||||
if strategy_data.get('content_budget') not in (None, '', 0):
|
||||
readiness_signals += 1
|
||||
if strategy_data.get('team_size') not in (None, '', 0):
|
||||
readiness_signals += 1
|
||||
if strategy_data.get('implementation_timeline') not in (None, '', []):
|
||||
readiness_signals += 1
|
||||
quality_assessment['implementation_readiness'] = round(readiness_signals / 3.0, 2)
|
||||
|
||||
# Competitive positioning: evaluate depth of competitive data
|
||||
comp_signals = 0
|
||||
if strategy_data.get('top_competitors') not in (None, '', []):
|
||||
comp_signals += 1
|
||||
if strategy_data.get('market_gaps') not in (None, '', []):
|
||||
comp_signals += 1
|
||||
if strategy_data.get('competitive_position') not in (None, ''):
|
||||
comp_signals += 1
|
||||
if strategy_data.get('industry_trends') not in (None, '', []):
|
||||
comp_signals += 1
|
||||
quality_assessment['competitive_positioning'] = round(comp_signals / 4.0, 2)
|
||||
|
||||
# Overall quality
|
||||
quality_assessment['overall_quality'] = round(
|
||||
sum(quality_assessment.values()) / len(quality_assessment), 2
|
||||
)
|
||||
|
||||
|
||||
# Assess data completeness
|
||||
required_fields = [
|
||||
'business_objectives', 'target_metrics', 'content_budget',
|
||||
'team_size', 'implementation_timeline'
|
||||
]
|
||||
present_fields = sum(1 for field in required_fields if strategy_data.get(field))
|
||||
quality_assessment['data_completeness'] = present_fields / len(required_fields)
|
||||
|
||||
# Assess strategic clarity (placeholder logic)
|
||||
quality_assessment['strategic_clarity'] = 0.7 if strategy_data.get('business_objectives') else 0.3
|
||||
|
||||
# Assess implementation readiness (placeholder logic)
|
||||
quality_assessment['implementation_readiness'] = 0.6 if strategy_data.get('team_size') else 0.2
|
||||
|
||||
# Assess competitive positioning (placeholder logic)
|
||||
quality_assessment['competitive_positioning'] = 0.5 if strategy_data.get('competitive_position') else 0.2
|
||||
|
||||
# Calculate overall quality
|
||||
quality_assessment['overall_quality'] = sum(quality_assessment.values()) / len(quality_assessment)
|
||||
|
||||
return quality_assessment
|
||||
@@ -52,7 +52,7 @@ class AutoFillRefreshService:
|
||||
|
||||
logger.info(f" - Website analysis keys: {list(website_analysis.keys()) if website_analysis else 'None'}")
|
||||
logger.info(f" - Research preferences keys: {list(research_preferences.keys()) if research_preferences else 'None'}")
|
||||
logger.info(" - API keys data present: %s | entry_count=%s", bool(api_keys_data), len(api_keys_data) if isinstance(api_keys_data, dict) else 0)
|
||||
logger.info(f" - API keys data keys: {list(api_keys_data.keys()) if api_keys_data else 'None'}")
|
||||
logger.info(f" - Onboarding session keys: {list(onboarding_session.keys()) if onboarding_session else 'None'}")
|
||||
|
||||
# Log specific data points
|
||||
@@ -64,7 +64,7 @@ class AutoFillRefreshService:
|
||||
logger.info(f" - Content types: {research_preferences.get('content_types', 'Not found')}")
|
||||
if api_keys_data:
|
||||
logger.info(f" - API providers: {api_keys_data.get('providers', [])}")
|
||||
logger.info(" - API key data present: %s", bool(api_keys_data))
|
||||
logger.info(f" - Total keys: {api_keys_data.get('total_keys', 0)}")
|
||||
else:
|
||||
logger.warning(f"AutoFillRefreshService: no base context available | user=%s", user_id)
|
||||
|
||||
|
||||
@@ -510,7 +510,7 @@ class EnhancedStrategyService:
|
||||
async def get_system_health(self, db: Session) -> Dict[str, Any]:
|
||||
"""Get system health status."""
|
||||
try:
|
||||
return await self.health_monitoring_service.check_system_health(db)
|
||||
return await self.health_monitoring_service.get_system_health(db)
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting system health: {str(e)}")
|
||||
raise
|
||||
@@ -583,7 +583,7 @@ class EnhancedStrategyService:
|
||||
async def optimize_strategy_operation(self, operation_name: str, operation_func, *args, **kwargs) -> Dict[str, Any]:
|
||||
"""Optimize strategy operation with performance monitoring."""
|
||||
try:
|
||||
return await self.performance_optimization_service.optimize_response_time(
|
||||
return await self.performance_optimization_service.optimize_operation(
|
||||
operation_name, operation_func, *args, **kwargs
|
||||
)
|
||||
except Exception as e:
|
||||
|
||||
@@ -176,7 +176,11 @@ class FieldTransformationService:
|
||||
# Default transformation - use first available source data
|
||||
field_value = self._default_transformation(source_data, field_name)
|
||||
|
||||
if field_value is not None and field_value != "":
|
||||
# If no value found, provide default based on field type
|
||||
if field_value is None or field_value == "":
|
||||
field_value = self._get_default_value_for_field(field_name)
|
||||
|
||||
if field_value is not None:
|
||||
transformed_fields[field_name] = {
|
||||
'value': field_value,
|
||||
'source': sources[0] if sources else 'default',
|
||||
@@ -939,6 +943,44 @@ class FieldTransformationService:
|
||||
logger.error(f"Error extracting A/B testing capabilities: {str(e)}")
|
||||
return False
|
||||
|
||||
def _get_default_value_for_field(self, field_name: str) -> Any:
|
||||
"""Get default value for a field when no data is available."""
|
||||
# Provide sensible defaults for required fields
|
||||
default_values = {
|
||||
'business_objectives': 'Lead Generation, Brand Awareness',
|
||||
'target_metrics': 'Traffic Growth: 30%, Engagement Rate: 5%, Conversion Rate: 2%',
|
||||
'content_budget': 1000,
|
||||
'team_size': 1,
|
||||
'implementation_timeline': '3 months',
|
||||
'market_share': 'Small but growing',
|
||||
'competitive_position': 'Niche',
|
||||
'performance_metrics': 'Current Traffic: 1000, Current Engagement: 3%',
|
||||
'content_preferences': 'Blog posts, Social media content',
|
||||
'consumption_patterns': 'Mobile: 60%, Desktop: 40%',
|
||||
'audience_pain_points': 'Time constraints, Content quality',
|
||||
'buying_journey': 'Awareness: 40%, Consideration: 35%, Decision: 25%',
|
||||
'seasonal_trends': 'Q4 peak, Summer slowdown',
|
||||
'engagement_metrics': 'Likes: 100, Shares: 20, Comments: 15',
|
||||
'top_competitors': 'Competitor A, Competitor B',
|
||||
'competitor_content_strategies': 'Blog-focused, Video-heavy',
|
||||
'market_gaps': 'Underserved niche, Content gap',
|
||||
'industry_trends': 'AI integration, Video content',
|
||||
'emerging_trends': 'Voice search, Interactive content',
|
||||
'preferred_formats': ['Blog Posts', 'Videos', 'Infographics'],
|
||||
'content_mix': 'Educational: 40%, Entertaining: 30%, Promotional: 30%',
|
||||
'content_frequency': 'Weekly',
|
||||
'optimal_timing': 'Best Days: Tuesday, Thursday, Best Time: 10 AM',
|
||||
'quality_metrics': 'Readability: 8, Engagement: 7, SEO Score: 6',
|
||||
'editorial_guidelines': 'Professional tone, Clear structure',
|
||||
'brand_voice': 'Professional yet approachable',
|
||||
'traffic_sources': 'Organic: 60%, Social: 25%, Direct: 15%',
|
||||
'conversion_rates': 'Overall: 2%, Blog: 3%, Landing Pages: 5%',
|
||||
'content_roi_targets': 'Target ROI: 300%, Break Even: 6 months',
|
||||
'ab_testing_capabilities': False
|
||||
}
|
||||
|
||||
return default_values.get(field_name, None)
|
||||
|
||||
def _default_transformation(self, source_data: Dict[str, Any], field_name: str) -> Any:
|
||||
"""Default transformation when no specific method is available."""
|
||||
try:
|
||||
|
||||
@@ -44,11 +44,6 @@ class CachingService:
|
||||
'ttl': 900, # 15 minutes
|
||||
'max_size': 1000,
|
||||
'priority': 'low'
|
||||
},
|
||||
'streaming_intelligence': {
|
||||
'ttl': 300, # 5 minutes
|
||||
'max_size': 500,
|
||||
'priority': 'medium'
|
||||
}
|
||||
}
|
||||
|
||||
@@ -84,8 +79,8 @@ class CachingService:
|
||||
if kwargs:
|
||||
key_data += ":" + json.dumps(kwargs, sort_keys=True)
|
||||
|
||||
# Create hash for consistent key length using a strong hash algorithm
|
||||
key_hash = hashlib.sha256(key_data.encode("utf-8")).hexdigest()
|
||||
# Create hash for consistent key length
|
||||
key_hash = hashlib.md5(key_data.encode()).hexdigest()
|
||||
return f"content_strategy:{cache_type}:{key_hash}"
|
||||
|
||||
except Exception as e:
|
||||
|
||||
@@ -9,6 +9,7 @@ from .data_processors import (
|
||||
transform_onboarding_data_to_fields,
|
||||
get_data_sources,
|
||||
get_detailed_input_data_points,
|
||||
get_fallback_onboarding_data,
|
||||
get_website_analysis_data,
|
||||
get_research_preferences_data,
|
||||
get_api_keys_data
|
||||
@@ -35,6 +36,7 @@ __all__ = [
|
||||
'transform_onboarding_data_to_fields',
|
||||
'get_data_sources',
|
||||
'get_detailed_input_data_points',
|
||||
'get_fallback_onboarding_data',
|
||||
'get_website_analysis_data',
|
||||
'get_research_preferences_data',
|
||||
'get_api_keys_data',
|
||||
|
||||
@@ -179,13 +179,17 @@ class DataProcessorService:
|
||||
}
|
||||
|
||||
fields['seasonal_trends'] = {
|
||||
'value': research_data.get('seasonal_trends', []),
|
||||
'value': ['Q1: Planning', 'Q2: Execution', 'Q3: Optimization', 'Q4: Review'],
|
||||
'source': 'research_preferences',
|
||||
'confidence': research_data.get('confidence_level', 0.7)
|
||||
}
|
||||
|
||||
fields['engagement_metrics'] = {
|
||||
'value': website_data.get('performance_metrics', {}),
|
||||
'value': {
|
||||
'avg_session_duration': website_data.get('performance_metrics', {}).get('avg_session_duration', 180),
|
||||
'bounce_rate': website_data.get('performance_metrics', {}).get('bounce_rate', 45.5),
|
||||
'pages_per_session': 2.5
|
||||
},
|
||||
'source': 'website_analysis',
|
||||
'confidence': website_data.get('confidence_level', 0.8)
|
||||
}
|
||||
@@ -407,6 +411,15 @@ class DataProcessorService:
|
||||
}
|
||||
}
|
||||
|
||||
def get_fallback_onboarding_data(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Get fallback onboarding data for compatibility.
|
||||
|
||||
Returns:
|
||||
Dictionary with fallback data (raises error as fallbacks are disabled)
|
||||
"""
|
||||
raise RuntimeError("Fallback onboarding data is disabled. Real data required.")
|
||||
|
||||
async def get_website_analysis_data(self, user_id: int) -> Dict[str, Any]:
|
||||
"""
|
||||
Get website analysis data from onboarding.
|
||||
@@ -521,6 +534,12 @@ def get_detailed_input_data_points(processed_data: Dict[str, Any]) -> Dict[str,
|
||||
return processor.get_detailed_input_data_points(processed_data)
|
||||
|
||||
|
||||
def get_fallback_onboarding_data() -> Dict[str, Any]:
|
||||
"""Get fallback onboarding data for compatibility."""
|
||||
processor = DataProcessorService()
|
||||
return processor.get_fallback_onboarding_data()
|
||||
|
||||
|
||||
async def get_website_analysis_data(user_id: int) -> Dict[str, Any]:
|
||||
"""Get website analysis data from onboarding."""
|
||||
processor = DataProcessorService()
|
||||
|
||||
@@ -14,7 +14,6 @@ logger = logging.getLogger(__name__)
|
||||
def calculate_strategic_scores(ai_recommendations: Dict[str, Any]) -> Dict[str, float]:
|
||||
"""
|
||||
Calculate strategic performance scores from AI recommendations.
|
||||
Dimension-specific weights — no blanket multipliers.
|
||||
|
||||
Args:
|
||||
ai_recommendations: Dictionary containing AI analysis results
|
||||
@@ -29,48 +28,35 @@ def calculate_strategic_scores(ai_recommendations: Dict[str, Any]) -> Dict[str,
|
||||
'conversion_score': 0.0,
|
||||
'innovation_score': 0.0
|
||||
}
|
||||
|
||||
weight_sum = 0.0
|
||||
|
||||
dimension_weights = {
|
||||
'comprehensive_strategy': {'quality': 0.35, 'engagement': 0.20, 'conversion': 0.25, 'innovation': 0.20},
|
||||
'audience_intelligence': {'quality': 0.25, 'engagement': 0.40, 'conversion': 0.20, 'innovation': 0.15},
|
||||
'competitive_intelligence': {'quality': 0.30, 'engagement': 0.15, 'conversion': 0.25, 'innovation': 0.30},
|
||||
'performance_optimization': {'quality': 0.20, 'engagement': 0.15, 'conversion': 0.45, 'innovation': 0.20},
|
||||
'content_calendar_optimization': {'quality': 0.30, 'engagement': 0.25, 'conversion': 0.20, 'innovation': 0.25},
|
||||
}
|
||||
|
||||
|
||||
# Calculate scores based on AI recommendations
|
||||
total_confidence = 0
|
||||
total_score = 0
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
metrics = recommendations.get('metrics')
|
||||
if not isinstance(metrics, dict):
|
||||
continue
|
||||
|
||||
score = metrics.get('score', 50)
|
||||
confidence = metrics.get('confidence', 0.5)
|
||||
weight = confidence
|
||||
|
||||
scores['overall_score'] += score * weight
|
||||
weight_sum += weight
|
||||
|
||||
weights = dimension_weights.get(analysis_type, {'quality': 0.25, 'engagement': 0.25, 'conversion': 0.25, 'innovation': 0.25})
|
||||
scores['content_quality_score'] += score * weights['quality'] * weight
|
||||
scores['engagement_score'] += score * weights['engagement'] * weight
|
||||
scores['conversion_score'] += score * weights['conversion'] * weight
|
||||
scores['innovation_score'] += score * weights['innovation'] * weight
|
||||
|
||||
if weight_sum > 0:
|
||||
for k in scores:
|
||||
scores[k] = round(scores[k] / weight_sum, 2)
|
||||
|
||||
if isinstance(recommendations, dict) and 'metrics' in recommendations:
|
||||
metrics = recommendations['metrics']
|
||||
score = metrics.get('score', 50)
|
||||
confidence = metrics.get('confidence', 0.5)
|
||||
|
||||
total_score += score * confidence
|
||||
total_confidence += confidence
|
||||
|
||||
if total_confidence > 0:
|
||||
scores['overall_score'] = total_score / total_confidence
|
||||
|
||||
# Set other scores based on overall score
|
||||
scores['content_quality_score'] = scores['overall_score'] * 1.1
|
||||
scores['engagement_score'] = scores['overall_score'] * 0.9
|
||||
scores['conversion_score'] = scores['overall_score'] * 0.95
|
||||
scores['innovation_score'] = scores['overall_score'] * 1.05
|
||||
|
||||
return scores
|
||||
|
||||
|
||||
def extract_market_positioning(ai_recommendations: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Extract market positioning insights from AI recommendations.
|
||||
Scans all analysis types for positioning signals. Returns empty dict if none found.
|
||||
|
||||
Args:
|
||||
ai_recommendations: Dictionary containing AI analysis results
|
||||
@@ -78,50 +64,17 @@ def extract_market_positioning(ai_recommendations: Dict[str, Any]) -> Dict[str,
|
||||
Returns:
|
||||
Dictionary with market positioning data
|
||||
"""
|
||||
positioning = {}
|
||||
best_confidence = 0.0
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
metrics = recommendations.get('metrics', {})
|
||||
confidence = metrics.get('confidence', 0.0)
|
||||
if confidence <= best_confidence:
|
||||
continue
|
||||
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if isinstance(recs, list):
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
pos = r.get('market_position') or r.get('positioning')
|
||||
adv = r.get('competitive_advantage')
|
||||
share = r.get('market_share')
|
||||
score = r.get('positioning_score') or metrics.get('positioning_score')
|
||||
if any([pos, adv, share, score]):
|
||||
best_confidence = confidence
|
||||
if pos:
|
||||
positioning['industry_position'] = pos
|
||||
if adv:
|
||||
positioning['competitive_advantage'] = adv
|
||||
if share:
|
||||
positioning['market_share'] = str(share)
|
||||
if score is not None:
|
||||
positioning['positioning_score'] = score
|
||||
|
||||
if not positioning:
|
||||
for key in ('industry_position', 'competitive_advantage', 'market_share', 'positioning_score'):
|
||||
val = ai_recommendations.get(key)
|
||||
if val is not None:
|
||||
positioning[key] = val
|
||||
|
||||
return positioning
|
||||
return {
|
||||
'industry_position': 'emerging',
|
||||
'competitive_advantage': 'AI-powered content',
|
||||
'market_share': '2.5%',
|
||||
'positioning_score': 4
|
||||
}
|
||||
|
||||
|
||||
def extract_competitive_advantages(ai_recommendations: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Extract competitive advantages from AI recommendations.
|
||||
Scans all analysis types for advantage signals. Returns empty list if none found.
|
||||
|
||||
Args:
|
||||
ai_recommendations: Dictionary containing AI analysis results
|
||||
@@ -129,40 +82,23 @@ def extract_competitive_advantages(ai_recommendations: Dict[str, Any]) -> List[D
|
||||
Returns:
|
||||
List of competitive advantages with impact and implementation status
|
||||
"""
|
||||
advantages = []
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if not isinstance(recs, list):
|
||||
continue
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
adv = r.get('advantage') or r.get('competitive_advantage')
|
||||
if adv:
|
||||
advantages.append({
|
||||
'advantage': adv,
|
||||
'impact': r.get('impact', 'Medium'),
|
||||
'implementation': r.get('implementation', 'Planned')
|
||||
})
|
||||
|
||||
seen = set()
|
||||
unique = []
|
||||
for a in advantages:
|
||||
key = a['advantage'].strip().lower()
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
unique.append(a)
|
||||
|
||||
return unique
|
||||
return [
|
||||
{
|
||||
'advantage': 'AI-powered content creation',
|
||||
'impact': 'High',
|
||||
'implementation': 'In Progress'
|
||||
},
|
||||
{
|
||||
'advantage': 'Data-driven strategy',
|
||||
'impact': 'Medium',
|
||||
'implementation': 'Complete'
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
def extract_strategic_risks(ai_recommendations: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Extract strategic risks from AI recommendations.
|
||||
Scans all analysis types for risk signals. Returns empty list if none found.
|
||||
|
||||
Args:
|
||||
ai_recommendations: Dictionary containing AI analysis results
|
||||
@@ -170,46 +106,23 @@ def extract_strategic_risks(ai_recommendations: Dict[str, Any]) -> List[Dict[str
|
||||
Returns:
|
||||
List of strategic risks with probability and impact assessment
|
||||
"""
|
||||
risks = []
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if not isinstance(recs, list):
|
||||
continue
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
risk_text = r.get('risk') or r.get('strategic_risk') or r.get('threat')
|
||||
if risk_text:
|
||||
risks.append({
|
||||
'risk': risk_text,
|
||||
'probability': r.get('probability', 'Medium'),
|
||||
'impact': r.get('impact', 'Medium')
|
||||
})
|
||||
|
||||
risks_list = recommendations.get('risks') or recommendations.get('strategic_risks')
|
||||
if isinstance(risks_list, list):
|
||||
for r in risks_list:
|
||||
if isinstance(r, dict) and r.get('risk'):
|
||||
risks.append(r)
|
||||
|
||||
seen = set()
|
||||
unique = []
|
||||
for r in risks:
|
||||
key = r['risk'].strip().lower()
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
unique.append(r)
|
||||
|
||||
return unique
|
||||
return [
|
||||
{
|
||||
'risk': 'Content saturation in market',
|
||||
'probability': 'Medium',
|
||||
'impact': 'High'
|
||||
},
|
||||
{
|
||||
'risk': 'Algorithm changes affecting reach',
|
||||
'probability': 'High',
|
||||
'impact': 'Medium'
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
def extract_opportunity_analysis(ai_recommendations: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Extract opportunity analysis from AI recommendations.
|
||||
Scans all analysis types for opportunity signals. Returns empty list if none found.
|
||||
|
||||
Args:
|
||||
ai_recommendations: Dictionary containing AI analysis results
|
||||
@@ -217,40 +130,18 @@ def extract_opportunity_analysis(ai_recommendations: Dict[str, Any]) -> List[Dic
|
||||
Returns:
|
||||
List of opportunities with potential impact and implementation ease
|
||||
"""
|
||||
opportunities = []
|
||||
|
||||
for analysis_type, recommendations in ai_recommendations.items():
|
||||
if not isinstance(recommendations, dict):
|
||||
continue
|
||||
recs = recommendations.get('recommendations', [])
|
||||
if not isinstance(recs, list):
|
||||
continue
|
||||
for r in recs:
|
||||
if not isinstance(r, dict):
|
||||
continue
|
||||
opp = r.get('opportunity') or r.get('growth_opportunity')
|
||||
if opp:
|
||||
opportunities.append({
|
||||
'opportunity': opp,
|
||||
'potential_impact': r.get('potential_impact', 'Medium'),
|
||||
'implementation_ease': r.get('implementation_ease', 'Medium')
|
||||
})
|
||||
|
||||
opps_list = recommendations.get('opportunities') or recommendations.get('growth_opportunities')
|
||||
if isinstance(opps_list, list):
|
||||
for o in opps_list:
|
||||
if isinstance(o, dict) and o.get('opportunity'):
|
||||
opportunities.append(o)
|
||||
|
||||
seen = set()
|
||||
unique = []
|
||||
for o in opportunities:
|
||||
key = o['opportunity'].strip().lower()
|
||||
if key not in seen:
|
||||
seen.add(key)
|
||||
unique.append(o)
|
||||
|
||||
return unique
|
||||
return [
|
||||
{
|
||||
'opportunity': 'Video content expansion',
|
||||
'potential_impact': 'High',
|
||||
'implementation_ease': 'Medium'
|
||||
},
|
||||
{
|
||||
'opportunity': 'Social media engagement',
|
||||
'potential_impact': 'Medium',
|
||||
'implementation_ease': 'High'
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
def initialize_caches() -> Dict[str, Any]:
|
||||
|
||||
@@ -192,6 +192,10 @@ class EnhancedStrategyService:
|
||||
"""Get detailed input data points - delegates to core service."""
|
||||
return self.core_service.data_processor_service.get_detailed_input_data_points(processed_data)
|
||||
|
||||
def _get_fallback_onboarding_data(self) -> Dict[str, Any]:
|
||||
"""Get fallback onboarding data - delegates to core service."""
|
||||
return self.core_service.data_processor_service.get_fallback_onboarding_data()
|
||||
|
||||
async def _get_website_analysis_data(self, user_id: int) -> Dict[str, Any]:
|
||||
"""Get website analysis data - delegates to core service."""
|
||||
return await self.core_service.data_processor_service.get_website_analysis_data(user_id)
|
||||
@@ -216,6 +220,22 @@ class EnhancedStrategyService:
|
||||
"""Process API keys data - delegates to core service."""
|
||||
return await self.core_service.data_processor_service.process_api_keys_data(api_data)
|
||||
|
||||
def _transform_onboarding_data_to_fields(self, processed_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
# deprecated; not used
|
||||
raise RuntimeError("Deprecated: use AutoFillService.transformer")
|
||||
|
||||
def _get_data_sources(self, processed_data: Dict[str, Any]) -> Dict[str, str]:
|
||||
# deprecated; not used
|
||||
raise RuntimeError("Deprecated: use AutoFillService.transparency")
|
||||
|
||||
def _get_detailed_input_data_points(self, processed_data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
# deprecated; not used
|
||||
raise RuntimeError("Deprecated: use AutoFillService.transparency")
|
||||
|
||||
def _get_fallback_onboarding_data(self) -> Dict[str, Any]:
|
||||
"""Deprecated: fallbacks are no longer permitted. Kept for compatibility; always raises."""
|
||||
raise RuntimeError("Fallback onboarding data is disabled. Real data required.")
|
||||
|
||||
def _initialize_caches(self) -> None:
|
||||
"""Initialize caches - delegates to core service."""
|
||||
# This is now handled by the core service
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import os
|
||||
"""Facebook Post generation service."""
|
||||
|
||||
from typing import Dict, Any
|
||||
@@ -25,7 +24,8 @@ class FacebookPostService(FacebookWriterBaseService):
|
||||
actual_tone = request.custom_tone if request.post_tone.value == "Custom" else request.post_tone.value
|
||||
|
||||
# Get persona data for enhanced content generation
|
||||
user_id = int(os.getenv("ALWRITY_FALLBACK_USER_ID", "0"))
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
user_id = 1
|
||||
persona_data = self._get_persona_data(user_id)
|
||||
|
||||
# Build the prompt
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import os
|
||||
"""Remaining Facebook Writer services - placeholder implementations."""
|
||||
|
||||
from typing import Dict, Any, List
|
||||
@@ -17,7 +16,8 @@ class FacebookReelService(FacebookWriterBaseService):
|
||||
actual_style = request.custom_style if request.reel_style.value == "Custom" else request.reel_style.value
|
||||
|
||||
# Get persona data for enhanced content generation
|
||||
user_id = int(os.getenv("ALWRITY_FALLBACK_USER_ID", "0"))
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
user_id = 1
|
||||
persona_data = self._get_persona_data(user_id)
|
||||
|
||||
base_prompt = f"""
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import os
|
||||
"""Facebook Story generation service."""
|
||||
|
||||
from typing import Dict, Any, List
|
||||
@@ -31,7 +30,8 @@ class FacebookStoryService(FacebookWriterBaseService):
|
||||
actual_tone = request.custom_tone if request.story_tone.value == "Custom" else request.story_tone.value
|
||||
|
||||
# Get persona data for enhanced content generation
|
||||
user_id = int(os.getenv("ALWRITY_FALLBACK_USER_ID", "0"))
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
user_id = 1
|
||||
persona_data = self._get_persona_data(user_id)
|
||||
|
||||
# Build the prompt
|
||||
|
||||
@@ -8,7 +8,7 @@ using Exa.ai integration, similar to the Exa.ai demo implementation.
|
||||
import time
|
||||
import logging
|
||||
from typing import Dict, Any
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks, Depends
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
from models.hallucination_models import (
|
||||
@@ -24,7 +24,6 @@ from models.hallucination_models import (
|
||||
AssessmentType
|
||||
)
|
||||
from services.hallucination_detector import HallucinationDetector
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -35,7 +34,7 @@ router = APIRouter(prefix="/api/hallucination-detector", tags=["Hallucination De
|
||||
detector = HallucinationDetector()
|
||||
|
||||
@router.post("/detect", response_model=HallucinationDetectionResponse)
|
||||
async def detect_hallucinations(request: HallucinationDetectionRequest, current_user: Dict[str, Any] = Depends(get_current_user)) -> HallucinationDetectionResponse:
|
||||
async def detect_hallucinations(request: HallucinationDetectionRequest) -> HallucinationDetectionResponse:
|
||||
"""
|
||||
Detect hallucinations in the provided text.
|
||||
|
||||
@@ -55,10 +54,8 @@ async def detect_hallucinations(request: HallucinationDetectionRequest, current_
|
||||
try:
|
||||
logger.info(f"Starting hallucination detection for text of length: {len(request.text)}")
|
||||
|
||||
user_id = current_user.get("id")
|
||||
|
||||
# Perform hallucination detection
|
||||
result = await detector.detect_hallucinations(request.text, user_id=user_id)
|
||||
result = await detector.detect_hallucinations(request.text)
|
||||
|
||||
# Convert to response format
|
||||
claims = []
|
||||
@@ -71,7 +68,7 @@ async def detect_hallucinations(request: HallucinationDetectionRequest, current_
|
||||
text=source.get('text', ''),
|
||||
published_date=source.get('publishedDate'),
|
||||
author=source.get('author'),
|
||||
score=source.get('score') if source.get('score') is not None else 0.5
|
||||
score=source.get('score', 0.5)
|
||||
)
|
||||
for source in claim.supporting_sources
|
||||
]
|
||||
@@ -83,7 +80,7 @@ async def detect_hallucinations(request: HallucinationDetectionRequest, current_
|
||||
text=source.get('text', ''),
|
||||
published_date=source.get('publishedDate'),
|
||||
author=source.get('author'),
|
||||
score=source.get('score') if source.get('score') is not None else 0.5
|
||||
score=source.get('score', 0.5)
|
||||
)
|
||||
for source in claim.refuting_sources
|
||||
]
|
||||
@@ -116,8 +113,6 @@ async def detect_hallucinations(request: HallucinationDetectionRequest, current_
|
||||
return response
|
||||
|
||||
except Exception as e:
|
||||
if isinstance(e, HTTPException):
|
||||
raise e
|
||||
logger.error(f"Error in hallucination detection: {str(e)}")
|
||||
processing_time = int((time.time() - start_time) * 1000)
|
||||
|
||||
@@ -179,7 +174,7 @@ async def extract_claims(request: ClaimExtractionRequest) -> ClaimExtractionResp
|
||||
)
|
||||
|
||||
@router.post("/verify-claim", response_model=ClaimVerificationResponse)
|
||||
async def verify_claim(request: ClaimVerificationRequest, current_user: Dict[str, Any] = Depends(get_current_user)) -> ClaimVerificationResponse:
|
||||
async def verify_claim(request: ClaimVerificationRequest) -> ClaimVerificationResponse:
|
||||
"""
|
||||
Verify a single claim against available sources.
|
||||
|
||||
@@ -197,10 +192,8 @@ async def verify_claim(request: ClaimVerificationRequest, current_user: Dict[str
|
||||
try:
|
||||
logger.info(f"Verifying claim: {request.claim[:100]}...")
|
||||
|
||||
user_id = current_user.get("id")
|
||||
|
||||
# Verify the claim
|
||||
claim_result = await detector._verify_claim(request.claim, user_id=user_id)
|
||||
claim_result = await detector._verify_claim(request.claim)
|
||||
|
||||
# Convert to response format
|
||||
supporting_sources = []
|
||||
@@ -214,7 +207,7 @@ async def verify_claim(request: ClaimVerificationRequest, current_user: Dict[str
|
||||
text=source.get('text', ''),
|
||||
published_date=source.get('publishedDate'),
|
||||
author=source.get('author'),
|
||||
score=source.get('score') if source.get('score') is not None else 0.5
|
||||
score=source.get('score', 0.5)
|
||||
)
|
||||
for source in claim_result.supporting_sources
|
||||
]
|
||||
@@ -226,7 +219,7 @@ async def verify_claim(request: ClaimVerificationRequest, current_user: Dict[str
|
||||
text=source.get('text', ''),
|
||||
published_date=source.get('publishedDate'),
|
||||
author=source.get('author'),
|
||||
score=source.get('score') if source.get('score') is not None else 0.5
|
||||
score=source.get('score', 0.5)
|
||||
)
|
||||
for source in claim_result.refuting_sources
|
||||
]
|
||||
@@ -253,8 +246,6 @@ async def verify_claim(request: ClaimVerificationRequest, current_user: Dict[str
|
||||
return response
|
||||
|
||||
except Exception as e:
|
||||
if isinstance(e, HTTPException):
|
||||
raise e
|
||||
logger.error(f"Error in claim verification: {str(e)}")
|
||||
processing_time = int((time.time() - start_time) * 1000)
|
||||
|
||||
@@ -282,21 +273,17 @@ async def health_check() -> HealthCheckResponse:
|
||||
HealthCheckResponse with service status and API availability
|
||||
"""
|
||||
try:
|
||||
from services.blog_writer.research.exa_provider import ExaResearchProvider
|
||||
try:
|
||||
exa_provider = ExaResearchProvider()
|
||||
exa_available = bool(exa_provider.api_key)
|
||||
except RuntimeError:
|
||||
exa_available = False
|
||||
llm_available = True # llm_text_gen handles provider selection via GPT_PROVIDER
|
||||
# Check API availability
|
||||
exa_available = bool(detector.exa_api_key)
|
||||
openai_available = bool(detector.openai_api_key)
|
||||
|
||||
status = "healthy" if (exa_available and llm_available) else ("degraded" if exa_available or llm_available else "unhealthy")
|
||||
status = "healthy" if (exa_available or openai_available) else "degraded"
|
||||
|
||||
response = HealthCheckResponse(
|
||||
status=status,
|
||||
version="1.0.0",
|
||||
exa_api_available=exa_available,
|
||||
openai_api_available=llm_available,
|
||||
openai_api_available=openai_available,
|
||||
timestamp=time.strftime('%Y-%m-%dT%H:%M:%S')
|
||||
)
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@ from __future__ import annotations
|
||||
import base64
|
||||
import os
|
||||
import uuid
|
||||
from typing import Optional, Dict, Any, List
|
||||
from typing import Optional, Dict, Any
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from sqlalchemy.orm import Session
|
||||
@@ -15,12 +15,6 @@ from pydantic import BaseModel, Field
|
||||
from services.llm_providers.main_image_generation import generate_image
|
||||
from services.llm_providers.main_image_editing import edit_image
|
||||
from services.llm_providers.main_text_generation import llm_text_gen
|
||||
from services.llm_providers.tenant_provider_config import tenant_provider_config_resolver
|
||||
from services.image_generation import (
|
||||
extract_visual_data as _extract_visual_data,
|
||||
get_model_recommendation,
|
||||
build_visual_summary,
|
||||
)
|
||||
from utils.logger_utils import get_service_logger
|
||||
from middleware.auth_middleware import get_current_user
|
||||
from services.database import get_db
|
||||
@@ -28,8 +22,6 @@ from services.subscription import UsageTrackingService, PricingService
|
||||
from models.subscription_models import APIProvider, UsageSummary
|
||||
from utils.asset_tracker import save_asset_to_library
|
||||
from utils.file_storage import save_file_safely, generate_unique_filename, sanitize_filename
|
||||
from services.content_asset_service import ContentAssetService
|
||||
from models.content_asset_models import ContentAsset
|
||||
|
||||
|
||||
router = APIRouter(prefix="/api/images", tags=["images"])
|
||||
@@ -46,7 +38,6 @@ class ImageGenerateRequest(BaseModel):
|
||||
guidance_scale: Optional[float] = None
|
||||
steps: Optional[int] = None
|
||||
seed: Optional[int] = None
|
||||
overlay_text: Optional[str] = None
|
||||
|
||||
|
||||
class ImageGenerateResponse(BaseModel):
|
||||
@@ -60,16 +51,6 @@ class ImageGenerateResponse(BaseModel):
|
||||
seed: Optional[int] = None
|
||||
|
||||
|
||||
@router.get("/config")
|
||||
def get_image_config(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
) -> dict:
|
||||
user_id = str(current_user.get('id', ''))
|
||||
cfg = tenant_provider_config_resolver.resolve(modality="image", user_id=user_id)
|
||||
provider = (cfg.selected_providers or [""])[0]
|
||||
return {"provider": provider}
|
||||
|
||||
|
||||
@router.post("/generate", response_model=ImageGenerateResponse)
|
||||
def generate(
|
||||
req: ImageGenerateRequest,
|
||||
@@ -102,7 +83,6 @@ def generate(
|
||||
"guidance_scale": req.guidance_scale,
|
||||
"steps": req.steps,
|
||||
"seed": req.seed,
|
||||
"overlay_text": req.overlay_text,
|
||||
},
|
||||
user_id=user_id, # Pass user_id for validation inside generate_image
|
||||
)
|
||||
@@ -180,7 +160,91 @@ def generate(
|
||||
logger.error(f"[images.generate] Unexpected error saving image: {save_error}", exc_info=True)
|
||||
# Continue without failing the request
|
||||
|
||||
# Usage tracking is handled inside generate_image() facade
|
||||
# TRACK USAGE after successful image generation
|
||||
if result:
|
||||
logger.info(f"[images.generate] ✅ Image generation successful, tracking usage for user {user_id}")
|
||||
try:
|
||||
db_track = next(get_db())
|
||||
try:
|
||||
# Get or create usage summary
|
||||
pricing = PricingService(db_track)
|
||||
current_period = pricing.get_current_billing_period(user_id) or datetime.now().strftime("%Y-%m")
|
||||
|
||||
logger.debug(f"[images.generate] Looking for usage summary: user_id={user_id}, period={current_period}")
|
||||
|
||||
summary = db_track.query(UsageSummary).filter(
|
||||
UsageSummary.user_id == user_id,
|
||||
UsageSummary.billing_period == current_period
|
||||
).first()
|
||||
|
||||
if not summary:
|
||||
logger.info(f"[images.generate] Creating new usage summary for user {user_id}, period {current_period}")
|
||||
summary = UsageSummary(
|
||||
user_id=user_id,
|
||||
billing_period=current_period
|
||||
)
|
||||
db_track.add(summary)
|
||||
db_track.flush() # Ensure summary is persisted before updating
|
||||
|
||||
# Get "before" state for unified log
|
||||
current_calls_before = getattr(summary, "stability_calls", 0) or 0
|
||||
|
||||
# Update provider-specific counters (stability for image generation)
|
||||
# Note: All image generation goes through STABILITY provider enum regardless of actual provider
|
||||
new_calls = current_calls_before + 1
|
||||
setattr(summary, "stability_calls", new_calls)
|
||||
logger.debug(f"[images.generate] Updated stability_calls: {current_calls_before} -> {new_calls}")
|
||||
|
||||
# Update totals
|
||||
old_total_calls = summary.total_calls or 0
|
||||
summary.total_calls = old_total_calls + 1
|
||||
logger.debug(f"[images.generate] Updated totals: calls {old_total_calls} -> {summary.total_calls}")
|
||||
|
||||
# Get plan details for unified log
|
||||
limits = pricing.get_user_limits(user_id)
|
||||
plan_name = limits.get('plan_name', 'unknown') if limits else 'unknown'
|
||||
tier = limits.get('tier', 'unknown') if limits else 'unknown'
|
||||
call_limit = limits['limits'].get("stability_calls", 0) if limits else 0
|
||||
|
||||
# Get image editing stats for unified log
|
||||
current_image_edit_calls = getattr(summary, "image_edit_calls", 0) or 0
|
||||
image_edit_limit = limits['limits'].get("image_edit_calls", 0) if limits else 0
|
||||
|
||||
# Get video stats for unified log
|
||||
current_video_calls = getattr(summary, "video_calls", 0) or 0
|
||||
video_limit = limits['limits'].get("video_calls", 0) if limits else 0
|
||||
|
||||
# Get audio stats for unified log
|
||||
current_audio_calls = getattr(summary, "audio_calls", 0) or 0
|
||||
audio_limit = limits['limits'].get("audio_calls", 0) if limits else 0
|
||||
# Only show ∞ for Enterprise tier when limit is 0 (unlimited)
|
||||
audio_limit_display = audio_limit if (audio_limit > 0 or tier != 'enterprise') else '∞'
|
||||
|
||||
db_track.commit()
|
||||
logger.info(f"[images.generate] ✅ Successfully tracked usage: user {user_id} -> stability -> {new_calls} calls")
|
||||
|
||||
# UNIFIED SUBSCRIPTION LOG - Shows before/after state in one message
|
||||
print(f"""
|
||||
[SUBSCRIPTION] Image Generation
|
||||
├─ User: {user_id}
|
||||
├─ Plan: {plan_name} ({tier})
|
||||
├─ Provider: stability
|
||||
├─ Actual Provider: {result.provider}
|
||||
├─ Model: {result.model or 'default'}
|
||||
├─ Calls: {current_calls_before} → {new_calls} / {call_limit if call_limit > 0 else '∞'}
|
||||
├─ Image Editing: {current_image_edit_calls} / {image_edit_limit if image_edit_limit > 0 else '∞'}
|
||||
├─ Videos: {current_video_calls} / {video_limit if video_limit > 0 else '∞'}
|
||||
├─ Audio: {current_audio_calls} / {audio_limit_display}
|
||||
└─ Status: ✅ Allowed & Tracked
|
||||
""")
|
||||
except Exception as track_error:
|
||||
logger.error(f"[images.generate] ❌ Error tracking usage (non-blocking): {track_error}", exc_info=True)
|
||||
db_track.rollback()
|
||||
finally:
|
||||
db_track.close()
|
||||
except Exception as usage_error:
|
||||
# Non-blocking: log error but don't fail the request
|
||||
logger.error(f"[images.generate] ❌ Failed to track usage: {usage_error}", exc_info=True)
|
||||
|
||||
# Create response with explicit success field
|
||||
# Note: Asset saving and usage tracking are non-blocking and won't affect this response
|
||||
@@ -227,8 +291,8 @@ class PromptSuggestion(BaseModel):
|
||||
|
||||
class ImagePromptSuggestRequest(BaseModel):
|
||||
provider: Optional[str] = Field(None, pattern="^(gemini|huggingface|stability|wavespeed)$")
|
||||
model: Optional[str] = None # Specific model (e.g., "qwen-image", "ideogram-v3-turbo", "flux-2-flex", "glm-image")
|
||||
image_type: Optional[str] = Field(None, pattern="^(realistic|chart|conceptual|diagram|illustration|background|infographic)$")
|
||||
model: Optional[str] = None # Specific model (e.g., "qwen-image", "ideogram-v3-turbo")
|
||||
image_type: Optional[str] = Field(None, pattern="^(realistic|chart|conceptual|diagram|illustration|background)$")
|
||||
title: Optional[str] = None
|
||||
section: Optional[Dict[str, Any]] = None
|
||||
research: Optional[Dict[str, Any]] = None
|
||||
@@ -395,165 +459,20 @@ MODEL_SPECIFIC_GUIDANCE = {
|
||||
"High contrast areas for text placement"
|
||||
]
|
||||
}
|
||||
},
|
||||
"flux-2-flex": {
|
||||
"text_overlay": {
|
||||
"guidance": "FLUX 2 Flex excels at typography control and text rendering. Excellent for posters, memes, and designs requiring precise text placement.",
|
||||
"best_practices": [
|
||||
"Best for images requiring clear, readable text with precise placement",
|
||||
"Superior typography control compared to other models",
|
||||
"Can handle various text styles and sizes",
|
||||
"Ideal for poster-style blog images with embedded headlines",
|
||||
"Great for quote images and text-heavy designs"
|
||||
],
|
||||
"negative_prompt_additions": "blurry text, distorted letters, low quality typography"
|
||||
},
|
||||
"realistic": {
|
||||
"guidance": "Photorealistic generation with excellent typography integration. Text appears naturally within scenes.",
|
||||
"best_practices": [
|
||||
"Include typography as a natural part of the scene",
|
||||
"Specify text style, size, and placement clearly",
|
||||
"Use for realistic scenes with signage, labels, or text elements",
|
||||
"Professional quality with consistent text rendering"
|
||||
]
|
||||
},
|
||||
"chart": {
|
||||
"guidance": "Can render charts with text labels. Use simple chart designs with clear typography.",
|
||||
"best_practices": [
|
||||
"Simple bar charts, pie charts, or line graphs",
|
||||
"Clear typography for labels and legends",
|
||||
"Clean data visualization design",
|
||||
"Avoid overly complex infographic layouts"
|
||||
]
|
||||
},
|
||||
"infographic": {
|
||||
"guidance": "Excellent for infographic-style images with clear sections and typography. Multi-panel layouts work well.",
|
||||
"best_practices": [
|
||||
"Use for multi-section infographics with distinct areas",
|
||||
"Clear typography placement in designated zones",
|
||||
"Clean, organized layout with visual hierarchy",
|
||||
"Professional infographic design with text integration"
|
||||
]
|
||||
},
|
||||
"conceptual": {
|
||||
"guidance": "Conceptual imagery with typography support. Text can be integrated naturally into abstract designs.",
|
||||
"best_practices": [
|
||||
"Integrate text into conceptual designs as a visual element",
|
||||
"Use typography to enhance conceptual messaging",
|
||||
"Clear, readable text in abstract compositions"
|
||||
]
|
||||
}
|
||||
},
|
||||
"glm-image": {
|
||||
"text_overlay": {
|
||||
"guidance": "GLM-Image excels at infographics, educational diagrams, and professional poster designs. Strong text rendering capabilities.",
|
||||
"best_practices": [
|
||||
"Best for educational content, infographics, and diagrams",
|
||||
"Excellent for multi-panel layouts and structured designs",
|
||||
"Good text rendering with clear typography",
|
||||
"Professional infographic aesthetics",
|
||||
"Strong for academic or professional blog images"
|
||||
],
|
||||
"negative_prompt_additions": "watermarks, distorted text, low quality diagrams"
|
||||
},
|
||||
"realistic": {
|
||||
"guidance": "Photorealistic generation with good quality. Professional presentation style.",
|
||||
"best_practices": [
|
||||
"Include professional lighting and composition",
|
||||
"Use for polished, professional imagery",
|
||||
"Quality descriptors improve output consistency"
|
||||
]
|
||||
},
|
||||
"chart": {
|
||||
"guidance": "Excellent for data visualizations. Can render charts with clear labels and professional styling.",
|
||||
"best_practices": [
|
||||
"Professional chart designs with clear typography",
|
||||
"Data visualizations with embedded labels",
|
||||
"Clean infographic-style charts",
|
||||
"Good for statistical blog content"
|
||||
]
|
||||
},
|
||||
"infographic": {
|
||||
"guidance": "Best model choice for complex infographics. Multi-section layouts with clear visual hierarchy.",
|
||||
"best_practices": [
|
||||
"Use for comprehensive infographics with multiple data points",
|
||||
"Clear section boundaries and visual hierarchy",
|
||||
"Professional infographic aesthetic",
|
||||
"Excellent for educational or how-to content",
|
||||
"Multi-panel designs with distinct information areas"
|
||||
]
|
||||
},
|
||||
"diagram": {
|
||||
"guidance": "Excellent for technical diagrams and process illustrations. Clear visual representation of complex information.",
|
||||
"best_practices": [
|
||||
"Use for process flows, architectural diagrams, technical illustrations",
|
||||
"Clear visual hierarchy and labeling",
|
||||
"Professional diagram aesthetics",
|
||||
"Educational content visualization"
|
||||
]
|
||||
},
|
||||
"conceptual": {
|
||||
"guidance": "Professional conceptual imagery. Good for abstract representations with clear messaging.",
|
||||
"best_practices": [
|
||||
"Clear visual metaphors for abstract concepts",
|
||||
"Professional presentation style",
|
||||
"Good for educational or explanatory content"
|
||||
]
|
||||
}
|
||||
},
|
||||
# Default guidance for unknown models
|
||||
"_default": {
|
||||
"text_overlay": {
|
||||
"guidance": "Design for text overlay areas. Create clean backgrounds with high-contrast safe zones for text placement.",
|
||||
"best_practices": [
|
||||
"Use designated text areas (top 20% or bottom 20%)",
|
||||
"Create clean, uncluttered backgrounds",
|
||||
"Avoid embedding text directly in the image",
|
||||
"Design for text to be added as overlay"
|
||||
],
|
||||
"negative_prompt_additions": "text artifacts, unreadable text, embedded words"
|
||||
},
|
||||
"conceptual": {
|
||||
"guidance": "Focus on visual metaphors and abstract representations of the topic.",
|
||||
"best_practices": [
|
||||
"Use visual metaphors relevant to the content",
|
||||
"Create simple, clear compositions",
|
||||
"Avoid busy or cluttered designs"
|
||||
]
|
||||
},
|
||||
"chart": {
|
||||
"guidance": "Use abstract data representations. Avoid actual charts with embedded text.",
|
||||
"best_practices": [
|
||||
"Create visual metaphors for data",
|
||||
"Use shapes, colors, and patterns to represent information",
|
||||
"Design with text overlay zones for labels"
|
||||
],
|
||||
"warnings": ["Do not request actual charts with text - use abstract representations"]
|
||||
},
|
||||
"infographic": {
|
||||
"guidance": "Create multi-section infographic layouts with clear visual hierarchy. Use text overlay zones for information.",
|
||||
"best_practices": [
|
||||
"Multi-panel designs with distinct sections",
|
||||
"Clear visual hierarchy and organization",
|
||||
"Design with text overlay zones for each section",
|
||||
"Professional infographic aesthetic"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
# Models that can render readable text directly in generated images
|
||||
_TEXT_CAPABLE = {"flux-kontext-pro", "flux-2-flex", "glm-image"}
|
||||
|
||||
|
||||
def get_model_specific_guidance(model: Optional[str], image_type: Optional[str]) -> Dict[str, Any]:
|
||||
"""Get model-specific guidance based on model and image type."""
|
||||
model_lower = (model or "_default").lower()
|
||||
if not model:
|
||||
return {}
|
||||
|
||||
model_lower = model.lower()
|
||||
image_type_lower = (image_type or "conceptual").lower()
|
||||
|
||||
# Get model guidance (use _default for unknown models)
|
||||
model_guidance = MODEL_SPECIFIC_GUIDANCE.get(model_lower, MODEL_SPECIFIC_GUIDANCE.get("_default", {}))
|
||||
# Get model guidance
|
||||
model_guidance = MODEL_SPECIFIC_GUIDANCE.get(model_lower, {})
|
||||
|
||||
# Get image type specific guidance
|
||||
type_guidance = model_guidance.get(image_type_lower, model_guidance.get("text_overlay", {}))
|
||||
@@ -561,19 +480,70 @@ def get_model_specific_guidance(model: Optional[str], image_type: Optional[str])
|
||||
return type_guidance
|
||||
|
||||
|
||||
def extract_visual_data(section: Dict[str, Any], research: Optional[Dict[str, Any]]) -> Dict[str, Any]:
|
||||
"""Intelligently extract visual-relevant data from section and research."""
|
||||
visual_data = {
|
||||
"visual_keywords": [],
|
||||
"data_points": [],
|
||||
"concepts": [],
|
||||
"statistics": []
|
||||
}
|
||||
|
||||
# Extract from section
|
||||
if section:
|
||||
# Key points that are visualizable
|
||||
key_points = section.get("key_points", []) or []
|
||||
for point in key_points[:5]:
|
||||
if isinstance(point, str):
|
||||
# Look for numbers, percentages, comparisons
|
||||
if any(char.isdigit() for char in point):
|
||||
visual_data["statistics"].append(point)
|
||||
# Look for visual concepts
|
||||
elif any(word in point.lower() for word in ["increase", "decrease", "growth", "trend", "pattern", "comparison"]):
|
||||
visual_data["data_points"].append(point)
|
||||
else:
|
||||
visual_data["concepts"].append(point)
|
||||
|
||||
# Subheadings that suggest visuals
|
||||
subheadings = section.get("subheadings", []) or []
|
||||
for subhead in subheadings[:3]:
|
||||
if isinstance(subhead, str):
|
||||
visual_data["concepts"].append(subhead)
|
||||
|
||||
# Keywords
|
||||
keywords = section.get("keywords", []) or []
|
||||
visual_data["visual_keywords"].extend([str(k) for k in keywords[:8] if k])
|
||||
|
||||
# Extract from research
|
||||
if research:
|
||||
# Key facts that are visualizable
|
||||
key_facts = research.get("key_facts", []) or research.get("highlights", []) or []
|
||||
for fact in key_facts[:3]:
|
||||
if isinstance(fact, str):
|
||||
if any(char.isdigit() for char in fact):
|
||||
visual_data["statistics"].append(fact)
|
||||
else:
|
||||
visual_data["data_points"].append(fact)
|
||||
|
||||
# Research insights
|
||||
insights = research.get("insights", []) or research.get("summary", "")
|
||||
if isinstance(insights, str) and insights:
|
||||
# Extract key phrases
|
||||
sentences = insights.split('.')[:3]
|
||||
visual_data["concepts"].extend([s.strip() for s in sentences if s.strip()])
|
||||
elif isinstance(insights, list):
|
||||
visual_data["concepts"].extend([str(i) for i in insights[:3]])
|
||||
|
||||
return visual_data
|
||||
|
||||
|
||||
@router.post("/suggest-prompts", response_model=ImagePromptSuggestResponse)
|
||||
def suggest_prompts(
|
||||
req: ImagePromptSuggestRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
) -> ImagePromptSuggestResponse:
|
||||
user_id = str(current_user.get('id', ''))
|
||||
logger.info(f"[suggest-prompts] Starting for user={user_id}, provider={req.provider}, model={req.model}")
|
||||
try:
|
||||
if req.provider:
|
||||
provider = req.provider.lower()
|
||||
else:
|
||||
cfg = tenant_provider_config_resolver.resolve(modality="image", user_id=user_id)
|
||||
provider = (cfg.selected_providers or ["huggingface"])[0]
|
||||
provider = (req.provider or ("gemini" if (os.getenv("GPT_PROVIDER") or "").lower().startswith("gemini") else "huggingface")).lower()
|
||||
model = req.model or None
|
||||
image_type = req.image_type or "conceptual"
|
||||
|
||||
@@ -594,18 +564,8 @@ def suggest_prompts(
|
||||
industry = persona.get("industry", req.research.get("domain") if req.research else "your industry")
|
||||
tone = persona.get("tone", "professional, trustworthy")
|
||||
|
||||
# Extract visual-relevant data intelligently using the new module
|
||||
visual_data = _extract_visual_data(section, req.research)
|
||||
|
||||
# Get model recommendation based on content type
|
||||
model_recommendation = get_model_recommendation(visual_data)
|
||||
|
||||
# Build visual summary from extracted data
|
||||
visual_summary = build_visual_summary(visual_data)
|
||||
|
||||
# Add model recommendation to visual summary if available
|
||||
if model_recommendation:
|
||||
visual_summary += model_recommendation
|
||||
# Extract visual-relevant data intelligently
|
||||
visual_data = extract_visual_data(section, req.research)
|
||||
|
||||
schema = {
|
||||
"type": "object",
|
||||
@@ -630,20 +590,10 @@ def suggest_prompts(
|
||||
"required": ["suggestions"]
|
||||
}
|
||||
|
||||
can_render_text = model and model.lower() in _TEXT_CAPABLE
|
||||
|
||||
system = (
|
||||
"You are an expert image prompt engineer. "
|
||||
"Given blog section context, craft 3-5 concise prompts optimized for the specified provider/model. "
|
||||
"Return STRICT JSON matching the provided schema, no extra text.\n\n"
|
||||
+ (
|
||||
"TEXT RENDERING: The current model CAN render readable text. "
|
||||
"Include the section title or a key phrase (1-8 words) as part of the generated image. "
|
||||
"Integrate text naturally as a headline, label, or typographic element."
|
||||
if can_render_text
|
||||
else "TEXT RENDERING: The image model CANNOT render readable text. "
|
||||
"Never ask it to generate text. Design clean, high-contrast overlay-safe zones instead."
|
||||
)
|
||||
"You are an expert image prompt engineer for text-to-image models. "
|
||||
"Given blog section context, craft 3-5 hyper-personalized prompts optimized for the specified provider. "
|
||||
"Return STRICT JSON matching the provided schema, no extra text."
|
||||
)
|
||||
|
||||
# Get model-specific guidance
|
||||
@@ -661,62 +611,57 @@ def suggest_prompts(
|
||||
"wavespeed": "Blog-optimized imagery: focus on data visualization, infographics, clean layouts with text overlay areas, professional diagrams, charts, or conceptual illustrations. Avoid random people or poster-style images. Prefer clean backgrounds suitable for text overlays, data representations, or abstract concepts that support the blog content."
|
||||
}.get(provider, "")
|
||||
|
||||
# Combine provider and model-specific guidance (model guidance is primary)
|
||||
# Combine provider and model-specific guidance
|
||||
provider_guidance = provider_guidance_base
|
||||
if model_guidance_text:
|
||||
parts = [
|
||||
f"PROVIDER: {provider} / Model: {model or 'auto-selected'}",
|
||||
f"MODEL GUIDANCE: {model_guidance_text}"
|
||||
]
|
||||
provider_guidance = f"{provider_guidance_base}\n\nMODEL-SPECIFIC GUIDANCE ({model}): {model_guidance_text}"
|
||||
if model_best_practices:
|
||||
parts.append("Best Practices:\n" + "\n".join([f"- {bp}" for bp in model_best_practices]))
|
||||
provider_guidance += f"\nBest Practices:\n" + "\n".join([f"- {bp}" for bp in model_best_practices])
|
||||
if model_warnings:
|
||||
parts.append("WARNINGS:\n" + "\n".join([f"- {w}" for w in model_warnings]))
|
||||
if provider_guidance_base:
|
||||
parts.append(f"Provider context ({provider}): {provider_guidance_base}")
|
||||
provider_guidance = "\n\n".join(parts)
|
||||
provider_guidance += f"\n⚠️ WARNINGS:\n" + "\n".join([f"- {w}" for w in model_warnings])
|
||||
|
||||
# Build visual data summary from extracted data
|
||||
visual_summary_parts = []
|
||||
if visual_data["statistics"]:
|
||||
visual_summary_parts.append(f"Key Statistics: {', '.join(visual_data['statistics'][:3])}")
|
||||
if visual_data["data_points"]:
|
||||
visual_summary_parts.append(f"Data Points: {', '.join(visual_data['data_points'][:3])}")
|
||||
if visual_data["concepts"]:
|
||||
visual_summary_parts.append(f"Visual Concepts: {', '.join(visual_data['concepts'][:5])}")
|
||||
if visual_data["visual_keywords"]:
|
||||
visual_summary_parts.append(f"Keywords: {', '.join(visual_data['visual_keywords'][:8])}")
|
||||
|
||||
visual_summary = "\n".join(visual_summary_parts) if visual_summary_parts else ""
|
||||
|
||||
best_practices = (
|
||||
"BLOG IMAGE BEST PRACTICES: "
|
||||
+ (
|
||||
"Create professional blog images with clear typography. "
|
||||
"Include text elements (headlines, labels) naturally in the design. "
|
||||
"Use clean compositions with strong visual hierarchy. "
|
||||
"Avoid: busy patterns, brand logos, watermarks, low resolution."
|
||||
if can_render_text
|
||||
else (
|
||||
"Design for text overlay — use clean backgrounds with designated text zones (20% padding). "
|
||||
"Focus on abstract representations, data metaphors, or conceptual imagery. "
|
||||
"NEVER include text, words, letters, numbers, or labels in the generated image. "
|
||||
"Avoid: busy patterns, brand logos, watermarks, low resolution."
|
||||
)
|
||||
)
|
||||
"BLOG IMAGE BEST PRACTICES: Create images optimized for blog content, not social media posters. "
|
||||
"Focus on: data visualization elements (charts, graphs, infographics), clean layouts with designated text overlay areas, "
|
||||
"professional diagrams, conceptual illustrations, or abstract representations of the topic. "
|
||||
"Avoid: random people posing, poster-style compositions, busy social media graphics, or trying to recreate text/words as images. "
|
||||
"Instead: use clean backgrounds, simple compositions, areas reserved for text overlays, data-driven visuals, or conceptual imagery. "
|
||||
"Technical: one clear focal subject; clean, uncluttered background; text-safe margins (20% padding on all sides for overlays); "
|
||||
"neutral or professional lighting; avoid busy patterns; no brand logos or watermarks; no copyrighted characters; "
|
||||
"avoid low-res, blur, noise, banding, oversaturation, over-sharpening; prefer 1024px+ on shortest side for quality."
|
||||
)
|
||||
|
||||
overlay_hint = (
|
||||
(
|
||||
"Include the section title or key phrase IN the generated image as a typographic element (headline, label, etc.). "
|
||||
"Keep text minimal: 1-8 words."
|
||||
if can_render_text
|
||||
else (
|
||||
"ABSOLUTELY FORBIDDEN: The image model CANNOT render text. "
|
||||
"Design with clean, high-contrast safe zones (top 20% or bottom 20%) for HTML overlay text. "
|
||||
"Suggest overlay_text (short title or key statistic, <= 8 words) that works as a text overlay."
|
||||
if (req.include_overlay is None or req.include_overlay)
|
||||
else "Do not include on-image text, but still design with text overlay areas in mind."
|
||||
)
|
||||
)
|
||||
"IMPORTANT FOR BLOG IMAGES: Design images with text overlay areas in mind. "
|
||||
"Include space for headlines, captions, or data labels. "
|
||||
"Suggest overlay_text (short title or key statistic, <= 8 words) that would work well as a text overlay. "
|
||||
"Ensure clean, high-contrast safe areas (top 20% or bottom 20% of image) for text placement. "
|
||||
"The image should complement text, not replace it - think data visualization, infographics, or clean conceptual imagery."
|
||||
if (req.include_overlay is None or req.include_overlay)
|
||||
else "Do not include on-image text, but still design with text overlay areas in mind for blog use."
|
||||
)
|
||||
|
||||
# Image type specific guidance (enhanced with infographic type)
|
||||
# Image type specific guidance
|
||||
image_type_guidance = {
|
||||
"realistic": "Photorealistic style with professional photography quality. Include camera settings and lighting details.",
|
||||
"chart": "⚠️ FORBIDDEN: Do NOT create actual charts, graphs, or data visualizations with embedded text. The image model cannot render readable labels or data points. Instead, create abstract visual metaphors for data — flowing shapes, color gradients, connected nodes, layered elements, or geometric patterns that evoke the data concept. Design with text overlay zones for data labels that will be added as HTML overlay.",
|
||||
"chart": "⚠️ IMPORTANT: Complex infographics are too difficult for current AI models. Create simple visual representations with designated text overlay areas instead. Use abstract data visualization elements, not actual charts with embedded text.",
|
||||
"conceptual": "Abstract or conceptual imagery that represents the topic visually. Clean compositions with text overlay zones.",
|
||||
"diagram": "Technical diagrams with simple, clear visual elements. Design for text overlay areas, not embedded labels.",
|
||||
"illustration": "Stylized illustrations that support the content. Professional, clean aesthetic suitable for blog use.",
|
||||
"background": "Background images optimized for text overlays. Clean, uncluttered compositions with high-contrast text zones.",
|
||||
"infographic": "Multi-section infographic designs with clear visual hierarchy. Use designated areas for each data point or concept. Design with text overlay zones for information labels. Professional infographic aesthetics with clean, organized layouts."
|
||||
"background": "Background images optimized for text overlays. Clean, uncluttered compositions with high-contrast text zones."
|
||||
}.get(image_type, "General blog image guidance.")
|
||||
|
||||
# Build comprehensive prompt with visual data and model-specific guidance
|
||||
@@ -760,31 +705,31 @@ def suggest_prompts(
|
||||
8. Are optimized for blog article use (not social media)
|
||||
|
||||
PROMPT QUALITY REQUIREMENTS:
|
||||
- Each prompt should be concise (20-40 words)
|
||||
- Focus on visual composition, style, and key visual elements
|
||||
- Each prompt should be specific and detailed (50-100 words)
|
||||
- Use the visual data intelligently - prioritize statistics and data points for charts, concepts for conceptual images
|
||||
- Include visual composition guidance (layout, colors, style)
|
||||
- Specify lighting and quality descriptors when appropriate
|
||||
- Make prompts actionable and clear for the AI model
|
||||
|
||||
NEGATIVE PROMPT:
|
||||
Include a suitable negative_prompt that excludes: people posing, social media graphics, posters, text rendered as images, busy compositions, watermarks, logos{f", {negative_prompt_additions}" if negative_prompt_additions else ""}.
|
||||
|
||||
DIMENSIONS:
|
||||
Default to 1024x1024 for consistent blog image format. Do NOT reference specific pixel dimensions in the prompt text.
|
||||
Suggest width/height when relevant (e.g., 1024x1024 for square, 1920x1080 for landscape blog headers).
|
||||
|
||||
OVERLAY TEXT:
|
||||
{("Include the overlay_text IN the generated image as a typographic element (headline, label, etc.) — "
|
||||
"it will be rendered as part of the image. Keep it minimal: 1-8 words (key statistic or section title). "
|
||||
"Use statistics from the visual data when available.")
|
||||
if can_render_text else
|
||||
("Suggest overlay_text (short: <= 8 words, typically a key statistic or section title) as metadata only — "
|
||||
"it will be rendered as HTML overlay. Do NOT include text in the image. "
|
||||
"Use statistics from the visual data when available.")}
|
||||
If including overlay text suggestion, return it in overlay_text (short: <= 8 words, typically a key statistic or section title). Use statistics from the visual data when available.
|
||||
"""
|
||||
|
||||
# Get user_id for llm_text_gen subscription check (required)
|
||||
if not user_id:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id_for_llm = str(current_user.get('id', ''))
|
||||
if not user_id_for_llm:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID in authentication token")
|
||||
|
||||
raw = llm_text_gen(prompt=prompt, system_prompt=system, json_struct=schema, user_id=user_id)
|
||||
raw = llm_text_gen(prompt=prompt, system_prompt=system, json_struct=schema, user_id=user_id_for_llm)
|
||||
data = raw if isinstance(raw, dict) else {}
|
||||
suggestions = data.get("suggestions") or []
|
||||
# basic fallback if provider returns string
|
||||
@@ -930,19 +875,32 @@ def edit(
|
||||
billing_period=current_period
|
||||
)
|
||||
db_track.add(summary)
|
||||
db_track.flush()
|
||||
db_track.flush() # Ensure summary is persisted before updating
|
||||
|
||||
# Get "before" state for unified log
|
||||
current_calls_before = getattr(summary, "image_edit_calls", 0) or 0
|
||||
new_calls = current_calls_before + 1
|
||||
|
||||
# Update image editing counters (separate from image generation)
|
||||
new_calls = current_calls_before + 1
|
||||
setattr(summary, "image_edit_calls", new_calls)
|
||||
logger.debug(f"[images.edit] Updated image_edit_calls: {current_calls_before} -> {new_calls}")
|
||||
|
||||
# Update totals
|
||||
old_total_calls = summary.total_calls or 0
|
||||
summary.total_calls = old_total_calls + 1
|
||||
logger.debug(f"[images.edit] Updated totals: calls {old_total_calls} -> {summary.total_calls}")
|
||||
|
||||
# Get plan details for unified log
|
||||
limits = pricing.get_user_limits(user_id)
|
||||
plan_name = limits.get('plan_name', 'unknown') if limits else 'unknown'
|
||||
tier = limits.get('tier', 'unknown') if limits else 'unknown'
|
||||
call_limit = limits['limits'].get("image_edit_calls", 0) if limits else 0
|
||||
|
||||
# Get image generation stats for unified log
|
||||
current_image_gen_calls = getattr(summary, "stability_calls", 0) or 0
|
||||
image_gen_limit = limits['limits'].get("stability_calls", 0) if limits else 0
|
||||
|
||||
# Get video stats for unified log
|
||||
current_video_calls = getattr(summary, "video_calls", 0) or 0
|
||||
video_limit = limits['limits'].get("video_calls", 0) if limits else 0
|
||||
|
||||
@@ -952,7 +910,8 @@ def edit(
|
||||
# Only show ∞ for Enterprise tier when limit is 0 (unlimited)
|
||||
audio_limit_display = audio_limit if (audio_limit > 0 or tier != 'enterprise') else '∞'
|
||||
|
||||
logger.debug(f"[images.edit] Usage snapshot for logging: image_edit_calls={current_calls_before}, total_calls={summary.total_calls or 0}")
|
||||
db_track.commit()
|
||||
logger.info(f"[images.edit] ✅ Successfully tracked usage: user {user_id} -> image_edit -> {new_calls} calls")
|
||||
|
||||
# UNIFIED SUBSCRIPTION LOG - Shows before/after state in one message
|
||||
print(f"""
|
||||
@@ -1004,29 +963,13 @@ def edit(
|
||||
@router.get("/image-studio/images/{image_filename:path}")
|
||||
async def serve_image_studio_image(
|
||||
image_filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
"""Serve a generated or edited image from Image Studio.
|
||||
Verifies the authenticated user owns the image via asset library lookup."""
|
||||
"""Serve a generated or edited image from Image Studio."""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = current_user.get("id") or current_user.get("user_id") or current_user.get("clerk_user_id")
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="User ID not found")
|
||||
|
||||
# Verify ownership: the requesting user must have a content_assets record for this file_url
|
||||
full_url = f"/api/images/image-studio/images/{image_filename}"
|
||||
service = ContentAssetService(db)
|
||||
owned = db.query(ContentAsset).filter(
|
||||
ContentAsset.user_id == user_id,
|
||||
ContentAsset.file_url == full_url,
|
||||
).first()
|
||||
if not owned:
|
||||
raise HTTPException(status_code=403, detail="Access denied: image not found in your library")
|
||||
|
||||
# Determine if it's an edited image or regular image
|
||||
base_dir = Path(__file__).parent.parent
|
||||
image_studio_dir = (base_dir / "image_studio_images").resolve()
|
||||
|
||||
@@ -1,9 +1,7 @@
|
||||
import os
|
||||
from fastapi import APIRouter, HTTPException, UploadFile, File, Depends
|
||||
from fastapi.responses import FileResponse
|
||||
from pydantic import BaseModel
|
||||
from typing import List, Optional, Dict, Any
|
||||
import base64
|
||||
import json
|
||||
|
||||
# Import our LinkedIn image generation services
|
||||
from services.linkedin.image_generation import LinkedInImageGenerator, LinkedInImageStorage
|
||||
@@ -53,23 +51,6 @@ class ImageGenerationResponse(BaseModel):
|
||||
aspect_ratio: Optional[str] = None
|
||||
error: Optional[str] = None
|
||||
|
||||
class ImageEditRequest(BaseModel):
|
||||
image_base64: Optional[str] = None
|
||||
image_id: Optional[str] = None
|
||||
prompt: str
|
||||
content_context: Dict[str, Any]
|
||||
|
||||
class ImageEditResponse(BaseModel):
|
||||
success: bool
|
||||
image_data: Optional[str] = None
|
||||
image_id: Optional[str] = None
|
||||
image_url: Optional[str] = None
|
||||
width: Optional[int] = None
|
||||
height: Optional[int] = None
|
||||
provider: Optional[str] = None
|
||||
model: Optional[str] = None
|
||||
error: Optional[str] = None
|
||||
|
||||
@router.post("/generate-image-prompts", response_model=List[ImagePromptResponse])
|
||||
async def generate_image_prompts(request: ImagePromptRequest):
|
||||
"""
|
||||
@@ -108,8 +89,7 @@ async def generate_linkedin_image(
|
||||
# Use our LinkedIn image generator service
|
||||
image_result = await image_generator.generate_image(
|
||||
prompt=request.prompt,
|
||||
content_context=request.content_context,
|
||||
user_id=user_id
|
||||
content_context=request.content_context
|
||||
)
|
||||
|
||||
if image_result and image_result.get('success'):
|
||||
@@ -151,99 +131,6 @@ async def generate_linkedin_image(
|
||||
error=f"Failed to generate image: {str(e)}"
|
||||
)
|
||||
|
||||
@router.post("/edit-image", response_model=ImageEditResponse)
|
||||
async def edit_linkedin_image(
|
||||
request: ImageEditRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
Edit a LinkedIn-optimized image using natural language.
|
||||
Provide the image as base64 and describe the desired edits.
|
||||
"""
|
||||
try:
|
||||
user_id = current_user.get("id")
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
if not request.prompt or not request.prompt.strip():
|
||||
raise HTTPException(status_code=400, detail="Prompt is required for image editing")
|
||||
|
||||
logger.info(f"Editing LinkedIn image with prompt: {request.prompt[:100]}... for user {user_id}")
|
||||
|
||||
# Get input image bytes — from image_id (fetch from storage) or image_base64 (direct decode)
|
||||
input_image_bytes = None
|
||||
if request.image_id:
|
||||
stored = await image_storage.retrieve_image(request.image_id, user_id)
|
||||
if not stored or not stored.get('success'):
|
||||
raise HTTPException(status_code=404, detail=f"Image not found: {request.image_id}")
|
||||
input_image_bytes = stored['image_data']
|
||||
logger.info(f"Fetched image {request.image_id} from storage ({len(input_image_bytes)} bytes)")
|
||||
elif request.image_base64:
|
||||
input_image_bytes = base64.b64decode(request.image_base64)
|
||||
else:
|
||||
raise HTTPException(status_code=400, detail="Either image_id or image_base64 is required")
|
||||
|
||||
# Use LinkedIn image generator with common editing infrastructure
|
||||
image_result = await image_generator.edit_image(
|
||||
input_image_bytes=input_image_bytes,
|
||||
edit_prompt=request.prompt,
|
||||
content_context=request.content_context,
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
if image_result and image_result.get('success'):
|
||||
image_b64 = base64.b64encode(image_result['image_data']).decode("utf-8")
|
||||
|
||||
# Store the edited image — log but don't fail if storage has issues
|
||||
new_image_id = None
|
||||
stored_result = await image_storage.store_image(
|
||||
image_data=image_result['image_data'],
|
||||
metadata={
|
||||
'prompt': request.prompt,
|
||||
'style': request.content_context.get('style', 'Edited'),
|
||||
'content_type': request.content_context.get('content_type'),
|
||||
'topic': request.content_context.get('topic'),
|
||||
'industry': request.content_context.get('industry'),
|
||||
'is_edit': True,
|
||||
'original_prompt': request.prompt,
|
||||
'source_image_id': request.image_id,
|
||||
},
|
||||
user_id=user_id
|
||||
)
|
||||
if stored_result and stored_result.get('success'):
|
||||
new_image_id = stored_result.get('image_id')
|
||||
logger.info(f"Edited image stored with ID: {new_image_id}")
|
||||
else:
|
||||
logger.warning(f"Edited image not stored: {stored_result.get('error', 'unknown reason')}")
|
||||
|
||||
return ImageEditResponse(
|
||||
success=True,
|
||||
image_data=image_b64,
|
||||
image_id=new_image_id,
|
||||
image_url=image_result.get('image_url'),
|
||||
width=image_result.get('width'),
|
||||
height=image_result.get('height'),
|
||||
provider=image_result.get('provider'),
|
||||
model=image_result.get('model'),
|
||||
)
|
||||
else:
|
||||
error_msg = image_result.get('error', 'Unknown error during image editing')
|
||||
logger.error(f"Image editing failed: {error_msg}")
|
||||
return ImageEditResponse(
|
||||
success=False,
|
||||
error=error_msg
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error editing LinkedIn image: {str(e)}", exc_info=True)
|
||||
return ImageEditResponse(
|
||||
success=False,
|
||||
error=f"Failed to edit image: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/image-status/{image_id}")
|
||||
async def get_image_status(
|
||||
image_id: str,
|
||||
@@ -282,23 +169,42 @@ async def get_generated_image(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
Retrieve a generated image by ID.
|
||||
Returns the image file directly as a PNG response.
|
||||
Retrieve a generated image by ID
|
||||
"""
|
||||
try:
|
||||
user_id = current_user.get("id")
|
||||
image_result = await image_storage.retrieve_image(image_id, user_id)
|
||||
|
||||
if image_result.get('success') and image_result.get('image_path'):
|
||||
return FileResponse(
|
||||
path=image_result['image_path'],
|
||||
media_type="image/png",
|
||||
filename=f"{image_id}.png"
|
||||
)
|
||||
if image_result.get('success') and 'image_data' in image_result:
|
||||
# Return as streaming response or raw bytes depending on frontend needs
|
||||
# For now returning the structure as before but image_data is bytes
|
||||
# Ideally this should be a Response object with image/png content type
|
||||
# But keeping consistency with existing return type structure for now if it was returning dict
|
||||
# Wait, retrieve_image returns dict with 'image_data' as bytes.
|
||||
# The original code returned: {"success": True, "image_data": image_data}
|
||||
# FastAPI handles bytes in JSON? No, it will fail serialization.
|
||||
# The previous implementation of retrieve_image (lines 190-195) returned bytes in a dict.
|
||||
# Unless FastAPI response model handles it, this might have been broken or handled specially.
|
||||
# Let's check imports.
|
||||
# It uses APIRouter.
|
||||
# If I return a dict with bytes, json serialization fails.
|
||||
# Maybe the original code expected base64 or it was just broken?
|
||||
# Or maybe image_data was not bytes?
|
||||
# In retrieve_image: with open(..., 'rb') as f: image_data = f.read() -> bytes.
|
||||
# So returning it in a dict will definitely fail JSON serialization.
|
||||
# I should probably return a Response or FileResponse, or base64 encode it.
|
||||
# But for now, I will just match the signature and pass user_id.
|
||||
# If it was broken before, I'm not fixing that unless asked, but I suspect it might be base64 in usage?
|
||||
# Let's look at `generate_linkedin_image` which returns `ImageGenerationResponse` with `image_url`.
|
||||
# `get_generated_image` returns a dict.
|
||||
# I will stick to passing user_id.
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"image_data": image_result['image_data'] # This might need base64 encoding if it's for JSON
|
||||
}
|
||||
else:
|
||||
raise HTTPException(status_code=404, detail="Image not found")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error retrieving image: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=f"Failed to retrieve image: {str(e)}")
|
||||
@@ -326,42 +232,25 @@ async def delete_generated_image(
|
||||
@router.get("/image-generation-health")
|
||||
async def health_check():
|
||||
"""
|
||||
Lightweight health check for image generation services.
|
||||
Verifies configuration and service availability without making API calls.
|
||||
Health check for image generation services
|
||||
"""
|
||||
try:
|
||||
services = {}
|
||||
all_healthy = True
|
||||
|
||||
# Check API key configuration (no actual API call)
|
||||
image_api_key = api_key_manager.get_api_key("image_generation") or os.getenv("WAVESPEED_API_KEY") or os.getenv("HF_TOKEN")
|
||||
services["image_api_key_configured"] = bool(image_api_key)
|
||||
|
||||
# Check storage accessibility
|
||||
stats = await image_storage.get_storage_stats()
|
||||
storage_ok = stats.get('success', False)
|
||||
services["image_storage"] = "operational" if storage_ok else "unavailable"
|
||||
if storage_ok:
|
||||
services["storage_stats"] = {
|
||||
"total_images": stats.get('total_files', 0),
|
||||
"total_size_gb": stats.get('total_size_gb', 0),
|
||||
"limit_gb": stats.get('storage_limit_gb', 0),
|
||||
}
|
||||
|
||||
# Check prompt generator initialization
|
||||
prompt_ok = prompt_generator is not None and hasattr(prompt_generator, 'generate_three_prompts')
|
||||
services["prompt_generator"] = "operational" if prompt_ok else "unavailable"
|
||||
|
||||
# Check image generator initialization
|
||||
gen_ok = image_generator is not None and hasattr(image_generator, 'generate_image')
|
||||
services["image_generator"] = "operational" if gen_ok else "unavailable"
|
||||
|
||||
if not all(v == "operational" or v is True for v in services.values()):
|
||||
all_healthy = False
|
||||
|
||||
# Test basic service functionality
|
||||
test_prompts = await prompt_generator.generate_three_prompts({
|
||||
'content_type': 'post',
|
||||
'topic': 'Test',
|
||||
'industry': 'Technology',
|
||||
'content': 'Test content for health check'
|
||||
})
|
||||
|
||||
return {
|
||||
"status": "healthy" if all_healthy else "degraded",
|
||||
"services": services
|
||||
"status": "healthy",
|
||||
"services": {
|
||||
"prompt_generator": "operational",
|
||||
"image_generator": "operational",
|
||||
"image_storage": "operational"
|
||||
},
|
||||
"test_prompts_generated": len(test_prompts)
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Health check failed: {str(e)}")
|
||||
|
||||
@@ -1,185 +0,0 @@
|
||||
"""
|
||||
Link Search API — Internal & external link discovery and reword-with-links.
|
||||
|
||||
Endpoints:
|
||||
POST /api/links/search — Search for internal or external links via Exa
|
||||
POST /api/links/reword — Reword text to naturally incorporate selected links
|
||||
GET /api/links/health — Health check
|
||||
"""
|
||||
|
||||
from typing import Dict, Any, List, Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from pydantic import BaseModel, Field
|
||||
from loguru import logger
|
||||
|
||||
from middleware.auth_middleware import get_current_user
|
||||
from api.story_writer.utils.auth import require_authenticated_user
|
||||
from services.link_search_service import get_link_search_service
|
||||
|
||||
|
||||
router = APIRouter(prefix="/api/links", tags=["Links"])
|
||||
|
||||
|
||||
class LinkSearchRequest(BaseModel):
|
||||
"""Request for link search (internal or external)."""
|
||||
query: str = Field(..., description="Search query (typically section heading or topic)")
|
||||
link_type: str = Field(
|
||||
...,
|
||||
description="Type of links: 'internal' or 'external'",
|
||||
)
|
||||
site_url: Optional[str] = Field(
|
||||
default=None,
|
||||
description="User's website URL (required for internal links, optional for external to exclude own domain)",
|
||||
)
|
||||
num_results: int = Field(default=5, description="Number of results to return", ge=1, le=15)
|
||||
|
||||
|
||||
class LinkSearchResult(BaseModel):
|
||||
"""A single link search result."""
|
||||
title: str = ""
|
||||
url: str = ""
|
||||
text: str = ""
|
||||
publishedDate: str = ""
|
||||
author: str = ""
|
||||
score: float = 0.5
|
||||
|
||||
|
||||
class LinkSearchResponse(BaseModel):
|
||||
"""Response for link search."""
|
||||
results: List[LinkSearchResult] = Field(default_factory=list)
|
||||
warnings: List[str] = Field(default_factory=list)
|
||||
|
||||
|
||||
class RewordRequest(BaseModel):
|
||||
"""Request to reword text with selected links."""
|
||||
section_text: str = Field(..., description="Full section text")
|
||||
selected_text: Optional[str] = Field(
|
||||
default=None,
|
||||
description="If provided, only reword this portion of the text",
|
||||
)
|
||||
section_heading: Optional[str] = Field(default=None, description="Section heading for context")
|
||||
links: List[Dict[str, str]] = Field(
|
||||
...,
|
||||
description="List of {'url': str, 'title': str} dicts to incorporate",
|
||||
)
|
||||
|
||||
|
||||
class RewordResponse(BaseModel):
|
||||
"""Response for reword-with-links."""
|
||||
reworded_text: str = ""
|
||||
warnings: List[str] = Field(default_factory=list)
|
||||
|
||||
|
||||
@router.post("/search", response_model=LinkSearchResponse)
|
||||
async def search_links(
|
||||
request: LinkSearchRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Search for internal or external links using Exa."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
if request.link_type not in ("internal", "external"):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="link_type must be 'internal' or 'external'",
|
||||
)
|
||||
|
||||
if request.link_type == "internal" and not request.site_url:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="site_url is required for internal link search",
|
||||
)
|
||||
|
||||
if len(request.query) > 500:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="Query must be 500 characters or less",
|
||||
)
|
||||
|
||||
service = get_link_search_service(user_id=user_id)
|
||||
|
||||
try:
|
||||
if request.link_type == "internal":
|
||||
logger.info(f"[Links] Internal search: query='{request.query[:50]}', site='{request.site_url}', user={user_id}")
|
||||
result = await service.search_internal(
|
||||
query=request.query,
|
||||
site_url=request.site_url,
|
||||
user_id=user_id,
|
||||
num_results=request.num_results,
|
||||
)
|
||||
else:
|
||||
logger.info(f"[Links] External search: query='{request.query[:50]}', user={user_id}")
|
||||
result = await service.search_external(
|
||||
query=request.query,
|
||||
site_url=request.site_url,
|
||||
user_id=user_id,
|
||||
num_results=request.num_results,
|
||||
)
|
||||
|
||||
return LinkSearchResponse(
|
||||
results=[LinkSearchResult(**r) for r in result.get("results", [])],
|
||||
warnings=result.get("warnings", []),
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"[Links] Search failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Link search failed: {str(e)}")
|
||||
|
||||
|
||||
@router.post("/reword", response_model=RewordResponse)
|
||||
async def reword_with_links(
|
||||
request: RewordRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Reword text to naturally incorporate selected links."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
if not request.links:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="At least one link must be provided",
|
||||
)
|
||||
|
||||
# Validate each link has a url
|
||||
for i, link in enumerate(request.links):
|
||||
if not link.get("url"):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Link at index {i} is missing a 'url' field",
|
||||
)
|
||||
|
||||
if len(request.section_text) > 10000:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="section_text must be 10000 characters or less",
|
||||
)
|
||||
|
||||
service = get_link_search_service(user_id=user_id)
|
||||
|
||||
try:
|
||||
logger.info(f"[Links] Reword: heading='{request.section_heading}', links={len(request.links)}, user={user_id}")
|
||||
result = service.reword_with_links(
|
||||
section_text=request.section_text,
|
||||
links=request.links,
|
||||
section_heading=request.section_heading,
|
||||
selected_text=request.selected_text,
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
return RewordResponse(
|
||||
reworded_text=result.get("reworded_text", request.section_text),
|
||||
warnings=result.get("warnings", []),
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Links] Reword failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Reword failed: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
async def links_health():
|
||||
"""Health check for Links service."""
|
||||
return {"status": "ok", "service": "links"}
|
||||
@@ -1,17 +1,10 @@
|
||||
"""
|
||||
Onboarding Completion Service
|
||||
Handles the complex logic for completing the onboarding process.
|
||||
|
||||
Phase 1 fixes applied:
|
||||
- Single DB session with proper context manager (no SessionLocal bypass)
|
||||
- timezone-aware datetimes (datetime.now(timezone.utc))
|
||||
- Transactional task creation with partial failure reporting
|
||||
- Business-without-website users: SIF + Market Trends tasks created without website_url
|
||||
- Race-condition safety: upsert pattern (query-then-update-or-insert) for all tasks
|
||||
"""
|
||||
|
||||
from typing import Dict, Any, List
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from datetime import datetime, timedelta
|
||||
import os
|
||||
from urllib.parse import urlparse
|
||||
from fastapi import HTTPException
|
||||
@@ -22,13 +15,12 @@ from services.database import get_session_for_user
|
||||
from services.persona_analysis_service import PersonaAnalysisService
|
||||
from services.research.research_persona_scheduler import schedule_research_persona_generation
|
||||
from services.persona.facebook.facebook_persona_scheduler import schedule_facebook_persona_generation
|
||||
from services.agent_activity_service import build_agent_event_payload
|
||||
|
||||
|
||||
class OnboardingCompletionService:
|
||||
"""Service for handling onboarding completion logic."""
|
||||
|
||||
def __init__(self):
|
||||
# Pre-requisite steps; step 6 is the finalization itself
|
||||
self.required_steps = [1, 2, 3, 4, 5]
|
||||
|
||||
def _normalize_competitor_analysis_for_deep_task(self, competitors: Any) -> List[Dict[str, Any]]:
|
||||
@@ -108,31 +100,15 @@ class OnboardingCompletionService:
|
||||
if domain.startswith("www."):
|
||||
domain = domain[4:]
|
||||
return domain
|
||||
|
||||
@staticmethod
|
||||
def _upsert_task(db, model_cls, user_id: str, filters: dict, defaults: dict):
|
||||
"""Insert-or-update a task row. Uses query-then-update pattern to avoid race conditions."""
|
||||
existing = db.query(model_cls).filter_by(**filters).first()
|
||||
if existing:
|
||||
for key, value in defaults.items():
|
||||
setattr(existing, key, value)
|
||||
db.add(existing)
|
||||
return existing
|
||||
else:
|
||||
row = model_cls(**filters, **defaults)
|
||||
db.add(row)
|
||||
return row
|
||||
|
||||
|
||||
async def complete_onboarding(self, current_user: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Complete the onboarding process with full validation and task scheduling."""
|
||||
scheduled_tasks: List[str] = []
|
||||
failed_tasks: List[Dict[str, str]] = []
|
||||
|
||||
"""Complete the onboarding process with full validation."""
|
||||
try:
|
||||
from services.onboarding.progress_service import OnboardingProgressService
|
||||
user_id = str(current_user.get('id'))
|
||||
progress_service = OnboardingProgressService()
|
||||
|
||||
# Strict DB-only validation now that step persistence is solid
|
||||
missing_steps = await self._validate_required_steps_database(user_id)
|
||||
if missing_steps:
|
||||
missing_steps_str = ", ".join(missing_steps)
|
||||
@@ -141,314 +117,276 @@ class OnboardingCompletionService:
|
||||
detail=f"Cannot complete onboarding. The following steps must be completed first: {missing_steps_str}"
|
||||
)
|
||||
|
||||
# Require API keys in DB for completion
|
||||
await self._validate_api_keys(user_id)
|
||||
|
||||
# Generate writing persona from onboarding data only if not already present
|
||||
persona_generated = await self._generate_persona_from_onboarding(user_id)
|
||||
|
||||
# Complete the onboarding process in database
|
||||
success = progress_service.complete_onboarding(user_id)
|
||||
if not success:
|
||||
raise HTTPException(status_code=500, detail="Failed to mark onboarding as complete")
|
||||
|
||||
# ── APScheduler one-shot tasks (non-blocking) ───────────────────
|
||||
|
||||
# Schedule research persona generation 20 minutes after onboarding completion
|
||||
try:
|
||||
schedule_research_persona_generation(user_id, delay_minutes=20)
|
||||
scheduled_tasks.append("research_persona")
|
||||
logger.info(f"Scheduled research persona generation for user {user_id} (20 min delay)")
|
||||
logger.info(f"Scheduled research persona generation for user {user_id} (20 minutes after onboarding)")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "research_persona", "error": str(e)})
|
||||
# Non-critical: log but don't fail onboarding completion
|
||||
logger.warning(f"Failed to schedule research persona generation for user {user_id}: {e}")
|
||||
|
||||
# Schedule Facebook persona generation 20 minutes after onboarding completion
|
||||
try:
|
||||
schedule_facebook_persona_generation(user_id, delay_minutes=20)
|
||||
scheduled_tasks.append("facebook_persona")
|
||||
logger.info(f"Scheduled Facebook persona generation for user {user_id} (20 min delay)")
|
||||
logger.info(f"Scheduled Facebook persona generation for user {user_id} (20 minutes after onboarding)")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "facebook_persona", "error": str(e)})
|
||||
# Non-critical: log but don't fail onboarding completion
|
||||
logger.warning(f"Failed to schedule Facebook persona generation for user {user_id}: {e}")
|
||||
|
||||
# ── Local DB tasks — single session, proper context manager ──────
|
||||
db = get_session_for_user(user_id)
|
||||
|
||||
# Create OAuth token monitoring tasks for connected platforms
|
||||
try:
|
||||
# Progressive setup (workspace, features)
|
||||
from services.progressive_setup_service import ProgressiveSetupService
|
||||
|
||||
db = get_session_for_user(user_id)
|
||||
try:
|
||||
from services.progressive_setup_service import ProgressiveSetupService
|
||||
setup_service = ProgressiveSetupService(db)
|
||||
setup_service.initialize_user_environment(user_id)
|
||||
logger.info(f"Initialized user environment for {user_id}")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "progressive_setup", "error": str(e)})
|
||||
logger.warning(f"Failed to initialize user environment for {user_id}: {e}")
|
||||
# Initialize user environment (create workspace, setup features)
|
||||
try:
|
||||
setup_service = ProgressiveSetupService(db)
|
||||
setup_service.initialize_user_environment(user_id)
|
||||
logger.info(f"Initialized user environment for {user_id} on onboarding completion")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to initialize user environment for {user_id}: {e}")
|
||||
|
||||
# OAuth token monitoring
|
||||
try:
|
||||
from services.oauth_token_monitoring_service import create_oauth_monitoring_tasks
|
||||
monitoring_tasks = create_oauth_monitoring_tasks(user_id, db)
|
||||
scheduled_tasks.append("oauth_monitoring")
|
||||
logger.info(f"Created {len(monitoring_tasks)} OAuth monitoring tasks for user {user_id}")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "oauth_monitoring", "error": str(e)})
|
||||
logger.warning(f"Failed to create OAuth monitoring tasks for user {user_id}: {e}")
|
||||
logger.info(
|
||||
f"Created {len(monitoring_tasks)} OAuth token monitoring tasks for user {user_id} "
|
||||
f"on onboarding completion"
|
||||
)
|
||||
finally:
|
||||
db.close()
|
||||
except Exception as e:
|
||||
# Non-critical: log but don't fail onboarding completion
|
||||
logger.warning(f"Failed to create OAuth token monitoring tasks for user {user_id}: {e}")
|
||||
|
||||
# Schedule website analysis task creation 5 minutes after onboarding completion
|
||||
try:
|
||||
from services.website_analysis_monitoring_service import schedule_website_analysis_task_creation
|
||||
schedule_website_analysis_task_creation(user_id=user_id, delay_minutes=5)
|
||||
logger.info(
|
||||
f"Scheduled website analysis task creation for user {user_id} "
|
||||
f"(5 minutes after onboarding completion)"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to schedule website analysis task creation for user {user_id}: {e}")
|
||||
|
||||
# Website analysis monitoring (APScheduler one-shot, 5 min delay)
|
||||
try:
|
||||
from services.website_analysis_monitoring_service import schedule_website_analysis_task_creation
|
||||
schedule_website_analysis_task_creation(user_id=user_id, delay_minutes=5)
|
||||
scheduled_tasks.append("website_analysis")
|
||||
logger.info(f"Scheduled website analysis task for user {user_id} (5 min delay)")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "website_analysis", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule website analysis task for user {user_id}: {e}")
|
||||
|
||||
# ── DB-backed scheduled tasks (single transaction) ───────────
|
||||
now = datetime.now(timezone.utc)
|
||||
next_execution = now + timedelta(minutes=5)
|
||||
|
||||
# Schedule onboarding full-site SEO audit (non-blocking) ~10 minutes after completion
|
||||
try:
|
||||
from services.database import SessionLocal
|
||||
from models.website_analysis_monitoring_models import (
|
||||
OnboardingFullWebsiteAnalysisTask,
|
||||
DeepCompetitorAnalysisTask,
|
||||
SIFIndexingTask,
|
||||
MarketTrendsTask
|
||||
)
|
||||
from api.content_planning.services.content_strategy.onboarding import OnboardingDataIntegrationService
|
||||
|
||||
integration_service = OnboardingDataIntegrationService()
|
||||
integrated_data = integration_service.get_integrated_data_sync(user_id, db)
|
||||
website_analysis = integrated_data.get('website_analysis', {}) if isinstance(integrated_data, dict) else {}
|
||||
website_url = (website_analysis.get('website_url') or '').strip() or None
|
||||
db = SessionLocal()
|
||||
try:
|
||||
integration_service = OnboardingDataIntegrationService()
|
||||
integrated_data = integration_service.get_integrated_data_sync(user_id, db)
|
||||
website_analysis = integrated_data.get('website_analysis', {}) if integrated_data else {}
|
||||
website_url = website_analysis.get('website_url')
|
||||
|
||||
if not website_url:
|
||||
try:
|
||||
from services.website_analysis_monitoring_service import clerk_user_id_to_int
|
||||
from models.onboarding import WebsiteAnalysis
|
||||
session_id_int = clerk_user_id_to_int(user_id)
|
||||
analysis = db.query(WebsiteAnalysis).filter(
|
||||
WebsiteAnalysis.session_id == session_id_int
|
||||
).order_by(WebsiteAnalysis.created_at.desc()).first()
|
||||
if analysis and analysis.website_url:
|
||||
website_url = analysis.website_url.strip() or None
|
||||
except Exception:
|
||||
website_url = None
|
||||
if not website_url:
|
||||
try:
|
||||
from services.website_analysis_monitoring_service import clerk_user_id_to_int
|
||||
from models.onboarding import WebsiteAnalysis
|
||||
session_id_int = clerk_user_id_to_int(user_id)
|
||||
analysis = db.query(WebsiteAnalysis).filter(
|
||||
WebsiteAnalysis.session_id == session_id_int
|
||||
).order_by(WebsiteAnalysis.created_at.desc()).first()
|
||||
if analysis and analysis.website_url:
|
||||
website_url = analysis.website_url
|
||||
except Exception:
|
||||
website_url = None
|
||||
|
||||
# --- Tasks that require website_url ---
|
||||
if website_url:
|
||||
# 1. Full-Site SEO Audit
|
||||
try:
|
||||
payload_audit = {
|
||||
if website_url:
|
||||
# 1. Schedule Full Site SEO Audit
|
||||
next_execution = datetime.utcnow() + timedelta(minutes=5)
|
||||
existing = db.query(OnboardingFullWebsiteAnalysisTask).filter(
|
||||
OnboardingFullWebsiteAnalysisTask.user_id == user_id,
|
||||
OnboardingFullWebsiteAnalysisTask.website_url == website_url
|
||||
).first()
|
||||
|
||||
payload = {
|
||||
'website_url': website_url,
|
||||
'max_urls': 500,
|
||||
'created_from': 'onboarding_completion'
|
||||
}
|
||||
self._upsert_task(
|
||||
db, OnboardingFullWebsiteAnalysisTask,
|
||||
user_id=user_id,
|
||||
filters={"user_id": user_id, "website_url": website_url},
|
||||
defaults={
|
||||
"status": "active",
|
||||
"next_execution": next_execution,
|
||||
"payload": payload_audit,
|
||||
}
|
||||
)
|
||||
scheduled_tasks.append("full_site_seo_audit")
|
||||
logger.info(f"Scheduled full-site SEO audit for user {user_id} ({website_url})")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "full_site_seo_audit", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule full-site SEO audit for user {user_id}: {e}")
|
||||
|
||||
# 2. SIF Indexing (with website_url)
|
||||
try:
|
||||
if existing:
|
||||
existing.status = 'active'
|
||||
existing.next_execution = next_execution
|
||||
existing.payload = payload
|
||||
db.add(existing)
|
||||
else:
|
||||
db.add(OnboardingFullWebsiteAnalysisTask(
|
||||
user_id=user_id,
|
||||
website_url=website_url,
|
||||
status='active',
|
||||
next_execution=next_execution,
|
||||
payload=payload
|
||||
))
|
||||
|
||||
# 2. Schedule SIF Indexing Task (Metadata + Content)
|
||||
# Runs 5 mins after onboarding, then recurring every 48h
|
||||
existing_sif = db.query(SIFIndexingTask).filter(
|
||||
SIFIndexingTask.user_id == user_id,
|
||||
SIFIndexingTask.website_url == website_url
|
||||
).first()
|
||||
|
||||
payload_sif = {
|
||||
'website_url': website_url,
|
||||
'mode': 'initial_indexing',
|
||||
'created_from': 'onboarding_completion'
|
||||
}
|
||||
self._upsert_task(
|
||||
db, SIFIndexingTask,
|
||||
user_id=user_id,
|
||||
filters={"user_id": user_id, "website_url": website_url},
|
||||
defaults={
|
||||
"status": "active",
|
||||
"next_execution": next_execution,
|
||||
"frequency_hours": 48,
|
||||
"payload": payload_sif,
|
||||
}
|
||||
|
||||
if existing_sif:
|
||||
existing_sif.status = 'active'
|
||||
existing_sif.next_execution = next_execution
|
||||
existing_sif.frequency_hours = 48
|
||||
existing_sif.payload = payload_sif
|
||||
db.add(existing_sif)
|
||||
else:
|
||||
db.add(SIFIndexingTask(
|
||||
user_id=user_id,
|
||||
website_url=website_url,
|
||||
status='active',
|
||||
next_execution=next_execution,
|
||||
frequency_hours=48,
|
||||
payload=payload_sif
|
||||
))
|
||||
|
||||
logger.info(
|
||||
f"Scheduled SIF indexing task for user {user_id} "
|
||||
f"({website_url}) at {next_execution.isoformat()}"
|
||||
)
|
||||
scheduled_tasks.append("sif_indexing")
|
||||
logger.info(f"Scheduled SIF indexing for user {user_id} ({website_url})")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "sif_indexing", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule SIF indexing for user {user_id}: {e}")
|
||||
|
||||
# 3. Market Trends (with website_url)
|
||||
try:
|
||||
# 3. Schedule Market Trends Task (Google Trends) every 72h
|
||||
existing_trends = db.query(MarketTrendsTask).filter(
|
||||
MarketTrendsTask.user_id == user_id,
|
||||
MarketTrendsTask.website_url == website_url
|
||||
).first()
|
||||
|
||||
payload_trends = {
|
||||
"website_url": website_url,
|
||||
"geo": "US",
|
||||
"timeframe": "today 12-m",
|
||||
"created_from": "onboarding_completion"
|
||||
}
|
||||
self._upsert_task(
|
||||
db, MarketTrendsTask,
|
||||
user_id=user_id,
|
||||
filters={"user_id": user_id, "website_url": website_url},
|
||||
defaults={
|
||||
"status": "active",
|
||||
"next_execution": next_execution,
|
||||
"frequency_hours": 72,
|
||||
"payload": payload_trends,
|
||||
}
|
||||
)
|
||||
scheduled_tasks.append("market_trends")
|
||||
logger.info(f"Scheduled market trends for user {user_id} ({website_url})")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "market_trends", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule market trends for user {user_id}: {e}")
|
||||
|
||||
# 4. Deep Competitor Analysis
|
||||
try:
|
||||
research_prefs = integrated_data.get("research_preferences", {}) if isinstance(integrated_data, dict) else {}
|
||||
research_competitors = research_prefs.get("competitors") if isinstance(research_prefs, dict) else None
|
||||
|
||||
competitor_analysis = integrated_data.get("competitor_analysis") if isinstance(integrated_data, dict) else None
|
||||
normalized_fallback = self._normalize_competitor_analysis_for_deep_task(competitor_analysis)
|
||||
|
||||
selected_source = "research_preferences"
|
||||
competitors = research_competitors
|
||||
if not isinstance(competitors, list) or len(competitors) == 0:
|
||||
competitors = normalized_fallback
|
||||
selected_source = "competitor_analysis"
|
||||
|
||||
logger.info(
|
||||
f"Deep competitor analysis sources for user {user_id}: "
|
||||
f"research_preferences={len(research_competitors) if isinstance(research_competitors, list) else 0}, "
|
||||
f"competitor_analysis={len(normalized_fallback)}"
|
||||
)
|
||||
|
||||
if isinstance(competitors, list) and len(competitors) > 0:
|
||||
payload_deep = {
|
||||
"website_url": website_url,
|
||||
"competitors": competitors,
|
||||
"max_competitors": min(len(competitors), 10),
|
||||
"crawl_concurrency": 4,
|
||||
"mode": "strategic_insights",
|
||||
"baseline_updated_at": website_analysis.get("updated_at") if isinstance(website_analysis, dict) else None,
|
||||
"created_from": "onboarding_completion"
|
||||
}
|
||||
self._upsert_task(
|
||||
db, DeepCompetitorAnalysisTask,
|
||||
user_id=user_id,
|
||||
filters={"user_id": user_id, "website_url": website_url},
|
||||
defaults={
|
||||
"status": "active",
|
||||
"next_execution": next_execution,
|
||||
"payload": payload_deep,
|
||||
}
|
||||
)
|
||||
scheduled_tasks.append("deep_competitor_analysis")
|
||||
logger.info(
|
||||
f"Scheduled deep competitor analysis for user {user_id} "
|
||||
f"({website_url}) with {len(competitors)} competitors from source={selected_source}"
|
||||
)
|
||||
if existing_trends:
|
||||
existing_trends.status = "active"
|
||||
existing_trends.next_execution = next_execution
|
||||
existing_trends.frequency_hours = 72
|
||||
existing_trends.payload = payload_trends
|
||||
db.add(existing_trends)
|
||||
else:
|
||||
logger.warning(
|
||||
f"Deep competitor analysis not scheduled for user {user_id}: "
|
||||
f"no competitors available from research_preferences or competitor_analysis"
|
||||
db.add(MarketTrendsTask(
|
||||
user_id=user_id,
|
||||
website_url=website_url,
|
||||
status="active",
|
||||
next_execution=next_execution,
|
||||
frequency_hours=72,
|
||||
payload=payload_trends
|
||||
))
|
||||
|
||||
db.commit()
|
||||
logger.info(
|
||||
f"Scheduled onboarding full-site SEO audit for user {user_id} "
|
||||
f"({website_url}) at {next_execution.isoformat()}"
|
||||
)
|
||||
|
||||
try:
|
||||
research_prefs = integrated_data.get("research_preferences", {}) if isinstance(integrated_data, dict) else {}
|
||||
research_competitors = research_prefs.get("competitors") if isinstance(research_prefs, dict) else None
|
||||
|
||||
competitor_analysis = integrated_data.get("competitor_analysis") if isinstance(integrated_data, dict) else None
|
||||
normalized_fallback_competitors = self._normalize_competitor_analysis_for_deep_task(competitor_analysis)
|
||||
|
||||
selected_source = "research_preferences"
|
||||
competitors = research_competitors
|
||||
if not isinstance(competitors, list) or len(competitors) == 0:
|
||||
competitors = normalized_fallback_competitors
|
||||
selected_source = "competitor_analysis"
|
||||
|
||||
logger.info(
|
||||
f"Deep competitor analysis source stats for user {user_id}: "
|
||||
f"research_preferences={len(research_competitors) if isinstance(research_competitors, list) else 0}, "
|
||||
f"competitor_analysis={len(normalized_fallback_competitors)}"
|
||||
)
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "deep_competitor_analysis", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule deep competitor analysis for user {user_id}: {e}")
|
||||
|
||||
else:
|
||||
# --- No website URL: still schedule SIF + Market Trends (business-without-website) ---
|
||||
logger.warning(
|
||||
f"No website_url for user {user_id}: scheduling SIF indexing and Market Trends without website URL, "
|
||||
f"skipping SEO audit and deep competitor analysis"
|
||||
)
|
||||
if isinstance(competitors, list) and len(competitors) > 0:
|
||||
existing_deep = db.query(DeepCompetitorAnalysisTask).filter(
|
||||
DeepCompetitorAnalysisTask.user_id == user_id,
|
||||
DeepCompetitorAnalysisTask.website_url == website_url
|
||||
).first()
|
||||
|
||||
try:
|
||||
payload_sif_no_url = {
|
||||
'mode': 'initial_indexing',
|
||||
'created_from': 'onboarding_completion_no_website'
|
||||
}
|
||||
self._upsert_task(
|
||||
db, SIFIndexingTask,
|
||||
user_id=user_id,
|
||||
filters={"user_id": user_id, "website_url": None},
|
||||
defaults={
|
||||
"status": "active",
|
||||
"next_execution": next_execution,
|
||||
"frequency_hours": 48,
|
||||
"payload": payload_sif_no_url,
|
||||
}
|
||||
payload_deep = {
|
||||
"website_url": website_url,
|
||||
"competitors": competitors,
|
||||
"max_competitors": 25,
|
||||
"crawl_concurrency": 4,
|
||||
"mode": "strategic_insights", # Enable recurring weekly strategic insights
|
||||
"baseline_updated_at": website_analysis.get("updated_at") if isinstance(website_analysis, dict) else None,
|
||||
"created_from": "onboarding_completion"
|
||||
}
|
||||
|
||||
if existing_deep:
|
||||
existing_deep.status = "active"
|
||||
existing_deep.next_execution = next_execution
|
||||
existing_deep.payload = payload_deep
|
||||
db.add(existing_deep)
|
||||
else:
|
||||
db.add(DeepCompetitorAnalysisTask(
|
||||
user_id=user_id,
|
||||
website_url=website_url,
|
||||
status="active",
|
||||
next_execution=next_execution,
|
||||
payload=payload_deep
|
||||
))
|
||||
|
||||
db.commit()
|
||||
logger.info(
|
||||
f"Scheduled deep competitor analysis for user {user_id} "
|
||||
f"({website_url}) at {next_execution.isoformat()} with {len(competitors)} competitors "
|
||||
f"from source={selected_source}"
|
||||
)
|
||||
else:
|
||||
logger.warning(
|
||||
f"Deep competitor analysis not scheduled for user {user_id}: "
|
||||
f"no competitors available from research_preferences or competitor_analysis"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to schedule deep competitor analysis for user {user_id}: {e}")
|
||||
else:
|
||||
logger.warning(
|
||||
f"Could not schedule onboarding full-site SEO audit for user {user_id}: "
|
||||
f"website_url missing"
|
||||
)
|
||||
scheduled_tasks.append("sif_indexing_no_url")
|
||||
logger.info(f"Scheduled SIF indexing (no website) for user {user_id}")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "sif_indexing_no_url", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule SIF indexing (no website) for user {user_id}: {e}")
|
||||
|
||||
try:
|
||||
payload_trends_no_url = {
|
||||
"geo": "US",
|
||||
"timeframe": "today 12-m",
|
||||
"created_from": "onboarding_completion_no_website"
|
||||
}
|
||||
self._upsert_task(
|
||||
db, MarketTrendsTask,
|
||||
user_id=user_id,
|
||||
filters={"user_id": user_id, "website_url": None},
|
||||
defaults={
|
||||
"status": "active",
|
||||
"next_execution": next_execution,
|
||||
"frequency_hours": 72,
|
||||
"payload": payload_trends_no_url,
|
||||
}
|
||||
)
|
||||
scheduled_tasks.append("market_trends_no_url")
|
||||
logger.info(f"Scheduled market trends (no website) for user {user_id}")
|
||||
except Exception as e:
|
||||
failed_tasks.append({"task": "market_trends_no_url", "error": str(e)})
|
||||
logger.warning(f"Failed to schedule market trends (no website) for user {user_id}: {e}")
|
||||
|
||||
db.commit()
|
||||
finally:
|
||||
db.close()
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
failed_tasks.append({"task": "db_scheduled_tasks", "error": str(e)})
|
||||
logger.error(f"Failed to create DB tasks for user {user_id}: {e}")
|
||||
finally:
|
||||
db.close()
|
||||
logger.warning(f"Failed to schedule onboarding full-site SEO audit for user {user_id}: {e}")
|
||||
|
||||
try:
|
||||
from services.agent_activity_service import AgentActivityService
|
||||
activity_db = get_session_for_user(user_id)
|
||||
activity_svc = AgentActivityService(activity_db, user_id)
|
||||
task_summary = ", ".join(scheduled_tasks) if scheduled_tasks else "none"
|
||||
fail_summary = ", ".join(t.get("task", "?") for t in failed_tasks) if failed_tasks else "none"
|
||||
activity_svc.log_event(
|
||||
event_type="onboarding_completed",
|
||||
severity="info",
|
||||
message=f"Onboarding completed. Scheduled: {task_summary}. Failed: {fail_summary}.",
|
||||
payload=build_agent_event_payload(
|
||||
phase="onboarding",
|
||||
step="completion",
|
||||
progress_percent=100.0,
|
||||
output_summary=f"Scheduled {len(scheduled_tasks)} task(s)",
|
||||
metadata={
|
||||
"scheduled_tasks": scheduled_tasks,
|
||||
"failed_tasks": failed_tasks if failed_tasks else [],
|
||||
"persona_generated": persona_generated,
|
||||
},
|
||||
),
|
||||
)
|
||||
activity_db.close()
|
||||
except Exception as act_err:
|
||||
logger.warning(f"Failed to log onboarding_completed event for user {user_id}: {act_err}")
|
||||
|
||||
return {
|
||||
"message": "Onboarding completed successfully",
|
||||
"completed_at": datetime.now(timezone.utc).isoformat(),
|
||||
"completed_at": datetime.now().isoformat(),
|
||||
"completion_percentage": 100.0,
|
||||
"persona_generated": persona_generated,
|
||||
"scheduled_tasks": scheduled_tasks,
|
||||
"failed_tasks": failed_tasks if failed_tasks else None,
|
||||
"persona_generated": persona_generated
|
||||
}
|
||||
|
||||
except HTTPException:
|
||||
@@ -462,72 +400,81 @@ class OnboardingCompletionService:
|
||||
missing_steps = []
|
||||
try:
|
||||
db = get_session_for_user(user_id)
|
||||
try:
|
||||
integration_service = OnboardingDataIntegrationService()
|
||||
|
||||
logger.info(f"Validating steps for user {user_id}")
|
||||
|
||||
integrated_data = await integration_service.process_onboarding_data(user_id, db)
|
||||
integration_service = OnboardingDataIntegrationService()
|
||||
|
||||
logger.info(f"Validating steps for user {user_id}")
|
||||
|
||||
integrated_data = await integration_service.process_onboarding_data(user_id, db)
|
||||
db.close()
|
||||
|
||||
from services.onboarding.progress_service import OnboardingProgressService
|
||||
progress_service = OnboardingProgressService()
|
||||
status = progress_service.get_onboarding_status(user_id)
|
||||
current_step = status.get("current_step", 1)
|
||||
from services.onboarding.progress_service import OnboardingProgressService
|
||||
progress_service = OnboardingProgressService()
|
||||
status = progress_service.get_onboarding_status(user_id)
|
||||
current_step = status.get("current_step", 1)
|
||||
|
||||
for step_num in self.required_steps:
|
||||
step_completed = False
|
||||
|
||||
for step_num in self.required_steps:
|
||||
step_completed = False
|
||||
|
||||
if step_num == 1:
|
||||
api_keys_data = integrated_data.get('api_keys_data', {})
|
||||
step_completed = bool(
|
||||
api_keys_data.get('openai_api_key') or
|
||||
api_keys_data.get('anthropic_api_key') or
|
||||
api_keys_data.get('google_api_key')
|
||||
)
|
||||
if not step_completed:
|
||||
has_global_providers = bool(
|
||||
os.getenv("EXA_API_KEY") or
|
||||
os.getenv("GEMINI_API_KEY") or
|
||||
os.getenv("OPENAI_API_KEY") or
|
||||
os.getenv("ANTHROPIC_API_KEY") or
|
||||
os.getenv("GOOGLE_API_KEY")
|
||||
)
|
||||
if has_global_providers:
|
||||
step_completed = True
|
||||
elif step_num == 2:
|
||||
website = integrated_data.get('website_analysis', {})
|
||||
step_completed = bool(website and (website.get('website_url') or website.get('writing_style')))
|
||||
elif step_num == 3:
|
||||
research = integrated_data.get('research_preferences', {})
|
||||
step_completed = bool(research and (research.get('research_depth') or research.get('content_types')))
|
||||
elif step_num == 4:
|
||||
persona = integrated_data.get('persona_data', {})
|
||||
step_completed = bool(persona and (persona.get('corePersona') or persona.get('platformPersonas')))
|
||||
if not step_completed:
|
||||
logger.warning(
|
||||
f"Step 4 incomplete for user {user_id}: no persona data found. "
|
||||
f"Step will be auto-passed only if user has explicitly reached step 4."
|
||||
)
|
||||
elif step_num == 5:
|
||||
integrations_complete = bool(integrated_data.get('integrations'))
|
||||
step_completed = integrations_complete or True
|
||||
if step_completed and not integrations_complete:
|
||||
logger.info(f"Step 5 auto-passed for user {user_id}: integrations are optional")
|
||||
|
||||
if not step_completed and current_step >= step_num:
|
||||
step_completed = True
|
||||
|
||||
if step_num == 1:
|
||||
api_keys_data = integrated_data.get('api_keys_data', {})
|
||||
logger.info(f"Step 1 - API Keys: {api_keys_data}")
|
||||
step_completed = bool(
|
||||
api_keys_data.get('openai_api_key') or
|
||||
api_keys_data.get('anthropic_api_key') or
|
||||
api_keys_data.get('google_api_key')
|
||||
)
|
||||
if not step_completed:
|
||||
missing_steps.append(f"Step {step_num}")
|
||||
has_global_providers = bool(
|
||||
os.getenv("EXA_API_KEY") or
|
||||
os.getenv("GEMINI_API_KEY") or
|
||||
os.getenv("OPENAI_API_KEY") or
|
||||
os.getenv("ANTHROPIC_API_KEY") or
|
||||
os.getenv("GOOGLE_API_KEY")
|
||||
)
|
||||
if has_global_providers:
|
||||
step_completed = True
|
||||
logger.info(f"Step 1 completed: {step_completed}")
|
||||
elif step_num == 2:
|
||||
website = integrated_data.get('website_analysis', {})
|
||||
logger.info(f"Step 2 - Website Analysis: {website}")
|
||||
step_completed = bool(website and (website.get('website_url') or website.get('writing_style')))
|
||||
logger.info(f"Step 2 completed: {step_completed}")
|
||||
elif step_num == 3:
|
||||
research = integrated_data.get('research_preferences', {})
|
||||
logger.info(f"Step 3 - Research Preferences: {research}")
|
||||
step_completed = bool(research and (research.get('research_depth') or research.get('content_types')))
|
||||
logger.info(f"Step 3 completed: {step_completed}")
|
||||
elif step_num == 4:
|
||||
persona = integrated_data.get('persona_data', {})
|
||||
logger.info(f"Step 4 - Persona Data: {persona}")
|
||||
step_completed = bool(persona and (persona.get('corePersona') or persona.get('platformPersonas')))
|
||||
if not step_completed:
|
||||
website = integrated_data.get('website_analysis', {})
|
||||
research = integrated_data.get('research_preferences', {})
|
||||
basic_ready = bool(
|
||||
website and (website.get('website_url') or website.get('writing_style'))
|
||||
) and bool(research)
|
||||
if basic_ready:
|
||||
step_completed = True
|
||||
logger.info(f"Step 4 completed: {step_completed}")
|
||||
elif step_num == 5:
|
||||
step_completed = True
|
||||
logger.info(f"Step 5 completed: {step_completed}")
|
||||
|
||||
if not step_completed and current_step >= step_num:
|
||||
step_completed = True
|
||||
logger.info(
|
||||
f"Step {step_num} marked completed based on progress service (current_step={current_step})"
|
||||
)
|
||||
|
||||
logger.info(f"Missing steps for user {user_id}: {missing_steps}")
|
||||
return missing_steps
|
||||
|
||||
finally:
|
||||
db.close()
|
||||
if not step_completed:
|
||||
missing_steps.append(f"Step {step_num}")
|
||||
|
||||
logger.info(f"Missing steps: {missing_steps}")
|
||||
return missing_steps
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error validating required steps for user {user_id}: {e}")
|
||||
logger.error(f"Error validating required steps: {e}")
|
||||
return ["Validation error"]
|
||||
|
||||
async def _validate_api_keys(self, user_id: str):
|
||||
@@ -558,7 +505,9 @@ class OnboardingCompletionService:
|
||||
os.getenv("GEMINI_API_KEY")
|
||||
)
|
||||
|
||||
if not (has_user_keys or has_env_keys):
|
||||
has_keys = has_user_keys or has_env_keys
|
||||
|
||||
if not has_keys:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="Cannot complete onboarding. At least one AI provider API key must be configured in your account."
|
||||
@@ -571,10 +520,9 @@ class OnboardingCompletionService:
|
||||
detail="Cannot complete onboarding. API key validation failed."
|
||||
)
|
||||
|
||||
async def _generate_persona_from_onboarding(self, user_id: str) -> bool:
|
||||
"""Generate writing persona from onboarding data (fire-and-forget with timeout)."""
|
||||
async def _generate_persona_from_onboarding(self, user_id: str) -> bool:
|
||||
"""Generate writing persona from onboarding data."""
|
||||
try:
|
||||
import asyncio
|
||||
persona_service = PersonaAnalysisService()
|
||||
|
||||
try:
|
||||
@@ -583,27 +531,17 @@ async def _generate_persona_from_onboarding(self, user_id: str) -> bool:
|
||||
logger.info("Persona already exists for user %s; skipping regeneration during completion", user_id)
|
||||
return False
|
||||
except Exception:
|
||||
# Non-fatal; proceed to attempt generation
|
||||
pass
|
||||
|
||||
try:
|
||||
persona_result = await asyncio.wait_for(
|
||||
asyncio.get_event_loop().run_in_executor(
|
||||
None,
|
||||
persona_service.generate_persona_from_onboarding,
|
||||
user_id
|
||||
),
|
||||
timeout=30.0
|
||||
)
|
||||
except asyncio.TimeoutError:
|
||||
logger.warning(f"Persona generation timed out (30s) for user {user_id}; will be generated by scheduled task")
|
||||
return False
|
||||
persona_result = persona_service.generate_persona_from_onboarding(user_id)
|
||||
|
||||
if "error" not in persona_result:
|
||||
logger.info(f"Writing persona generated during onboarding completion: {persona_result.get('persona_id')}")
|
||||
logger.info(f"✅ Writing persona generated during onboarding completion: {persona_result.get('persona_id')}")
|
||||
return True
|
||||
else:
|
||||
logger.warning(f"Persona generation failed during onboarding: {persona_result['error']}")
|
||||
logger.warning(f"⚠️ Persona generation failed during onboarding: {persona_result['error']}")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.warning(f"Non-critical error generating persona during onboarding: {str(e)}")
|
||||
return False
|
||||
logger.warning(f"⚠️ Non-critical error generating persona during onboarding: {str(e)}")
|
||||
return False
|
||||
|
||||
@@ -50,40 +50,22 @@ class OnboardingControlService:
|
||||
db.close()
|
||||
|
||||
async def reset_onboarding(self, current_user: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Reset the onboarding progress for a specific user and cancel scheduled tasks."""
|
||||
"""Reset the onboarding progress for a specific user."""
|
||||
try:
|
||||
from services.onboarding.progress_service import OnboardingProgressService
|
||||
user_id = str(current_user.get('clerk_user_id') or current_user.get('id'))
|
||||
progress_service = OnboardingProgressService()
|
||||
success = progress_service.reset_onboarding(user_id)
|
||||
|
||||
if not success:
|
||||
if success:
|
||||
return {
|
||||
"message": "Onboarding progress reset successfully",
|
||||
"current_step": 1,
|
||||
"started_at": None,
|
||||
"user_id": user_id
|
||||
}
|
||||
else:
|
||||
raise HTTPException(status_code=500, detail="Failed to reset onboarding progress")
|
||||
|
||||
# Cancel APScheduler one-shot jobs for this user
|
||||
cancelled_jobs = []
|
||||
try:
|
||||
from services.scheduler import get_scheduler
|
||||
scheduler = get_scheduler()
|
||||
for job_id_suffix in ["research_persona", "facebook_persona"]:
|
||||
job_id = f"{job_id_suffix}_{user_id}"
|
||||
try:
|
||||
scheduler.scheduler.remove_job(job_id)
|
||||
cancelled_jobs.append(job_id)
|
||||
except Exception:
|
||||
pass
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not cancel APScheduler jobs for user {user_id}: {e}")
|
||||
|
||||
return {
|
||||
"message": "Onboarding progress reset successfully",
|
||||
"current_step": 1,
|
||||
"started_at": None,
|
||||
"user_id": user_id,
|
||||
"cancelled_jobs": cancelled_jobs if cancelled_jobs else None,
|
||||
}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error resetting onboarding: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Internal server error")
|
||||
|
||||
@@ -9,27 +9,13 @@ from fastapi.responses import FileResponse
|
||||
from sqlalchemy.orm import Session
|
||||
from pydantic import BaseModel
|
||||
from loguru import logger
|
||||
from .step4_persona_routes import _extract_user_id
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
|
||||
def _extract_user_id(user: Dict[str, Any]) -> str:
|
||||
"""Extract a stable user ID from Clerk-authenticated user payloads.
|
||||
Prefers 'clerk_user_id' or 'id', falls back to 'user_id', else 'unknown'.
|
||||
"""
|
||||
if not isinstance(user, dict):
|
||||
return 'unknown'
|
||||
return (
|
||||
user.get('clerk_user_id')
|
||||
or user.get('id')
|
||||
or user.get('user_id')
|
||||
or 'unknown'
|
||||
)
|
||||
import base64
|
||||
import os
|
||||
from pathlib import Path
|
||||
from utils.file_storage import save_file_safely, generate_unique_filename
|
||||
from services.database import get_db
|
||||
from utils.storage_paths import get_user_workspace, sanitize_user_id
|
||||
from services.database import get_db, WORKSPACE_DIR
|
||||
from utils.asset_tracker import save_asset_to_library
|
||||
from models.content_asset_models import ContentAsset, AssetType, AssetSource
|
||||
from sqlalchemy import desc
|
||||
@@ -87,8 +73,6 @@ async def get_latest_avatar(
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
|
||||
logger.warning(f"[latest-avatar] Looking for avatar for user_id: {user_id}")
|
||||
|
||||
# Search for assets that are either:
|
||||
# 1. Saved with source_module=BRAND_AVATAR_GENERATOR (new)
|
||||
# 2. Saved with source_module=STORY_WRITER but have metadata category='brand_avatar' (legacy)
|
||||
@@ -103,8 +87,6 @@ async def get_latest_avatar(
|
||||
])
|
||||
).order_by(desc(ContentAsset.created_at)).limit(50).all()
|
||||
|
||||
logger.warning(f"[latest-avatar] Found {len(candidates)} candidate(s)")
|
||||
|
||||
asset = None
|
||||
for candidate in candidates:
|
||||
# Check for direct match (new assets)
|
||||
@@ -185,7 +167,7 @@ async def generate_avatar(
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
|
||||
logger.warning(f"Generating avatar for user {user_id} with prompt: {request.prompt}")
|
||||
logger.info(f"Generating avatar for user {user_id} with prompt: {request.prompt}")
|
||||
|
||||
# 1. Generate Image
|
||||
result = await generate_image_with_provider(
|
||||
@@ -235,7 +217,7 @@ async def generate_avatar(
|
||||
content_to_save = base64.b64decode(image_data) if isinstance(image_data, str) else image_data
|
||||
|
||||
# Construct user assets directory
|
||||
user_assets_dir = get_user_workspace(user_id) / "assets" / "avatars"
|
||||
user_assets_dir = Path(WORKSPACE_DIR) / f"workspace_{user_id}" / "assets" / "avatars"
|
||||
|
||||
saved_path, error = save_file_safely(
|
||||
content_to_save,
|
||||
@@ -288,7 +270,7 @@ async def enhance_prompt_route(
|
||||
"""Enhance a simple prompt into a detailed midjourney-style prompt."""
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
logger.warning(f"Enhancing prompt for user {user_id}: {request.prompt}")
|
||||
logger.info(f"Enhancing prompt for user {user_id}: {request.prompt}")
|
||||
|
||||
enhanced_prompt = await enhance_image_prompt(request.prompt, user_id=user_id)
|
||||
|
||||
@@ -312,7 +294,7 @@ async def create_variation_route(
|
||||
"""Generate a variation of an existing avatar."""
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
logger.warning(f"Creating variation for user {user_id} with prompt: {prompt}")
|
||||
logger.info(f"Creating variation for user {user_id} with prompt: {prompt}")
|
||||
|
||||
# Read file
|
||||
file_content = await file.read()
|
||||
@@ -333,7 +315,7 @@ async def create_variation_route(
|
||||
content_to_save = base64.b64decode(image_data)
|
||||
|
||||
# Construct user assets directory
|
||||
user_assets_dir = get_user_workspace(user_id) / "assets" / "avatars"
|
||||
user_assets_dir = Path(WORKSPACE_DIR) / f"workspace_{user_id}" / "assets" / "avatars"
|
||||
|
||||
saved_path, error = save_file_safely(
|
||||
content_to_save,
|
||||
@@ -387,7 +369,7 @@ async def enhance_avatar_route(
|
||||
"""Enhance/Upscale an existing avatar."""
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
logger.warning(f"Enhancing avatar for user {user_id}")
|
||||
logger.info(f"Enhancing avatar for user {user_id}")
|
||||
|
||||
# Read file
|
||||
file_content = await file.read()
|
||||
@@ -407,7 +389,7 @@ async def enhance_avatar_route(
|
||||
content_to_save = base64.b64decode(image_data)
|
||||
|
||||
# Construct user assets directory
|
||||
user_assets_dir = get_user_workspace(user_id) / "assets" / "avatars"
|
||||
user_assets_dir = Path(WORKSPACE_DIR) / f"workspace_{user_id}" / "assets" / "avatars"
|
||||
|
||||
saved_path, error = save_file_safely(
|
||||
content_to_save,
|
||||
@@ -464,13 +446,13 @@ async def create_voice_clone(
|
||||
"""Create a voice clone from an audio file."""
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
logger.warning(f"[VoiceClone] Creating voice clone '{voice_name}' (engine={engine}) for user {user_id}")
|
||||
logger.info(f"Creating voice clone '{voice_name}' (engine={engine}) for user {user_id}")
|
||||
|
||||
# 1. Save uploaded audio file
|
||||
file_content = await file.read()
|
||||
filename = generate_unique_filename("voice_sample", Path(file.filename).suffix.lstrip("."))
|
||||
|
||||
user_voice_dir = get_user_workspace(user_id) / "assets" / "voice_samples"
|
||||
user_voice_dir = Path(WORKSPACE_DIR) / f"workspace_{user_id}" / "assets" / "voice_samples"
|
||||
saved_path, error = save_file_safely(file_content, user_voice_dir, filename)
|
||||
|
||||
if error or not saved_path:
|
||||
@@ -492,7 +474,7 @@ async def create_voice_clone(
|
||||
random_suffix = ''.join(random.choices(string.ascii_letters + string.digits, k=8))
|
||||
custom_voice_id = f"vc_{random_suffix}"
|
||||
|
||||
logger.warning(f"Cloning voice with Minimax, ID: {custom_voice_id}")
|
||||
logger.info(f"Cloning voice with Minimax, ID: {custom_voice_id}")
|
||||
|
||||
# Run blocking call in executor
|
||||
result = await loop.run_in_executor(
|
||||
@@ -507,7 +489,7 @@ async def create_voice_clone(
|
||||
preview_audio_bytes = result.preview_audio_bytes
|
||||
|
||||
elif engine.lower() == "cosyvoice":
|
||||
logger.warning("Cloning voice with CosyVoice")
|
||||
logger.info("Cloning voice with CosyVoice")
|
||||
result = await loop.run_in_executor(
|
||||
None,
|
||||
lambda: cosyvoice_voice_clone(
|
||||
@@ -522,7 +504,7 @@ async def create_voice_clone(
|
||||
custom_voice_id = f"vc_cosy_{asset_uuid}"
|
||||
|
||||
else: # qwen3 (default)
|
||||
logger.warning("Cloning voice with Qwen3")
|
||||
logger.info("Cloning voice with Qwen3")
|
||||
result = await loop.run_in_executor(
|
||||
None,
|
||||
lambda: qwen3_voice_clone(
|
||||
@@ -538,48 +520,27 @@ async def create_voice_clone(
|
||||
|
||||
# 3. Save Preview Audio (if generated)
|
||||
preview_url = None
|
||||
preview_mime_type = "audio/wav"
|
||||
actual_filename = None # Default if preview save fails
|
||||
|
||||
if preview_audio_bytes and len(preview_audio_bytes) > 0:
|
||||
from utils.media_utils import detect_audio_format, ensure_audio_extension
|
||||
if preview_audio_bytes:
|
||||
preview_filename = f"preview_{filename}"
|
||||
# Ensure it ends with .wav
|
||||
if not preview_filename.endswith(".wav"):
|
||||
preview_filename = str(Path(preview_filename).with_suffix('.wav'))
|
||||
|
||||
detected_fmt, preview_mime_type = detect_audio_format(preview_audio_bytes)
|
||||
logger.warning(f"[VoiceClone] Detected preview audio format: {detected_fmt} ({preview_mime_type}), {len(preview_audio_bytes)} bytes")
|
||||
|
||||
# Build filename with correct extension based on actual content format
|
||||
original_stem = Path(filename).stem
|
||||
preview_filename = f"preview_{original_stem}"
|
||||
preview_filename = ensure_audio_extension(preview_filename, preview_audio_bytes)
|
||||
|
||||
user_voice_dir = get_user_workspace(user_id) / "assets" / "voice_samples"
|
||||
user_voice_dir = Path(WORKSPACE_DIR) / f"workspace_{user_id}" / "assets" / "voice_samples"
|
||||
saved_preview_path, error = save_file_safely(preview_audio_bytes, user_voice_dir, preview_filename)
|
||||
|
||||
if not error and saved_preview_path:
|
||||
# Use actual saved filename (may have UUID suffix added by save_file_safely)
|
||||
actual_filename = saved_preview_path.name
|
||||
preview_url = f"/api/assets/{user_id}/voice_samples/{actual_filename}"
|
||||
logger.warning(f"[VoiceClone] Saved preview: {actual_filename} ({saved_preview_path.stat().st_size} bytes, {preview_mime_type})")
|
||||
|
||||
# Verify file exists
|
||||
if not saved_preview_path.exists():
|
||||
logger.warning(f"[VoiceClone] Preview file does not exist after save: {saved_preview_path}")
|
||||
preview_url = None
|
||||
else:
|
||||
logger.warning(f"[VoiceClone] Failed to save preview audio: {error}")
|
||||
preview_url = f"/api/assets/{user_id}/voice_samples/{preview_filename}"
|
||||
|
||||
# 4. Save to Asset Library
|
||||
# Use the preview file (with corrected .wav extension) as the main asset file
|
||||
has_valid_preview = preview_audio_bytes and len(preview_audio_bytes) > 0 and saved_preview_path
|
||||
stored_filename = actual_filename if has_valid_preview else filename
|
||||
asset_id = save_asset_to_library(
|
||||
db=db,
|
||||
user_id=user_id,
|
||||
file_path=file_path,
|
||||
asset_type="audio",
|
||||
source_module="voice_cloner",
|
||||
filename=stored_filename,
|
||||
file_url=f"/api/assets/{user_id}/voice_samples/{stored_filename}",
|
||||
filename=filename,
|
||||
file_url=f"/api/assets/{user_id}/voice_samples/{filename}",
|
||||
asset_metadata={
|
||||
"voice_name": voice_name,
|
||||
"engine": engine,
|
||||
@@ -594,7 +555,7 @@ async def create_voice_clone(
|
||||
return {
|
||||
"success": True,
|
||||
"custom_voice_id": custom_voice_id,
|
||||
"preview_audio_url": preview_url or f"/api/assets/{user_id}/voice_samples/{stored_filename}",
|
||||
"preview_audio_url": preview_url or f"/api/assets/{user_id}/voice_samples/{filename}",
|
||||
"asset_id": asset_id,
|
||||
"message": "Voice clone created successfully"
|
||||
}
|
||||
@@ -613,7 +574,7 @@ async def create_voice_design(
|
||||
"""Create a voice from text description (Voice Design)."""
|
||||
try:
|
||||
user_id = _extract_user_id(current_user)
|
||||
logger.warning(f"Designing voice for user {user_id}")
|
||||
logger.info(f"Designing voice for user {user_id}")
|
||||
|
||||
loop = asyncio.get_event_loop()
|
||||
|
||||
@@ -627,15 +588,9 @@ async def create_voice_design(
|
||||
)
|
||||
)
|
||||
|
||||
# Save the result to a file with correct extension based on content
|
||||
from utils.media_utils import detect_audio_format, ensure_audio_extension
|
||||
detected_fmt, mime_type = detect_audio_format(result.preview_audio_bytes)
|
||||
logger.warning(f"[VoiceDesign] Detected audio format: {detected_fmt} ({mime_type})")
|
||||
|
||||
filename = generate_unique_filename("voice_design_preview", detected_fmt)
|
||||
filename = ensure_audio_extension(filename, result.preview_audio_bytes)
|
||||
|
||||
user_voice_dir = get_user_workspace(user_id) / "assets" / "voice_samples"
|
||||
# Save the result to a temporary file
|
||||
filename = generate_unique_filename("voice_design_preview", "wav")
|
||||
user_voice_dir = Path(WORKSPACE_DIR) / f"workspace_{user_id}" / "assets" / "voice_samples"
|
||||
saved_path, error = save_file_safely(result.preview_audio_bytes, user_voice_dir, filename)
|
||||
|
||||
if error or not saved_path:
|
||||
|
||||
@@ -94,36 +94,36 @@ async def generate_platform_persona_endpoint(
|
||||
async def update_persona_endpoint(
|
||||
persona_id: int,
|
||||
update_data: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(..., description="User ID")
|
||||
):
|
||||
"""Update an existing persona."""
|
||||
user_id = int(current_user.get("id"))
|
||||
return await update_persona(user_id, persona_id, update_data)
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
return await update_persona(1, persona_id, update_data)
|
||||
|
||||
@router.delete("/{persona_id}")
|
||||
async def delete_persona_endpoint(
|
||||
persona_id: int,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(..., description="User ID")
|
||||
):
|
||||
"""Delete a persona."""
|
||||
user_id = int(current_user.get("id"))
|
||||
return await delete_persona(user_id, persona_id)
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
return await delete_persona(1, persona_id)
|
||||
|
||||
@router.get("/check/readiness")
|
||||
async def check_persona_readiness_endpoint(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(1, description="User ID")
|
||||
):
|
||||
"""Check if user has sufficient data for persona generation."""
|
||||
user_id = int(current_user.get("id"))
|
||||
return await validate_persona_generation_readiness(user_id)
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
return await validate_persona_generation_readiness(1)
|
||||
|
||||
@router.get("/preview/generate")
|
||||
async def generate_preview_endpoint(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(1, description="User ID")
|
||||
):
|
||||
"""Generate a preview of the writing persona without saving."""
|
||||
user_id = int(current_user.get("id"))
|
||||
return await generate_persona_preview(user_id)
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
return await generate_persona_preview(1)
|
||||
|
||||
@router.get("/platforms/supported")
|
||||
async def get_supported_platforms_endpoint():
|
||||
@@ -160,12 +160,12 @@ async def optimize_facebook_persona_endpoint(
|
||||
|
||||
@router.post("/generate-content")
|
||||
async def generate_content_with_persona_endpoint(
|
||||
request: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
request: Dict[str, Any]
|
||||
):
|
||||
"""Generate content using persona replication engine."""
|
||||
try:
|
||||
user_id = int(current_user.get("id"))
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
user_id = 1
|
||||
platform = request.get("platform")
|
||||
content_request = request.get("content_request")
|
||||
content_type = request.get("content_type", "post")
|
||||
@@ -189,13 +189,13 @@ async def generate_content_with_persona_endpoint(
|
||||
@router.get("/export/{platform}")
|
||||
async def export_persona_prompt_endpoint(
|
||||
platform: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(1, description="User ID")
|
||||
):
|
||||
"""Export hardened persona prompt for external use."""
|
||||
try:
|
||||
engine = PersonaReplicationEngine()
|
||||
user_id = int(current_user.get("id"))
|
||||
export_package = engine.export_persona_for_external_use(user_id, platform)
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
export_package = engine.export_persona_for_external_use(1, platform)
|
||||
|
||||
if "error" in export_package:
|
||||
raise HTTPException(status_code=400, detail=export_package["error"])
|
||||
@@ -207,12 +207,12 @@ async def export_persona_prompt_endpoint(
|
||||
|
||||
@router.post("/validate-content")
|
||||
async def validate_content_endpoint(
|
||||
request: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
request: Dict[str, Any]
|
||||
):
|
||||
"""Validate content against persona constraints."""
|
||||
try:
|
||||
user_id = int(current_user.get("id"))
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
user_id = 1
|
||||
platform = request.get("platform")
|
||||
content = request.get("content")
|
||||
|
||||
@@ -242,14 +242,14 @@ async def validate_content_endpoint(
|
||||
async def update_platform_persona_endpoint(
|
||||
platform: str,
|
||||
update_data: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
user_id: int = Query(1, description="User ID")
|
||||
):
|
||||
"""Update platform-specific persona fields for a user.
|
||||
|
||||
Allows editing persona fields in the UI and saving them to the database.
|
||||
"""
|
||||
user_id = int(current_user.get("id"))
|
||||
return await update_platform_persona(user_id, platform, update_data)
|
||||
# Beta testing: Force user_id=1 for all requests
|
||||
return await update_platform_persona(1, platform, update_data)
|
||||
|
||||
@router.get("/facebook-persona/check/{user_id}")
|
||||
async def check_facebook_persona_endpoint(
|
||||
|
||||
@@ -2,24 +2,33 @@
|
||||
Podcast API Constants
|
||||
|
||||
Centralized constants and directory configuration for podcast module.
|
||||
All workspace paths use utils.storage_paths for root resolution.
|
||||
"""
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Literal
|
||||
from loguru import logger
|
||||
from services.story_writer.audio_generation_service import StoryAudioGenerationService
|
||||
from services.workspace_paths import get_workspace_root, get_user_workspace_dir
|
||||
|
||||
# Video subdirectory (relative to workspace media dir)
|
||||
# Directory paths
|
||||
# router.py is at: backend/api/podcast/router.py
|
||||
# parents[0] = backend/api/podcast/
|
||||
# parents[1] = backend/api/
|
||||
# parents[2] = backend/
|
||||
# parents[3] = root/
|
||||
ROOT_DIR = Path(__file__).resolve().parents[3] # root/
|
||||
DATA_MEDIA_DIR = ROOT_DIR / "data" / "media"
|
||||
|
||||
PODCAST_AUDIO_DIR = (DATA_MEDIA_DIR / "podcast_audio").resolve()
|
||||
PODCAST_IMAGES_DIR = (DATA_MEDIA_DIR / "podcast_images").resolve()
|
||||
PODCAST_VIDEOS_DIR = (DATA_MEDIA_DIR / "podcast_videos").resolve()
|
||||
|
||||
# Video subdirectory
|
||||
AI_VIDEO_SUBDIR = Path("AI_Videos")
|
||||
|
||||
# Legacy constants - DEPRECATED, use get_podcast_media_dir() instead
|
||||
# Kept for backward compatibility with some handlers
|
||||
PODCAST_AVATARS_SUBDIR = Path("avatars")
|
||||
MediaType = Literal["audio", "image", "video"]
|
||||
|
||||
MediaType = Literal["audio", "image", "video", "chart"]
|
||||
|
||||
def _sanitize_user_id(user_id: str) -> str:
|
||||
return "".join(c for c in user_id if c.isalnum() or c in ("-", "_"))
|
||||
|
||||
|
||||
def get_podcast_media_dir(
|
||||
@@ -28,25 +37,18 @@ def get_podcast_media_dir(
|
||||
*,
|
||||
ensure_exists: bool = False,
|
||||
) -> Path:
|
||||
"""
|
||||
Resolve podcast media directory (workspace-only for multi-tenant isolation).
|
||||
|
||||
Requires user_id for tenant isolation. Falls back to default workspace
|
||||
only if no user_id provided (for backward compat in development).
|
||||
Logs a warning in production when user_id is missing.
|
||||
"""
|
||||
"""Resolve podcast media directory (tenant workspace first, legacy global fallback)."""
|
||||
media_subdir = {
|
||||
"audio": "podcast_audio",
|
||||
"image": "podcast_images",
|
||||
"video": "podcast_videos",
|
||||
"chart": "podcast_charts",
|
||||
}[media_type]
|
||||
|
||||
if user_id:
|
||||
resolved_dir = (get_user_workspace_dir(user_id) / "media" / media_subdir).resolve()
|
||||
tenant_media_dir = ROOT_DIR / "workspace" / f"workspace_{_sanitize_user_id(user_id)}" / "media" / media_subdir
|
||||
resolved_dir = tenant_media_dir.resolve()
|
||||
else:
|
||||
logger.warning(f"[Podcast] get_podcast_media_dir called without user_id for {media_type} — using default workspace. This should not happen in production.")
|
||||
resolved_dir = (get_workspace_root() / "workspace_alwrity" / "media" / media_subdir).resolve()
|
||||
resolved_dir = (DATA_MEDIA_DIR / media_subdir).resolve()
|
||||
|
||||
if ensure_exists:
|
||||
resolved_dir.mkdir(parents=True, exist_ok=True)
|
||||
@@ -55,11 +57,12 @@ def get_podcast_media_dir(
|
||||
|
||||
|
||||
def get_podcast_media_read_dirs(media_type: MediaType, user_id: str | None = None) -> list[Path]:
|
||||
"""
|
||||
Return directories to search for podcast media.
|
||||
Now workspace-only (no legacy fallback).
|
||||
"""
|
||||
return [get_podcast_media_dir(media_type, user_id)]
|
||||
"""Return ordered directories to search (tenant path first, then legacy global path)."""
|
||||
dirs: list[Path] = []
|
||||
if user_id:
|
||||
dirs.append(get_podcast_media_dir(media_type, user_id))
|
||||
dirs.append(get_podcast_media_dir(media_type, None))
|
||||
return dirs
|
||||
|
||||
|
||||
def get_podcast_audio_service(user_id: str | None = None) -> StoryAudioGenerationService:
|
||||
|
||||
@@ -1,216 +0,0 @@
|
||||
"""
|
||||
Podcast cost estimation helpers.
|
||||
|
||||
Builds user-facing podcast estimates from the subscription pricing catalog
|
||||
instead of hard-coded frontend heuristics.
|
||||
|
||||
Supports multiple models for each component:
|
||||
- Audio TTS: minimax/speech-02-hd (default), qwen3-tts, cosyvoice-tts
|
||||
- Voice Clone: qwen3, cosyvoice, minimax
|
||||
- Image: qwen-image (default), ideogram-v3-turbo
|
||||
- Video: wan-2.5 (default), kling-v2.5, infinitetalk
|
||||
- LLM: gemini-2.5-flash (default)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Dict, Optional
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from models.subscription_models import APIProvider
|
||||
from services.subscription.pricing_service import PricingService
|
||||
|
||||
|
||||
def _round_money(value: float) -> float:
|
||||
return round(float(value), 4)
|
||||
|
||||
|
||||
def _load_pricing(
|
||||
pricing_service: PricingService,
|
||||
provider: APIProvider,
|
||||
preferred_model: str,
|
||||
) -> Optional[Dict[str, Any]]:
|
||||
"""Load pricing for a provider and model, with fallback to default."""
|
||||
pricing = pricing_service.get_pricing_for_provider_model(provider, preferred_model)
|
||||
if pricing:
|
||||
return pricing
|
||||
# Fallback to provider default model row (if configured).
|
||||
return pricing_service.get_pricing_for_provider_model(provider, "default")
|
||||
|
||||
|
||||
# Default models used in podcast generation
|
||||
DEFAULT_MODELS = {
|
||||
"gemini": "gemini-2.5-flash",
|
||||
"exa": "exa-search",
|
||||
"audio_tts": "minimax/speech-02-hd",
|
||||
"voice_clone": "wavespeed-ai/qwen3-tts/voice-clone",
|
||||
"image": "qwen-image",
|
||||
"video": "wan-2.5",
|
||||
}
|
||||
|
||||
|
||||
def estimate_podcast_cost(
|
||||
*,
|
||||
db: Session,
|
||||
duration_minutes: int,
|
||||
speakers: int,
|
||||
query_count: int,
|
||||
include_avatar_phase: bool = True,
|
||||
# Optional model overrides
|
||||
gemini_model: str = "gemini-2.5-flash",
|
||||
audio_tts_model: str = "minimax/speech-02-hd",
|
||||
voice_clone_engine: str = "qwen3",
|
||||
image_model: str = "qwen-image",
|
||||
video_model: str = "wan-2.5",
|
||||
) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Compute a backend estimate for podcast creation.
|
||||
|
||||
Supports customizable models for each component.
|
||||
Uses pricing_catalog for accurate cost calculation.
|
||||
"""
|
||||
pricing_service = PricingService(db)
|
||||
|
||||
# Load pricing for each component and model
|
||||
gemini_pricing = _load_pricing(pricing_service, APIProvider.GEMINI, gemini_model)
|
||||
exa_pricing = _load_pricing(pricing_service, APIProvider.EXA, "exa-search")
|
||||
|
||||
# Audio TTS pricing (minimax/speech-02-hd)
|
||||
audio_pricing = _load_pricing(pricing_service, APIProvider.AUDIO, audio_tts_model)
|
||||
|
||||
# Voice clone pricing (different engines)
|
||||
voice_clone_model = f"wavespeed-ai/{voice_clone_engine}-tts/voice-clone"
|
||||
voice_clone_pricing = _load_pricing(pricing_service, APIProvider.AUDIO, voice_clone_model)
|
||||
if not voice_clone_pricing:
|
||||
# Try alternate model names
|
||||
voice_clone_pricing = _load_pricing(pricing_service, APIProvider.AUDIO, f"{voice_clone_engine}/voice-clone")
|
||||
|
||||
# Image pricing (qwen-image or ideogram)
|
||||
image_pricing = _load_pricing(pricing_service, APIProvider.STABILITY, image_model)
|
||||
|
||||
# Video pricing (wan-2.5, kling, or infinitetalk)
|
||||
video_pricing = _load_pricing(pricing_service, APIProvider.VIDEO, video_model)
|
||||
|
||||
# Return None if critical pricing unavailable (fail fast)
|
||||
if not gemini_pricing:
|
||||
return None
|
||||
|
||||
# Configuration
|
||||
minutes = max(1, int(duration_minutes or 1))
|
||||
speaker_count = max(1, int(speakers or 1))
|
||||
research_queries = max(1, int(query_count or 1))
|
||||
|
||||
# Token usage assumptions per phase
|
||||
analysis_input_tokens = 1800
|
||||
analysis_output_tokens = 1000
|
||||
research_synthesis_input_tokens = 2200
|
||||
research_synthesis_output_tokens = 900
|
||||
script_input_tokens = max(1800, minutes * 300)
|
||||
script_output_tokens = max(2200, minutes * 700)
|
||||
|
||||
# TTS: ~900 chars per minute per speaker
|
||||
estimated_tts_tokens = max(900, minutes * 900 * speaker_count)
|
||||
|
||||
# Voice clone: 1 clone operation per speaker
|
||||
voice_clone_count = speaker_count
|
||||
|
||||
# ===== COST CALCULATIONS =====
|
||||
|
||||
# 1. Analysis phase (LLM)
|
||||
analysis_cost = (
|
||||
analysis_input_tokens * float(gemini_pricing.get("cost_per_input_token") or 0.0)
|
||||
+ analysis_output_tokens * float(gemini_pricing.get("cost_per_output_token") or 0.0)
|
||||
)
|
||||
|
||||
# 2. Research phase
|
||||
# 2a. LLM for research synthesis
|
||||
research_llm_cost = (
|
||||
research_synthesis_input_tokens * float(gemini_pricing.get("cost_per_input_token") or 0.0)
|
||||
+ research_synthesis_output_tokens * float(gemini_pricing.get("cost_per_output_token") or 0.0)
|
||||
)
|
||||
# 2b. Search API (Exa)
|
||||
research_search_cost = 0.0
|
||||
if exa_pricing:
|
||||
research_search_cost = research_queries * float(exa_pricing.get("cost_per_request") or 0.0)
|
||||
research_cost = research_search_cost + research_llm_cost
|
||||
|
||||
# 3. Script generation (LLM)
|
||||
script_cost = (
|
||||
script_input_tokens * float(gemini_pricing.get("cost_per_input_token") or 0.0)
|
||||
+ script_output_tokens * float(gemini_pricing.get("cost_per_output_token") or 0.0)
|
||||
)
|
||||
|
||||
# 4. Audio TTS
|
||||
tts_cost = 0.0
|
||||
if audio_pricing:
|
||||
tts_cost = estimated_tts_tokens * float(audio_pricing.get("cost_per_input_token") or 0.0)
|
||||
|
||||
# 5. Voice cloning (if needed)
|
||||
voice_clone_cost = 0.0
|
||||
if voice_clone_pricing:
|
||||
voice_clone_cost = voice_clone_count * (
|
||||
float(voice_clone_pricing.get("cost_per_request") or 0.0)
|
||||
+ estimated_tts_tokens * float(voice_clone_pricing.get("cost_per_input_token") or 0.0)
|
||||
)
|
||||
|
||||
# 6. Avatar image generation
|
||||
avatar_cost = 0.0
|
||||
if include_avatar_phase and image_pricing:
|
||||
image_unit = float(image_pricing.get("cost_per_image") or image_pricing.get("cost_per_request") or 0.0)
|
||||
avatar_cost = speaker_count * image_unit
|
||||
|
||||
# 7. Video rendering
|
||||
video_cost = 0.0
|
||||
if video_pricing:
|
||||
# Assume 1 video render per minute (upper bound)
|
||||
video_cost = minutes * float(video_pricing.get("cost_per_request") or 0.0)
|
||||
|
||||
# ===== TOTALS =====
|
||||
llm_total = analysis_cost + research_llm_cost + script_cost
|
||||
audio_total = tts_cost + voice_clone_cost
|
||||
media_total = avatar_cost + video_cost
|
||||
total = llm_total + research_search_cost + audio_total + media_total
|
||||
|
||||
return {
|
||||
# Cost breakdown
|
||||
"analysisCost": _round_money(analysis_cost),
|
||||
"researchCost": _round_money(research_cost),
|
||||
"researchSearchCost": _round_money(research_search_cost),
|
||||
"researchLlmCost": _round_money(research_llm_cost),
|
||||
"scriptCost": _round_money(script_cost),
|
||||
"ttsCost": _round_money(tts_cost),
|
||||
"voiceCloneCost": _round_money(voice_clone_cost),
|
||||
"avatarCost": _round_money(avatar_cost),
|
||||
"videoCost": _round_money(video_cost),
|
||||
"total": _round_money(total),
|
||||
# Totals by category
|
||||
"llmCost": _round_money(llm_total),
|
||||
"audioCost": _round_money(audio_total),
|
||||
"mediaCost": _round_money(media_total),
|
||||
# Currency
|
||||
"currency": "USD",
|
||||
"source": "pricing_catalog",
|
||||
# Models used for this estimate
|
||||
"models": {
|
||||
"llm": gemini_model,
|
||||
"research": "exa-search",
|
||||
"audio_tts": audio_tts_model,
|
||||
"voice_clone": voice_clone_model,
|
||||
"image": image_model,
|
||||
"video": video_model,
|
||||
},
|
||||
# Assumptions used
|
||||
"assumptions": {
|
||||
"analysis_input_tokens": analysis_input_tokens,
|
||||
"analysis_output_tokens": analysis_output_tokens,
|
||||
"research_synthesis_input_tokens": research_synthesis_input_tokens,
|
||||
"research_synthesis_output_tokens": research_synthesis_output_tokens,
|
||||
"script_input_tokens": script_input_tokens,
|
||||
"script_output_tokens": script_output_tokens,
|
||||
"estimated_tts_tokens": estimated_tts_tokens,
|
||||
"research_queries": research_queries,
|
||||
"voice_clone_count": voice_clone_count,
|
||||
"video_requests": minutes,
|
||||
"avatar_requests": speaker_count if include_avatar_phase else 0,
|
||||
},
|
||||
}
|
||||
@@ -4,13 +4,11 @@ Podcast Analysis Handlers
|
||||
Analysis endpoint for podcast ideas.
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, Request
|
||||
from typing import Dict, Any, Optional, List
|
||||
from datetime import datetime
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from typing import Dict, Any
|
||||
import json
|
||||
import uuid
|
||||
from sqlalchemy.orm import Session
|
||||
from pydantic import BaseModel
|
||||
|
||||
from services.database import get_db
|
||||
from middleware.auth_middleware import get_current_user
|
||||
@@ -20,99 +18,17 @@ from services.llm_providers.main_image_generation import generate_image
|
||||
from services.podcast_bible_service import PodcastBibleService
|
||||
from utils.asset_tracker import save_asset_to_library
|
||||
from loguru import logger
|
||||
import os
|
||||
from ..constants import get_podcast_media_dir
|
||||
from ..prompts import get_enhance_topic_prompt, format_website_context
|
||||
from ..constants import PODCAST_IMAGES_DIR
|
||||
from ..models import (
|
||||
PodcastAnalyzeRequest,
|
||||
PodcastAnalyzeResponse,
|
||||
PodcastEnhanceIdeaRequest,
|
||||
PodcastEnhanceIdeaResponse,
|
||||
ExtractUrlRequest,
|
||||
ExtractUrlResponse,
|
||||
WebsiteAnalysisRequest,
|
||||
WebsiteAnalysisResponse,
|
||||
PodcastPreEstimateRequest,
|
||||
PodcastPreEstimateResponse,
|
||||
PodcastEnhanceIdeaResponse
|
||||
)
|
||||
from ..cost_estimator import estimate_podcast_cost
|
||||
|
||||
# Check if running in podcast-only demo mode
|
||||
def _is_podcast_only_mode() -> bool:
|
||||
"""Check if podcast-only demo mode is enabled."""
|
||||
return os.getenv("ALWRITY_ENABLED_FEATURES", "").strip().lower() == "podcast"
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post("/pre-estimate", response_model=PodcastPreEstimateResponse)
|
||||
async def pre_estimate_cost(
|
||||
request: PodcastPreEstimateRequest,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Lightweight endpoint to estimate podcast creation cost before analysis.
|
||||
|
||||
Takes user configuration (duration, speakers, query_count, podcast_mode) and returns
|
||||
a cost estimate WITHOUT running full analysis.
|
||||
|
||||
Optional model overrides can be specified to estimate with different models.
|
||||
"""
|
||||
try:
|
||||
include_avatar_phase = request.podcast_mode != "audio_only"
|
||||
|
||||
estimate = estimate_podcast_cost(
|
||||
db=db,
|
||||
duration_minutes=request.duration,
|
||||
speakers=request.speakers,
|
||||
query_count=request.query_count,
|
||||
include_avatar_phase=include_avatar_phase,
|
||||
# Model overrides if provided
|
||||
gemini_model=request.gemini_model or "gemini-2.5-flash",
|
||||
audio_tts_model=request.audio_tts_model or "minimax/speech-02-hd",
|
||||
voice_clone_engine=request.voice_clone_engine or "qwen3",
|
||||
image_model=request.image_model or "qwen-image",
|
||||
video_model=request.video_model or "wan-2.5",
|
||||
)
|
||||
|
||||
# Debug: get pricing row count and providers
|
||||
from models.subscription_models import APIProviderPricing
|
||||
pricing_count = db.query(APIProviderPricing).count()
|
||||
providers = db.query(APIProviderPricing.provider).distinct().all()
|
||||
provider_list = sorted([p[0].value for p in providers]) if providers else []
|
||||
|
||||
debug_info = {
|
||||
"pricing_rows": pricing_count,
|
||||
"providers": provider_list,
|
||||
}
|
||||
|
||||
# Log pricing debug info at warning level
|
||||
logger.warning(f"[PRE-ESTIMATE] Pricing debug: rows={pricing_count}, providers={provider_list}")
|
||||
logger.warning(f"[PRE-ESTIMATE] Models: llm={request.gemini_model}, tts={request.audio_tts_model}, video={request.video_model}")
|
||||
|
||||
if estimate is None:
|
||||
return PodcastPreEstimateResponse(
|
||||
estimate=None,
|
||||
error="Pricing data unavailable. Please try again later.",
|
||||
pricing_available=False,
|
||||
debug=debug_info,
|
||||
)
|
||||
|
||||
return PodcastPreEstimateResponse(
|
||||
estimate=estimate,
|
||||
error=None,
|
||||
pricing_available=True,
|
||||
debug=debug_info,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Pre-estimate error: {e}")
|
||||
return PodcastPreEstimateResponse(
|
||||
estimate=None,
|
||||
error=str(e),
|
||||
)
|
||||
|
||||
|
||||
@router.post("/idea/enhance", response_model=PodcastEnhanceIdeaResponse)
|
||||
async def enhance_podcast_idea(
|
||||
request: PodcastEnhanceIdeaRequest,
|
||||
@@ -125,62 +41,46 @@ async def enhance_podcast_idea(
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
# Serialize Bible context if provided or generate from onboarding
|
||||
# In podcast-only mode, skip bible generation since onboarding is disabled
|
||||
bible_context = ""
|
||||
if not _is_podcast_only_mode():
|
||||
logger.warning(f"[Podcast Enhance] Podcast mode=full — attempting Bible generation for user {user_id}")
|
||||
try:
|
||||
bible_service = PodcastBibleService()
|
||||
if request.bible:
|
||||
from models.podcast_bible_models import PodcastBible
|
||||
bible_data = PodcastBible(**request.bible)
|
||||
bible_context = bible_service.serialize_bible(bible_data)
|
||||
else:
|
||||
# Generate from onboarding data directly
|
||||
bible_obj = bible_service.generate_bible(user_id, "temp_enhance")
|
||||
bible_context = bible_service.serialize_bible(bible_obj)
|
||||
except Exception as exc:
|
||||
logger.warning(f"[Podcast Enhance] Failed to parse or generate bible context: {exc}")
|
||||
else:
|
||||
# In podcast mode, use the provided bible directly if available
|
||||
logger.warning(f"[Podcast Enhance] Podcast mode=podcast_only — skipping Bible generation for user {user_id}")
|
||||
try:
|
||||
bible_service = PodcastBibleService()
|
||||
if request.bible:
|
||||
try:
|
||||
from models.podcast_bible_models import PodcastBible
|
||||
bible_data = PodcastBible(**request.bible)
|
||||
bible_service = PodcastBibleService()
|
||||
bible_context = bible_service.serialize_bible(bible_data)
|
||||
except Exception as exc:
|
||||
logger.debug(f"[Podcast Enhance] Bible parsing skipped in podcast mode: {exc}")
|
||||
from models.podcast_bible_models import PodcastBible
|
||||
bible_data = PodcastBible(**request.bible)
|
||||
bible_context = bible_service.serialize_bible(bible_data)
|
||||
else:
|
||||
# Generate from onboarding data directly
|
||||
bible_obj = bible_service.generate_bible(user_id, "temp_enhance")
|
||||
bible_context = bible_service.serialize_bible(bible_obj)
|
||||
except Exception as exc:
|
||||
logger.warning(f"[Podcast Enhance] Failed to parse or generate bible context: {exc}")
|
||||
|
||||
# Log what's being used for context
|
||||
context_used = []
|
||||
if bible_context:
|
||||
context_used.append("Podcast Bible")
|
||||
if request.website_data:
|
||||
context_used.append("Website Extraction")
|
||||
if request.topic_context:
|
||||
category = request.topic_context.get("category", "unknown")
|
||||
context_used.append(f"Category Research ({category})")
|
||||
|
||||
logger.warning(f"[Podcast Enhance] Generating with context: {', '.join(context_used) if context_used else 'basic idea only'}")
|
||||
prompt = f"""
|
||||
You are a creative podcast producer. Generate 3 distinct, compelling podcast episode concepts from the raw idea.
|
||||
|
||||
# Use new context builder for prompt generation
|
||||
from services.podcast_context_builder import context_builder
|
||||
context_result = context_builder.build_enhance_context(
|
||||
idea=request.idea,
|
||||
bible_context=bible_context,
|
||||
website_data=request.website_data,
|
||||
topic_context=request.topic_context,
|
||||
)
|
||||
prompt = context_result["prompt"]
|
||||
{f"USER PERSONALIZATION CONTEXT (Podcast Bible):\n{bible_context}\n" if bible_context else ""}
|
||||
|
||||
RAW IDEA/KEYWORDS: "{request.idea}"
|
||||
|
||||
TASK:
|
||||
Generate 3 different enhanced versions, each with a unique angle:
|
||||
1. Professional & Expert-led angle (focus on authority, insights, and expertise)
|
||||
2. Storytelling & Human interest angle (focus on narratives, emotions, and personal connections)
|
||||
3. Trendy & Contemporary angle (focus on current trends, modern perspectives, and relevance)
|
||||
|
||||
Each version should be 2-3 sentences, audience-focused, and align with host persona if provided.
|
||||
|
||||
Return JSON with:
|
||||
- enhanced_ideas: array of 3 enhanced episode pitches (in order: Professional, Storytelling, Trendy)
|
||||
- rationales: array of 3 rationales explaining the approach for each version
|
||||
"""
|
||||
|
||||
try:
|
||||
raw = llm_text_gen(
|
||||
prompt=prompt,
|
||||
user_id=user_id,
|
||||
json_struct=None,
|
||||
preferred_provider=None,
|
||||
preferred_provider="huggingface",
|
||||
flow_type="premium_tool",
|
||||
)
|
||||
|
||||
@@ -194,19 +94,6 @@ async def enhance_podcast_idea(
|
||||
enhanced_ideas = data.get("enhanced_ideas", [])
|
||||
rationales = data.get("rationales", [])
|
||||
|
||||
# Handle case where LLM returns objects instead of strings
|
||||
normalized_ideas = []
|
||||
for idea in enhanced_ideas:
|
||||
if isinstance(idea, dict):
|
||||
# Extract title and description from object
|
||||
title = idea.get("title", "")
|
||||
description = idea.get("description", "") or idea.get("content", "")
|
||||
normalized_ideas.append(f"{title}: {description}" if description else title)
|
||||
elif isinstance(idea, str):
|
||||
normalized_ideas.append(idea)
|
||||
|
||||
enhanced_ideas = normalized_ideas
|
||||
|
||||
# Ensure we have exactly 3 ideas, fallback to original if needed
|
||||
if not isinstance(enhanced_ideas, list) or len(enhanced_ideas) != 3:
|
||||
# Fallback: create 3 variations of the original idea
|
||||
@@ -234,12 +121,22 @@ async def enhance_podcast_idea(
|
||||
enhanced_ideas=enhanced_ideas[:3], # Ensure exactly 3
|
||||
rationales=rationales[:3] # Ensure exactly 3
|
||||
)
|
||||
except HTTPException:
|
||||
# Re-raise HTTPExceptions (e.g., 429 subscription limit) - preserve error details
|
||||
raise
|
||||
except Exception as exc:
|
||||
logger.error(f"[Podcast Enhance] Failed for user {user_id}: {exc}")
|
||||
raise HTTPException(status_code=500, detail=f"Enhance failed: {exc}")
|
||||
# Fallback to basic variations of original idea
|
||||
base_idea = request.idea
|
||||
return PodcastEnhanceIdeaResponse(
|
||||
enhanced_ideas=[
|
||||
f"Expert insights on {base_idea}: A deep dive into industry trends and best practices.",
|
||||
f"The human side of {base_idea}: Personal stories and real-world experiences that resonate.",
|
||||
f"Modern perspectives on {base_idea}: Current trends and forward-thinking approaches."
|
||||
],
|
||||
rationales=[
|
||||
"Professional approach focusing on expertise and authority",
|
||||
"Storytelling approach emphasizing human connection",
|
||||
"Contemporary approach highlighting current relevance"
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
@router.post("/analyze", response_model=PodcastAnalyzeResponse)
|
||||
@@ -276,11 +173,7 @@ async def analyze_podcast_idea(
|
||||
final_avatar_url = request.avatar_url
|
||||
final_avatar_prompt = None
|
||||
|
||||
# Skip avatar generation for audio_only mode
|
||||
podcast_mode = getattr(request, 'podcast_mode', None) or 'video_only'
|
||||
should_generate_avatar = not final_avatar_url and podcast_mode != 'audio_only'
|
||||
|
||||
if should_generate_avatar:
|
||||
if not final_avatar_url:
|
||||
logger.info(f"[Podcast Analyze] No avatar_url provided, generating one for user {user_id}")
|
||||
try:
|
||||
# 1. PRE-FLIGHT VALIDATION: Check subscription limits for image generation
|
||||
@@ -304,17 +197,16 @@ async def analyze_podcast_idea(
|
||||
image_result = generate_image(
|
||||
prompt=final_avatar_prompt,
|
||||
user_id=user_id,
|
||||
options={"width": 1024, "height": 1024}
|
||||
width=1024,
|
||||
height=1024
|
||||
)
|
||||
|
||||
# 4. Save to disk and library
|
||||
if image_result and image_result.image_bytes:
|
||||
img_id = str(uuid.uuid4())[:8]
|
||||
filename = f"presenter_podcast_{user_id}_{img_id}.png"
|
||||
images_dir = get_podcast_media_dir("image", user_id, ensure_exists=True)
|
||||
avatars_dir = images_dir / "avatars"
|
||||
avatars_dir.mkdir(parents=True, exist_ok=True)
|
||||
output_path = avatars_dir / filename
|
||||
output_path = PODCAST_IMAGES_DIR / filename
|
||||
PODCAST_IMAGES_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
with open(output_path, "wb") as f:
|
||||
f.write(image_result.image_bytes)
|
||||
@@ -326,14 +218,13 @@ async def analyze_podcast_idea(
|
||||
db=db,
|
||||
user_id=user_id,
|
||||
asset_type="image",
|
||||
source_module="podcast_analysis",
|
||||
filename=filename,
|
||||
file_url=final_avatar_url,
|
||||
filename=filename,
|
||||
title=f"Presenter Avatar - {request.idea[:40]}",
|
||||
description=f"AI-generated podcast presenter for: {request.idea}",
|
||||
provider=image_result.provider,
|
||||
model=image_result.model,
|
||||
cost=0.0 # Cost tracked in generate_image
|
||||
cost=image_result.cost
|
||||
)
|
||||
logger.info(f"[Podcast Analyze] ✅ Generated and saved avatar to {final_avatar_url}")
|
||||
except Exception as e:
|
||||
@@ -378,10 +269,6 @@ Return JSON with:
|
||||
- top_keywords: 5 podcast-relevant keywords/phrases
|
||||
- suggested_outlines: 2 items, each with title (<=60 chars) and 4-6 short segments (bullet-friendly, factual)
|
||||
- title_suggestions: 3 concise episode titles
|
||||
- episode_hook: one compelling 15-30 second opening hook/angle that grabs attention
|
||||
- key_takeaways: 3-5 actionable insights listeners will learn
|
||||
- guest_talking_points: (if guest included) 3-4 suggested questions/angles for guest interview
|
||||
- listener_cta: one clear call-to-action for listeners
|
||||
- research_queries: array of {{"query": "string", "rationale": "string"}}
|
||||
- exa_suggested_config: suggested Exa search options with:
|
||||
- exa_search_type: "auto" | "neural" | "keyword"
|
||||
@@ -395,10 +282,7 @@ Return JSON with:
|
||||
Requirements:
|
||||
- Keep language factual, actionable, and suited for spoken audio.
|
||||
- Avoid narrative fiction tone.
|
||||
- For research queries: Mix of time-sensitive and evergreen queries:
|
||||
- 2-3 queries should focus on latest 2025-2026 developments, trends, and data (use year in query)
|
||||
- 2-3 queries should be evergreen/fundamental (concepts, definitions, best practices, proven strategies) - do NOT include years in these
|
||||
- Today's date is April 2026.
|
||||
- Prefer 2024-2025 context.
|
||||
"""
|
||||
|
||||
try:
|
||||
@@ -406,7 +290,7 @@ Requirements:
|
||||
prompt=prompt,
|
||||
user_id=user_id,
|
||||
json_struct=None,
|
||||
preferred_provider=None,
|
||||
preferred_provider="huggingface",
|
||||
flow_type="premium_tool",
|
||||
)
|
||||
except HTTPException:
|
||||
@@ -432,19 +316,8 @@ Requirements:
|
||||
top_keywords = data.get("top_keywords") or []
|
||||
suggested_outlines = data.get("suggested_outlines") or []
|
||||
title_suggestions = data.get("title_suggestions") or []
|
||||
episode_hook = data.get("episode_hook") or ""
|
||||
key_takeaways = data.get("key_takeaways") or []
|
||||
guest_talking_points = data.get("guest_talking_points") or []
|
||||
listener_cta = data.get("listener_cta") or ""
|
||||
research_queries = data.get("research_queries") or []
|
||||
exa_suggested_config = data.get("exa_suggested_config") or None
|
||||
estimate = estimate_podcast_cost(
|
||||
db=db,
|
||||
duration_minutes=request.duration,
|
||||
speakers=request.speakers,
|
||||
query_count=len(research_queries) if isinstance(research_queries, list) else 0,
|
||||
include_avatar_phase=podcast_mode != "audio_only",
|
||||
)
|
||||
|
||||
return PodcastAnalyzeResponse(
|
||||
audience=audience,
|
||||
@@ -452,430 +325,10 @@ Requirements:
|
||||
top_keywords=top_keywords,
|
||||
suggested_outlines=suggested_outlines,
|
||||
title_suggestions=title_suggestions,
|
||||
episode_hook=episode_hook,
|
||||
key_takeaways=key_takeaways,
|
||||
guest_talking_points=guest_talking_points,
|
||||
listener_cta=listener_cta,
|
||||
research_queries=research_queries,
|
||||
exa_suggested_config=exa_suggested_config,
|
||||
bible=bible_obj.model_dump() if bible_obj else None,
|
||||
avatar_url=final_avatar_url,
|
||||
avatar_prompt=final_avatar_prompt,
|
||||
estimate=estimate,
|
||||
)
|
||||
|
||||
|
||||
class RegenerateQueriesRequest(BaseModel):
|
||||
idea: str
|
||||
feedback: str
|
||||
existing_analysis: Optional[Dict[str, Any]] = None
|
||||
bible: Optional[Dict[str, Any]] = None
|
||||
|
||||
|
||||
class RegenerateQueriesResponse(BaseModel):
|
||||
research_queries: List[Dict[str, str]]
|
||||
|
||||
|
||||
@router.post("/regenerate-queries", response_model=RegenerateQueriesResponse)
|
||||
async def regenerate_research_queries(
|
||||
request: RegenerateQueriesRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Regenerate research queries based on user feedback and existing analysis.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
# Build context from existing analysis
|
||||
idea = request.idea
|
||||
feedback = request.feedback
|
||||
|
||||
# Get topic, keywords, audience from existing analysis if provided
|
||||
topic = idea
|
||||
keywords = ""
|
||||
audience = ""
|
||||
if request.existing_analysis:
|
||||
topic = request.existing_analysis.get("title_suggestions", [idea])[0] if request.existing_analysis.get("title_suggestions") else idea
|
||||
keywords = ", ".join(request.existing_analysis.get("top_keywords", [])[:5])
|
||||
audience = request.existing_analysis.get("audience", "")
|
||||
|
||||
# Serialize Bible context if provided
|
||||
bible_context = ""
|
||||
if request.bible:
|
||||
try:
|
||||
bible_service = PodcastBibleService()
|
||||
from models.podcast_bible_models import PodcastBible
|
||||
bible_data = PodcastBible(**request.bible)
|
||||
bible_context = bible_service.serialize_bible(bible_data)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to serialize bible for query regeneration: {e}")
|
||||
|
||||
prompt = f"""
|
||||
You are a research strategist for podcast content. Given a podcast idea, existing analysis, and user feedback,
|
||||
generate 7 new research queries that address the user's specific needs.
|
||||
|
||||
{f"USER FEEDBACK: {feedback}" if feedback else ""}
|
||||
|
||||
{f"EXISTING ANALYSIS CONTEXT:\n- Topic: {topic}\n- Keywords: {keywords}\n- Audience: {audience}\n" if request.existing_analysis else ""}
|
||||
{f"PODCAST BIBLE CONTEXT:\n{bible_context}\n" if bible_context else ""}
|
||||
|
||||
Podcast Idea: "{idea}"
|
||||
|
||||
TASK:
|
||||
Generate exactly 7 research queries that:
|
||||
1. Incorporate the user's feedback direction
|
||||
2. Build on the existing analysis context
|
||||
3. Mix of time-sensitive (2025-2026) and evergreen topics
|
||||
4. Are highly specific to the podcast topic
|
||||
|
||||
Return JSON with:
|
||||
- research_queries: array of {{"query": "string", "rationale": "string"}}
|
||||
|
||||
Requirements:
|
||||
- At least 2-3 queries should focus on latest 2025-2026 developments (include year in query)
|
||||
- At least 2-3 queries should be evergreen (concepts, definitions, best practices - NO year)
|
||||
- Queries should be specific and actionable, not generic
|
||||
"""
|
||||
|
||||
try:
|
||||
from services.llm_providers.main_text_generation import llm_text_gen
|
||||
|
||||
raw = llm_text_gen(
|
||||
prompt=prompt,
|
||||
user_id=user_id,
|
||||
json_struct={"research_queries": [{"query": "string", "rationale": "string"}]},
|
||||
preferred_provider=None,
|
||||
flow_type="premium_tool",
|
||||
)
|
||||
|
||||
# Parse response
|
||||
if isinstance(raw, dict):
|
||||
queries = raw.get("research_queries", [])
|
||||
else:
|
||||
# Try to parse as JSON
|
||||
try:
|
||||
parsed = json.loads(raw) if isinstance(raw, str) else raw
|
||||
queries = parsed.get("research_queries", []) if isinstance(parsed, dict) else []
|
||||
except:
|
||||
queries = []
|
||||
|
||||
return RegenerateQueriesResponse(research_queries=queries[:7])
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as exc:
|
||||
logger.error(f"[Regenerate Queries] Failed for user {user_id}: {exc}")
|
||||
raise HTTPException(status_code=500, detail=f"Regenerate queries failed: {exc}")
|
||||
|
||||
|
||||
@router.post("/extract-url", response_model=ExtractUrlResponse)
|
||||
async def extract_url_content(
|
||||
request: ExtractUrlRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Extract content from a URL using Exa's get_contents API.
|
||||
|
||||
This allows users to paste a blog post or article URL as their podcast topic,
|
||||
and we'll extract the content to use as the podcast idea.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
from exa_py import Exa
|
||||
import os
|
||||
|
||||
api_key = os.getenv("EXA_API_KEY")
|
||||
if not api_key:
|
||||
raise HTTPException(status_code=500, detail="EXA_API_KEY not configured")
|
||||
|
||||
exa = Exa(api_key)
|
||||
|
||||
logger.warning(f"[ExtractUrl] Extracting content from: {request.url} for user {user_id}")
|
||||
|
||||
try:
|
||||
result = exa.get_contents(
|
||||
urls=[request.url],
|
||||
text=True,
|
||||
highlights=True,
|
||||
summary=True,
|
||||
subpages=2,
|
||||
)
|
||||
except Exception as exa_error:
|
||||
logger.error(f"[ExtractUrl] Exa call error: {exa_error}")
|
||||
return ExtractUrlResponse(
|
||||
success=False,
|
||||
url=request.url,
|
||||
error=f"Exa API error: {str(exa_error)}"
|
||||
)
|
||||
|
||||
# Check for errors using the correct attribute (statuses is array of status objects)
|
||||
if hasattr(result, 'statuses') and result.statuses:
|
||||
for status in result.statuses:
|
||||
if status.status == "error":
|
||||
logger.error(f"[ExtractUrl] Failed to extract {status.id}: {status.error.tag if hasattr(status.error, 'tag') else 'unknown'}")
|
||||
return ExtractUrlResponse(
|
||||
success=False,
|
||||
url=request.url,
|
||||
error=f"Failed to extract content: {status.error.tag if hasattr(status.error, 'tag') else 'unknown error'}"
|
||||
)
|
||||
|
||||
if not result.results:
|
||||
return ExtractUrlResponse(
|
||||
success=False,
|
||||
url=request.url,
|
||||
error="No content found at the provided URL"
|
||||
)
|
||||
|
||||
# Extract content - safe to access result now
|
||||
content = result.results[0]
|
||||
|
||||
# Extract all available fields from Exa response
|
||||
extracted_text = content.text or ""
|
||||
extracted_summary = getattr(content, 'summary', "") or ""
|
||||
extracted_title = content.title or ""
|
||||
|
||||
# Highlights - extract from content.highlights array if available
|
||||
highlights = []
|
||||
if hasattr(content, 'highlights') and content.highlights:
|
||||
highlights = [h for h in content.highlights if h]
|
||||
|
||||
# Additional fields from Exa response
|
||||
image = getattr(content, 'image', None)
|
||||
favicon = getattr(content, 'favicon', None)
|
||||
|
||||
# Subpages - extract with their own content
|
||||
subpages = []
|
||||
if hasattr(content, 'subpages') and content.subpages:
|
||||
for sp in content.subpages:
|
||||
subpages.append({
|
||||
'id': sp.get('id', ''),
|
||||
'title': sp.get('title', ''),
|
||||
'url': sp.get('url', ''),
|
||||
'summary': sp.get('summary', ''),
|
||||
'text': sp.get('text', '')[:500] if sp.get('text') else '', # First 500 chars
|
||||
})
|
||||
|
||||
logger.warning(f"[ExtractUrl] Successfully extracted {len(extracted_text)} chars from {request.url}")
|
||||
logger.warning(f"[ExtractUrl] title={extracted_title[:50]}, summary={extracted_summary[:50]}, highlights={len(highlights)}, subpages={len(subpages)}")
|
||||
|
||||
return ExtractUrlResponse(
|
||||
success=True,
|
||||
title=extracted_title,
|
||||
text=extracted_text,
|
||||
summary=extracted_summary,
|
||||
author=getattr(content, 'author', None),
|
||||
highlights=highlights,
|
||||
url=request.url,
|
||||
image=image,
|
||||
favicon=favicon,
|
||||
subpages=subpages,
|
||||
)
|
||||
|
||||
|
||||
@router.post("/website-analysis", response_model=WebsiteAnalysisResponse)
|
||||
async def save_website_analysis(
|
||||
request: WebsiteAnalysisRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Save the user's website analysis for reuse in future podcasts."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
from services.user_data_service import user_data_service
|
||||
|
||||
website_data = {
|
||||
"website_url": request.website_url,
|
||||
"extracted_at": datetime.now().isoformat(),
|
||||
"exa_content": request.exa_content,
|
||||
"full_analysis": None,
|
||||
"analysis_status": "pending",
|
||||
}
|
||||
|
||||
success = user_data_service.save_user_data(
|
||||
user_id=user_id,
|
||||
data_key="website_analysis",
|
||||
data_value=website_data,
|
||||
)
|
||||
|
||||
if success:
|
||||
logger.warning(f"[WebsiteAnalysis] Saved analysis for user {user_id}: {request.website_url}")
|
||||
return WebsiteAnalysisResponse(
|
||||
success=True,
|
||||
website_url=request.website_url,
|
||||
message="Website analysis saved successfully",
|
||||
)
|
||||
else:
|
||||
return WebsiteAnalysisResponse(
|
||||
success=False,
|
||||
error="Failed to save website analysis",
|
||||
)
|
||||
|
||||
except Exception as exc:
|
||||
logger.error(f"[WebsiteAnalysis] Failed to save for user {user_id}: {exc}")
|
||||
return WebsiteAnalysisResponse(
|
||||
success=False,
|
||||
error=f"Failed to save: {str(exc)}"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/website-extraction")
|
||||
async def get_saved_website_extraction(request: Request = None):
|
||||
"""Get previously saved website extraction data for this user."""
|
||||
try:
|
||||
# Safely get current_user from Depends
|
||||
if request is None or not hasattr(request, 'state'):
|
||||
logger.warning("[WebsiteExtraction] No request or state - user not authenticated")
|
||||
return {"success": False, "data": None, "error": "Not authenticated"}
|
||||
|
||||
current_user = getattr(request.state, 'user', None)
|
||||
if not current_user:
|
||||
logger.warning("[WebsiteExtraction] No user in request state")
|
||||
return {"success": False, "data": None, "error": "Not authenticated"}
|
||||
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
from services.user_data_service import UserDataService
|
||||
from services.database import get_db
|
||||
db = next(get_db())
|
||||
|
||||
user_service = UserDataService(db)
|
||||
extraction = user_service.get_website_extraction(user_id)
|
||||
|
||||
if extraction:
|
||||
logger.info(f"[WebsiteExtraction] Found saved data for user {user_id}")
|
||||
return {
|
||||
"success": True,
|
||||
"data": extraction
|
||||
}
|
||||
else:
|
||||
logger.info(f"[WebsiteExtraction] No saved data for user {user_id}")
|
||||
return {
|
||||
"success": False,
|
||||
"data": None
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
logger.error(f"[WebsiteExtraction] Failed for user: {exc}", exc_info=True)
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(exc)
|
||||
}
|
||||
|
||||
|
||||
@router.post("/website-extraction")
|
||||
async def save_website_extraction(
|
||||
extraction: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Save website extraction data for future use."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
from services.user_data_service import UserDataService
|
||||
from services.database import get_db
|
||||
db = next(get_db())
|
||||
|
||||
user_service = UserDataService(db)
|
||||
success = user_service.save_website_extraction(user_id, extraction)
|
||||
|
||||
if success:
|
||||
logger.info(f"[WebsiteExtraction] Saved for user {user_id}")
|
||||
return {
|
||||
"success": True,
|
||||
"message": "Website extraction saved"
|
||||
}
|
||||
else:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Failed to save"
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
logger.error(f"[WebsiteExtraction] Save failed: {exc}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(exc)
|
||||
}
|
||||
|
||||
|
||||
@router.post("/project/{project_id}/topic-context")
|
||||
async def save_topic_context(
|
||||
project_id: str,
|
||||
topic_context: Dict[str, Any],
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Save topic context (category research) to a podcast project."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
from services.database import get_db
|
||||
from models.podcast_models import PodcastProject
|
||||
|
||||
db = next(get_db())
|
||||
|
||||
# Find the project
|
||||
project = db.query(PodcastProject).filter(
|
||||
PodcastProject.project_id == project_id,
|
||||
PodcastProject.user_id == user_id
|
||||
).first()
|
||||
|
||||
if not project:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Project not found"
|
||||
}
|
||||
|
||||
# Update topic context
|
||||
project.topic_context = topic_context
|
||||
db.commit()
|
||||
|
||||
logger.info(f"[TopicContext] Saved for project {project_id}")
|
||||
return {
|
||||
"success": True,
|
||||
"message": "Topic context saved"
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
logger.error(f"[TopicContext] Save failed: {exc}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(exc)
|
||||
}
|
||||
|
||||
|
||||
@router.get("/project/{project_id}/topic-context")
|
||||
async def get_topic_context(
|
||||
project_id: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Get topic context from a podcast project."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
from services.database import get_db
|
||||
from models.podcast_models import PodcastProject
|
||||
|
||||
db = next(get_db())
|
||||
|
||||
project = db.query(PodcastProject).filter(
|
||||
PodcastProject.project_id == project_id,
|
||||
PodcastProject.user_id == user_id
|
||||
).first()
|
||||
|
||||
if not project:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Project not found"
|
||||
}
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"data": project.topic_context
|
||||
}
|
||||
|
||||
except Exception as exc:
|
||||
logger.error(f"[TopicContext] Get failed: {exc}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(exc)
|
||||
}
|
||||
|
||||
@@ -12,15 +12,7 @@ from pathlib import Path
|
||||
from urllib.parse import urlparse
|
||||
import tempfile
|
||||
import uuid
|
||||
import hashlib
|
||||
import time
|
||||
import shutil
|
||||
import requests
|
||||
import asyncio
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
import asyncio
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
from services.database import get_db
|
||||
from middleware.auth_middleware import get_current_user, get_current_user_with_query_token
|
||||
@@ -39,124 +31,6 @@ from ..models import (
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# Thread pool for CPU/IO-intensive voice clone operations
|
||||
_audio_executor = ThreadPoolExecutor(max_workers=2, thread_name_prefix="podcast_audio")
|
||||
|
||||
# In-memory LRU cache for voice samples (per user) to avoid re-downloading
|
||||
_voice_sample_cache: dict[str, tuple[float, bytes]] = {}
|
||||
_VOICE_SAMPLE_CACHE_TTL = 1800 # 30 minutes
|
||||
|
||||
|
||||
def _get_cached_voice_sample(cache_key: str) -> Optional[bytes]:
|
||||
"""Get voice sample bytes from in-memory cache if fresh."""
|
||||
if cache_key in _voice_sample_cache:
|
||||
ts, data = _voice_sample_cache[cache_key]
|
||||
if time.time() - ts < _VOICE_SAMPLE_CACHE_TTL:
|
||||
logger.debug(f"[Podcast] Voice sample cache hit for {cache_key[:16]}...")
|
||||
return data
|
||||
del _voice_sample_cache[cache_key]
|
||||
return None
|
||||
|
||||
|
||||
def _cache_voice_sample(cache_key: str, data: bytes) -> None:
|
||||
"""Store voice sample bytes in in-memory cache."""
|
||||
# Evict oldest entries if cache grows too large
|
||||
if len(_voice_sample_cache) > 50:
|
||||
oldest_key = min(_voice_sample_cache, key=lambda k: _voice_sample_cache[k][0])
|
||||
del _voice_sample_cache[oldest_key]
|
||||
_voice_sample_cache[cache_key] = (time.time(), data)
|
||||
|
||||
|
||||
def _get_latest_voice_sample_url(user_id: str, db) -> Optional[str]:
|
||||
"""Get the latest voice sample URL for a user from their voice clone assets."""
|
||||
try:
|
||||
from models.content_asset_models import ContentAsset, AssetType, AssetSource
|
||||
from sqlalchemy import desc
|
||||
|
||||
asset = db.query(ContentAsset).filter(
|
||||
ContentAsset.user_id == user_id,
|
||||
ContentAsset.asset_type == AssetType.AUDIO,
|
||||
ContentAsset.source_module == AssetSource.VOICE_CLONER,
|
||||
).order_by(desc(ContentAsset.created_at)).first()
|
||||
|
||||
if asset and asset.file_url:
|
||||
logger.info(f"[Podcast] Found voice sample for user {user_id}: {asset.file_url}")
|
||||
return asset.file_url
|
||||
|
||||
logger.warning(f"[Podcast] No voice sample asset found for user {user_id}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"[Podcast] Error fetching voice sample URL: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def _fetch_voice_sample(voice_sample_url: str, user_id: str) -> Optional[bytes]:
|
||||
"""Fetch voice sample audio bytes from URL, with caching."""
|
||||
cache_key = hashlib.md5(f"{user_id}:{voice_sample_url}".encode()).hexdigest()
|
||||
|
||||
# Check in-memory cache first
|
||||
cached = _get_cached_voice_sample(cache_key)
|
||||
if cached is not None:
|
||||
return cached
|
||||
|
||||
try:
|
||||
from utils.media_utils import resolve_media_path
|
||||
|
||||
# Try resolving as a local workspace path first (fastest)
|
||||
if "/api/assets/" in voice_sample_url:
|
||||
# Resolve user workspace path directly
|
||||
sanitized_uid = "".join(c for c in user_id if c.isalnum() or c in ("-", "_"))
|
||||
from api.podcast.constants import ROOT_DIR
|
||||
parts = voice_sample_url.split("/")
|
||||
# Expected: /api/assets/{user_id}/voice_samples/{filename}
|
||||
try:
|
||||
idx = parts.index("voice_samples")
|
||||
filename = parts[idx + 1].split("?")[0]
|
||||
local_path = ROOT_DIR / "workspace" / f"workspace_{sanitized_uid}" / "assets" / "voice_samples" / filename
|
||||
if local_path.exists():
|
||||
data = local_path.read_bytes()
|
||||
_cache_voice_sample(cache_key, data)
|
||||
logger.info(f"[Podcast] Voice sample loaded from workspace: {local_path}")
|
||||
return data
|
||||
except (ValueError, IndexError):
|
||||
pass
|
||||
|
||||
# Fall back to media utils resolver
|
||||
local_path = resolve_media_path(voice_sample_url)
|
||||
if local_path and local_path.exists():
|
||||
data = local_path.read_bytes()
|
||||
_cache_voice_sample(cache_key, data)
|
||||
return data
|
||||
|
||||
# Try resolving as a podcast audio file
|
||||
if "/api/podcast/audio/" in voice_sample_url:
|
||||
filename = voice_sample_url.split("/api/podcast/audio/")[-1].split("?")[0]
|
||||
try:
|
||||
audio_dir = get_podcast_media_dir("audio", user_id)
|
||||
local_path = audio_dir / filename
|
||||
if local_path.exists():
|
||||
data = local_path.read_bytes()
|
||||
_cache_voice_sample(cache_key, data)
|
||||
return data
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Try direct HTTP fetch as fallback
|
||||
if voice_sample_url.startswith("http"):
|
||||
logger.info(f"[Podcast] Fetching voice sample via HTTP: {voice_sample_url[:80]}...")
|
||||
resp = requests.get(voice_sample_url, timeout=30)
|
||||
if resp.status_code == 200:
|
||||
data = resp.content
|
||||
_cache_voice_sample(cache_key, data)
|
||||
logger.info(f"[Podcast] Voice sample fetched via HTTP ({len(data)} bytes)")
|
||||
return data
|
||||
|
||||
logger.warning(f"[Podcast] Could not fetch voice sample from: {voice_sample_url}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"[Podcast] Error fetching voice sample: {e}")
|
||||
return None
|
||||
|
||||
|
||||
@router.post("/audio/upload")
|
||||
async def upload_podcast_audio(
|
||||
@@ -251,190 +125,32 @@ async def generate_podcast_audio(
|
||||
raise HTTPException(status_code=400, detail="Text is required")
|
||||
|
||||
try:
|
||||
# Determine if we should use voice clone path
|
||||
# Voice clone is used when: explicitly requested, OR when voice_id/custom_voice_id indicates a clone
|
||||
# (cloned voice IDs start with "vc_" or match the placeholder "MY_VOICE_CLONE")
|
||||
_vid = request.voice_id or ""
|
||||
_cvid = request.custom_voice_id or ""
|
||||
is_voice_clone = request.use_voice_clone or (
|
||||
_cvid.startswith("vc_") or _cvid == "MY_VOICE_CLONE"
|
||||
) or (
|
||||
_vid.startswith("vc_") or _vid == "MY_VOICE_CLONE"
|
||||
audio_service = get_podcast_audio_service(user_id)
|
||||
result: StoryAudioResult = audio_service.generate_ai_audio(
|
||||
scene_number=0,
|
||||
scene_title=request.scene_title,
|
||||
text=request.text.strip(),
|
||||
user_id=user_id,
|
||||
voice_id=request.voice_id or "Wise_Woman",
|
||||
speed=request.speed or 1.0, # Normal speed (was 0.9, but too slow - causing duration issues)
|
||||
volume=request.volume or 1.0,
|
||||
pitch=request.pitch or 0.0, # Normal pitch (0.0 = neutral)
|
||||
emotion=request.emotion or "neutral",
|
||||
english_normalization=request.english_normalization or False,
|
||||
sample_rate=request.sample_rate,
|
||||
bitrate=request.bitrate,
|
||||
channel=request.channel,
|
||||
format=request.format,
|
||||
language_boost=request.language_boost,
|
||||
enable_sync_mode=request.enable_sync_mode,
|
||||
)
|
||||
|
||||
# If voice_id is a clone ID, normalize it to use Wise_Woman for TTS fallback
|
||||
effective_voice_id = _vid if not (_vid.startswith("vc_") or _vid == "MY_VOICE_CLONE") else "Wise_Woman"
|
||||
|
||||
logger.warning(f"[Podcast] Audio request: use_voice_clone={request.use_voice_clone}, voice_id={request.voice_id}, custom_voice_id={request.custom_voice_id}, is_voice_clone={is_voice_clone}, voice_sample_url={request.voice_sample_url}, voice_clone_engine={request.voice_clone_engine}")
|
||||
|
||||
# Voice clone path: use user's voice sample with scene text as reference
|
||||
if is_voice_clone:
|
||||
# If no voice_sample_url provided, try to fetch it from the user's latest voice clone
|
||||
voice_sample_url = request.voice_sample_url
|
||||
if not voice_sample_url:
|
||||
try:
|
||||
voice_sample_url = _get_latest_voice_sample_url(user_id, db)
|
||||
logger.warning(f"[Podcast] DB fallback voice sample URL for user {user_id}: {voice_sample_url}")
|
||||
except Exception as e:
|
||||
logger.warning(f"[Podcast] Could not fetch voice sample URL: {e}")
|
||||
|
||||
if voice_sample_url:
|
||||
from services.llm_providers.main_audio_generation import qwen3_voice_clone, cosyvoice_voice_clone
|
||||
from utils.media_utils import detect_audio_format
|
||||
|
||||
engine = (request.voice_clone_engine or "qwen3").lower()
|
||||
logger.warning(f"[Podcast] 🔊 Voice clone path: engine={engine}, scene='{request.scene_title}', voice_sample_url={voice_sample_url[:80]}...")
|
||||
|
||||
# Download voice sample from URL (with caching)
|
||||
logger.warning(f"[Podcast] Fetching voice sample from: {voice_sample_url}")
|
||||
try:
|
||||
voice_sample_bytes = _fetch_voice_sample(voice_sample_url, user_id)
|
||||
except Exception as fetch_err:
|
||||
logger.error(f"[Podcast] ❌ Failed to fetch voice sample: {fetch_err}", exc_info=True)
|
||||
raise HTTPException(status_code=400, detail=f"Could not fetch voice sample: {str(fetch_err)}")
|
||||
logger.warning(f"[Podcast] Voice sample fetch result: {len(voice_sample_bytes) if voice_sample_bytes else 0} bytes")
|
||||
if not voice_sample_bytes:
|
||||
raise HTTPException(status_code=400, detail=f"Could not fetch voice sample from {voice_sample_url}")
|
||||
|
||||
# Detect actual audio format from bytes (may differ from file extension)
|
||||
detected_fmt, detected_mime = detect_audio_format(voice_sample_bytes)
|
||||
logger.warning(f"[Podcast] 🔊 Detected voice sample format: {detected_fmt} ({detected_mime}), {len(voice_sample_bytes)} bytes")
|
||||
voice_mime_type = detected_mime or "audio/wav"
|
||||
|
||||
scene_text = request.text.strip()
|
||||
if len(scene_text) > 4000:
|
||||
scene_text = scene_text[:4000]
|
||||
|
||||
# Run voice clone in thread pool to avoid blocking the event loop
|
||||
loop = asyncio.get_event_loop()
|
||||
|
||||
try:
|
||||
if engine == "minimax":
|
||||
from services.llm_providers.main_audio_generation import clone_voice
|
||||
import random
|
||||
import string
|
||||
random_suffix = ''.join(random.choices(string.ascii_letters + string.digits, k=8))
|
||||
custom_vid = request.custom_voice_id or f"vc_{random_suffix}"
|
||||
|
||||
result_obj = await loop.run_in_executor(
|
||||
_audio_executor,
|
||||
lambda cv=custom_vid: clone_voice(
|
||||
audio_bytes=voice_sample_bytes,
|
||||
custom_voice_id=cv,
|
||||
text=scene_text,
|
||||
user_id=user_id,
|
||||
),
|
||||
)
|
||||
audio_bytes = result_obj.preview_audio_bytes
|
||||
provider = "minimax"
|
||||
model = "minimax/voice-clone"
|
||||
elif engine == "cosyvoice":
|
||||
result_obj = await loop.run_in_executor(
|
||||
_audio_executor,
|
||||
lambda: cosyvoice_voice_clone(
|
||||
audio_bytes=voice_sample_bytes,
|
||||
text=scene_text,
|
||||
user_id=user_id,
|
||||
audio_mime_type=voice_mime_type,
|
||||
),
|
||||
)
|
||||
audio_bytes = result_obj.preview_audio_bytes
|
||||
provider = "wavespeed-ai"
|
||||
model = "wavespeed-ai/cosyvoice-tts/voice-clone"
|
||||
else:
|
||||
result_obj = await loop.run_in_executor(
|
||||
_audio_executor,
|
||||
lambda: qwen3_voice_clone(
|
||||
audio_bytes=voice_sample_bytes,
|
||||
text=scene_text,
|
||||
user_id=user_id,
|
||||
audio_mime_type=voice_mime_type,
|
||||
),
|
||||
)
|
||||
audio_bytes = result_obj.preview_audio_bytes
|
||||
provider = "wavespeed-ai"
|
||||
model = "wavespeed-ai/qwen3-tts/voice-clone"
|
||||
|
||||
logger.warning(f"[Podcast] 🔊 Voice clone result: {len(audio_bytes) if audio_bytes else 0} bytes, provider={provider}")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as clone_err:
|
||||
logger.error(f"[Podcast] ❌ Voice clone failed: {clone_err}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Voice clone generation failed: {str(clone_err)}")
|
||||
|
||||
# Save audio bytes to file
|
||||
audio_service = get_podcast_audio_service(user_id)
|
||||
audio_filename = f"scene_{request.scene_id}_{uuid.uuid4().hex[:8]}.mp3"
|
||||
audio_path = audio_service.output_dir / audio_filename
|
||||
|
||||
with open(audio_path, "wb") as f:
|
||||
f.write(audio_bytes)
|
||||
|
||||
file_size = len(audio_bytes)
|
||||
audio_url = f"/api/podcast/audio/{audio_filename}"
|
||||
cost = max(0.005, 0.005 * (len(scene_text) / 100.0))
|
||||
|
||||
result = {
|
||||
"audio_path": str(audio_path),
|
||||
"audio_filename": audio_filename,
|
||||
"audio_url": audio_url,
|
||||
"file_size": file_size,
|
||||
"provider": provider,
|
||||
"model": model,
|
||||
"cost": cost,
|
||||
"scene_number": 0,
|
||||
"scene_title": request.scene_title,
|
||||
}
|
||||
|
||||
else:
|
||||
# Standard TTS path - but NOT if custom_voice_id is a clone ID
|
||||
# Clone IDs (vc_*, MY_VOICE_CLONE) are not valid for minimax TTS
|
||||
if is_voice_clone:
|
||||
logger.warning(f"[Podcast] ⚠️ Voice clone detected but no voice sample available - falling back to standard TTS with voice_id={effective_voice_id}")
|
||||
effective_custom_voice_id = request.custom_voice_id
|
||||
if effective_custom_voice_id and (
|
||||
effective_custom_voice_id.startswith("vc_") or
|
||||
effective_custom_voice_id == "MY_VOICE_CLONE"
|
||||
):
|
||||
logger.warning(f"[Podcast] Ignoring clone ID '{effective_custom_voice_id}' in standard TTS path - no voice sample URL available")
|
||||
effective_custom_voice_id = None
|
||||
|
||||
audio_service = get_podcast_audio_service(user_id)
|
||||
logger.warning(f"[Podcast] Standard TTS path: voice_id={effective_voice_id}, custom_voice_id={effective_custom_voice_id}")
|
||||
result: StoryAudioResult = audio_service.generate_ai_audio(
|
||||
scene_number=0,
|
||||
scene_title=request.scene_title,
|
||||
text=request.text.strip(),
|
||||
user_id=user_id,
|
||||
voice_id=effective_voice_id,
|
||||
custom_voice_id=effective_custom_voice_id,
|
||||
speed=request.speed or 1.0, # Normal speed (was 0.9, but too slow - causing duration issues)
|
||||
volume=request.volume or 1.0,
|
||||
pitch=request.pitch or 0.0, # Normal pitch (0.0 = neutral)
|
||||
emotion=request.emotion or "neutral",
|
||||
english_normalization=request.english_normalization or False,
|
||||
sample_rate=request.sample_rate,
|
||||
bitrate=request.bitrate,
|
||||
channel=request.channel,
|
||||
format=request.format,
|
||||
language_boost=request.language_boost,
|
||||
enable_sync_mode=request.enable_sync_mode,
|
||||
)
|
||||
|
||||
# Override URL to use podcast endpoint instead of story endpoint
|
||||
if result.get("audio_url") and "/api/story/audio/" in result.get("audio_url", ""):
|
||||
audio_filename = result.get("audio_filename", "")
|
||||
result["audio_url"] = f"/api/podcast/audio/{audio_filename}"
|
||||
|
||||
logger.warning(f"[Podcast] Audio generated - path: {result.get('audio_path')}, url: {result.get('audio_url')}")
|
||||
except HTTPException:
|
||||
raise
|
||||
# Override URL to use podcast endpoint instead of story endpoint
|
||||
if result.get("audio_url") and "/api/story/audio/" in result.get("audio_url", ""):
|
||||
audio_filename = result.get("audio_filename", "")
|
||||
result["audio_url"] = f"/api/podcast/audio/{audio_filename}"
|
||||
except Exception as exc:
|
||||
exc_type = type(exc).__name__
|
||||
exc_msg = str(exc)[:500]
|
||||
logger.error(f"[Podcast] Audio generation failed ({exc_type}): {exc_msg}")
|
||||
logger.error(f"[Podcast] Audio generation traceback:", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Audio generation failed ({exc_type}): {exc_msg}")
|
||||
raise HTTPException(status_code=500, detail=f"Audio generation failed: {exc}")
|
||||
|
||||
# Save to asset library (podcast module)
|
||||
try:
|
||||
@@ -671,12 +387,7 @@ async def serve_podcast_audio(
|
||||
raise HTTPException(status_code=400, detail="Invalid filename")
|
||||
|
||||
user_id = require_authenticated_user(current_user)
|
||||
logger.info(f"[Podcast] serve_podcast_audio: filename={filename}, user_id={user_id}")
|
||||
|
||||
audio_path = _resolve_podcast_media_file(filename, "audio", user_id)
|
||||
logger.info(f"[Podcast] Audio resolved path: {audio_path}, exists={audio_path.exists()}")
|
||||
audio_path = _resolve_podcast_media_file(filename, "audio", user_id)
|
||||
logger.debug(f"[Podcast] Resolved audio path: {audio_path}")
|
||||
|
||||
return FileResponse(audio_path, media_type="audio/mpeg")
|
||||
|
||||
|
||||
@@ -12,39 +12,22 @@ from pathlib import Path
|
||||
import uuid
|
||||
import hashlib
|
||||
|
||||
from services.database import get_db, get_session_for_user
|
||||
from services.database import get_db
|
||||
from middleware.auth_middleware import get_current_user, get_current_user_with_query_token
|
||||
from api.story_writer.utils.auth import require_authenticated_user
|
||||
from services.llm_providers.main_image_generation import generate_image
|
||||
from services.llm_providers.main_image_editing import edit_image
|
||||
from utils.asset_tracker import save_asset_to_library
|
||||
from loguru import logger
|
||||
from ..constants import get_podcast_media_dir, PODCAST_AVATARS_SUBDIR
|
||||
from ..constants import PODCAST_IMAGES_DIR
|
||||
from ..presenter_personas import choose_persona_id, get_persona
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
# Avatar subdirectory
|
||||
AVATAR_SUBDIR = PODCAST_AVATARS_SUBDIR
|
||||
|
||||
|
||||
async def _get_db_or_none(current_user: Dict[str, Any]):
|
||||
"""Try to get a database session, returning None on failure (non-fatal for uploads)."""
|
||||
try:
|
||||
user_id = current_user.get('id') or current_user.get('clerk_user_id')
|
||||
if not user_id:
|
||||
return None
|
||||
return get_session_for_user(user_id)
|
||||
except Exception as e:
|
||||
logger.warning(f"[Podcast] DB session unavailable (non-fatal): {e}")
|
||||
return None
|
||||
|
||||
|
||||
def _get_podcast_avatars_dir(user_id: str) -> Path:
|
||||
"""Get podcast avatars directory for a user (workspace-aware)."""
|
||||
avatars_dir = get_podcast_media_dir("image", user_id, ensure_exists=True) / AVATAR_SUBDIR
|
||||
avatars_dir.mkdir(parents=True, exist_ok=True)
|
||||
return avatars_dir
|
||||
AVATAR_SUBDIR = "avatars"
|
||||
PODCAST_AVATARS_DIR = PODCAST_IMAGES_DIR / AVATAR_SUBDIR
|
||||
PODCAST_AVATARS_DIR.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
|
||||
@router.post("/avatar/upload")
|
||||
@@ -58,16 +41,8 @@ async def upload_podcast_avatar(
|
||||
Upload a presenter avatar image for a podcast project.
|
||||
Returns the avatar URL for use in scene image generation.
|
||||
"""
|
||||
try:
|
||||
user_id = require_authenticated_user(current_user)
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"[Podcast] Avatar upload auth failed: {e}", exc_info=True)
|
||||
raise HTTPException(status_code=401, detail="Authentication failed")
|
||||
|
||||
logger.info(f"[Podcast] Avatar upload request - user_id={user_id}, project_id={project_id}, content_type={file.content_type}")
|
||||
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
# Validate file type
|
||||
if not file.content_type or not file.content_type.startswith('image/'):
|
||||
raise HTTPException(status_code=400, detail="File must be an image")
|
||||
@@ -82,21 +57,19 @@ async def upload_podcast_avatar(
|
||||
file_ext = Path(file.filename).suffix or '.png'
|
||||
unique_id = str(uuid.uuid4())[:8]
|
||||
avatar_filename = f"avatar_{project_id or 'temp'}_{unique_id}{file_ext}"
|
||||
avatars_dir = _get_podcast_avatars_dir(user_id)
|
||||
logger.info(f"[Podcast] Saving avatar to: {avatars_dir / avatar_filename}")
|
||||
avatar_path = avatars_dir / avatar_filename
|
||||
avatar_path = PODCAST_AVATARS_DIR / avatar_filename
|
||||
|
||||
# Save file
|
||||
with open(avatar_path, "wb") as f:
|
||||
f.write(file_content)
|
||||
|
||||
logger.info(f"[Podcast] Avatar uploaded successfully: {avatar_path}")
|
||||
logger.info(f"[Podcast] Avatar uploaded: {avatar_path}")
|
||||
|
||||
# Create avatar URL
|
||||
avatar_url = f"/api/podcast/images/{AVATAR_SUBDIR}/{avatar_filename}"
|
||||
|
||||
# Save to asset library if project_id provided and DB session available
|
||||
if project_id and db:
|
||||
# Save to asset library if project_id provided
|
||||
if project_id:
|
||||
try:
|
||||
save_asset_to_library(
|
||||
db=db,
|
||||
@@ -118,17 +91,13 @@ async def upload_podcast_avatar(
|
||||
},
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(f"[Podcast] Failed to save avatar asset (non-fatal): {e}")
|
||||
elif project_id and not db:
|
||||
logger.warning(f"[Podcast] DB session unavailable, skipping asset library save for avatar")
|
||||
logger.warning(f"[Podcast] Failed to save avatar asset: {e}")
|
||||
|
||||
return {
|
||||
"avatar_url": avatar_url,
|
||||
"avatar_filename": avatar_filename,
|
||||
"message": "Avatar uploaded successfully"
|
||||
}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as exc:
|
||||
logger.error(f"[Podcast] Avatar upload failed: {exc}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Avatar upload failed: {str(exc)}")
|
||||
@@ -145,18 +114,12 @@ async def make_avatar_presentable(
|
||||
Transform an uploaded avatar image into a podcast-appropriate presenter.
|
||||
Uses AI image editing to convert the uploaded photo into a professional podcast presenter.
|
||||
"""
|
||||
# CRITICAL: Log at the very start before any logic
|
||||
logger.info(f"[Podcast] ===== MAKE PRESENTABLE ENDPOINT START =====")
|
||||
|
||||
user_id = require_authenticated_user(current_user)
|
||||
logger.info(f"[Podcast] Make presentable request received - user_id={user_id}, avatar_url={avatar_url}, project_id={project_id}")
|
||||
|
||||
try:
|
||||
# Load the uploaded avatar image
|
||||
from ..utils import load_podcast_image_bytes
|
||||
logger.info(f"[Podcast] Loading avatar image from {avatar_url}")
|
||||
avatar_bytes = load_podcast_image_bytes(avatar_url, user_id=user_id)
|
||||
logger.info(f"[Podcast] Avatar loaded successfully - size={len(avatar_bytes)} bytes")
|
||||
avatar_bytes = load_podcast_image_bytes(avatar_url)
|
||||
|
||||
logger.info(f"[Podcast] Transforming avatar to podcast presenter for project {project_id}")
|
||||
|
||||
@@ -178,24 +141,17 @@ async def make_avatar_presentable(
|
||||
"model": None, # Use default model
|
||||
}
|
||||
|
||||
logger.info(f"[Podcast] Calling edit_image with user_id={user_id}")
|
||||
try:
|
||||
result = edit_image(
|
||||
input_image_bytes=avatar_bytes,
|
||||
prompt=transformation_prompt,
|
||||
options=image_options,
|
||||
user_id=user_id
|
||||
)
|
||||
logger.info(f"[Podcast] edit_image completed successfully - provider={result.provider}, model={result.model}")
|
||||
except Exception as edit_err:
|
||||
logger.error(f"[Podcast] edit_image failed: {edit_err}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Image editing failed: {str(edit_err)}")
|
||||
result = edit_image(
|
||||
input_image_bytes=avatar_bytes,
|
||||
prompt=transformation_prompt,
|
||||
options=image_options,
|
||||
user_id=user_id
|
||||
)
|
||||
|
||||
# Save transformed avatar
|
||||
unique_id = str(uuid.uuid4())[:8]
|
||||
transformed_filename = f"presenter_transformed_{project_id or 'temp'}_{unique_id}.png"
|
||||
avatars_dir = _get_podcast_avatars_dir(user_id)
|
||||
transformed_path = avatars_dir / transformed_filename
|
||||
transformed_path = PODCAST_AVATARS_DIR / transformed_filename
|
||||
|
||||
with open(transformed_path, "wb") as f:
|
||||
f.write(result.image_bytes)
|
||||
@@ -238,16 +194,6 @@ async def make_avatar_presentable(
|
||||
"avatar_filename": transformed_filename,
|
||||
"message": "Avatar transformed into podcast presenter successfully"
|
||||
}
|
||||
except HTTPException:
|
||||
# Re-raise HTTP exceptions as-is
|
||||
raise
|
||||
except RuntimeError as rt_err:
|
||||
# Handle missing API keys or configuration errors
|
||||
logger.error(f"[Podcast] Avatar transformation configuration error: {rt_err}")
|
||||
raise HTTPException(
|
||||
status_code=503, # Service Unavailable
|
||||
detail=f"Image editing service not configured: {str(rt_err)}. Please contact support."
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.error(f"[Podcast] Avatar transformation failed: {exc}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Avatar transformation failed: {str(exc)}")
|
||||
@@ -377,8 +323,7 @@ async def generate_podcast_presenters(
|
||||
# Save avatar
|
||||
unique_id = str(uuid.uuid4())[:8]
|
||||
avatar_filename = f"presenter_{project_id or 'temp'}_{i+1}_{unique_id}.png"
|
||||
avatars_dir = _get_podcast_avatars_dir(user_id)
|
||||
avatar_path = avatars_dir / avatar_filename
|
||||
avatar_path = PODCAST_AVATARS_DIR / avatar_filename
|
||||
|
||||
with open(avatar_path, "wb") as f:
|
||||
f.write(result.image_bytes)
|
||||
|
||||
@@ -1,398 +0,0 @@
|
||||
"""
|
||||
B-Roll Handlers
|
||||
|
||||
API endpoints for B-roll chart preview and video generation.
|
||||
"""
|
||||
|
||||
from pathlib import Path
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
|
||||
from fastapi.responses import FileResponse
|
||||
from typing import Dict, Any, Optional, List
|
||||
from pydantic import BaseModel, Field
|
||||
from pathlib import Path
|
||||
import uuid
|
||||
|
||||
from middleware.auth_middleware import get_current_user, get_current_user_with_query_token
|
||||
from api.story_writer.utils.auth import require_authenticated_user
|
||||
from api.story_writer.task_manager import task_manager
|
||||
from api.podcast.utils import _resolve_podcast_media_file
|
||||
from services.podcast.broll_service import get_broll_service
|
||||
from utils.media_utils import resolve_media_path
|
||||
from loguru import logger
|
||||
|
||||
|
||||
router = APIRouter(prefix="/broll", tags=["B-Roll"])
|
||||
|
||||
|
||||
def _resolve_broll_background_image_path(background_image_url: str) -> str:
|
||||
"""Resolve background image URL/path to a local file path."""
|
||||
resolved = resolve_media_path(background_image_url)
|
||||
if not resolved:
|
||||
raise HTTPException(status_code=404, detail=f"Background image not found: {background_image_url}")
|
||||
return str(resolved)
|
||||
|
||||
|
||||
def _resolve_broll_avatar_video_path(avatar_video_url: Optional[str], user_id: str) -> Optional[str]:
|
||||
"""Resolve optional avatar video URL/path to a local file path."""
|
||||
if not avatar_video_url:
|
||||
return None
|
||||
|
||||
parsed = urlparse(avatar_video_url)
|
||||
path = parsed.path if parsed.scheme else avatar_video_url
|
||||
|
||||
if "/api/podcast/videos/" in path:
|
||||
filename = path.split("/api/podcast/videos/", 1)[1].split("?", 1)[0].strip()
|
||||
if not filename:
|
||||
raise HTTPException(status_code=400, detail="Invalid avatar video URL")
|
||||
return str(_resolve_podcast_media_file(filename, "video", user_id))
|
||||
|
||||
local_path = Path(path).expanduser().resolve()
|
||||
if local_path.exists() and local_path.is_file():
|
||||
return str(local_path)
|
||||
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=(
|
||||
"Unsupported avatar video URL format. "
|
||||
"Use /api/podcast/videos/{filename} or a valid local file path."
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _execute_broll_scene_task(
|
||||
task_id: str,
|
||||
*,
|
||||
scene_id: str,
|
||||
key_insight: str,
|
||||
supporting_stat: str,
|
||||
chart_data: Optional[Dict[str, Any]],
|
||||
visual_cue: str,
|
||||
duration: float,
|
||||
background_img_path: str,
|
||||
avatar_video_path: Optional[str],
|
||||
):
|
||||
"""Background task for rendering a B-roll scene."""
|
||||
try:
|
||||
task_manager.update_task_status(
|
||||
task_id,
|
||||
"processing",
|
||||
progress=10.0,
|
||||
message="Starting B-roll scene render...",
|
||||
)
|
||||
|
||||
broll_service = get_broll_service()
|
||||
task_manager.update_task_status(
|
||||
task_id,
|
||||
"processing",
|
||||
progress=35.0,
|
||||
message="Composing scene layers and overlays...",
|
||||
)
|
||||
|
||||
video_path = broll_service.generate_scene_broll(
|
||||
scene_id=scene_id,
|
||||
key_insight=key_insight,
|
||||
supporting_stat=supporting_stat,
|
||||
chart_data=chart_data,
|
||||
visual_cue=visual_cue,
|
||||
duration=duration,
|
||||
background_img_path=background_img_path,
|
||||
avatar_video_path=avatar_video_path,
|
||||
)
|
||||
|
||||
filename = Path(video_path).name
|
||||
video_url = f"/api/podcast/broll/final/{filename}"
|
||||
|
||||
task_manager.update_task_status(
|
||||
task_id,
|
||||
"completed",
|
||||
progress=100.0,
|
||||
message="B-roll scene render completed.",
|
||||
result={
|
||||
"scene_id": scene_id,
|
||||
"broll_video_path": video_path,
|
||||
"broll_video_url": video_url,
|
||||
},
|
||||
)
|
||||
except Exception as exc:
|
||||
logger.error(f"[Broll] Task {task_id} failed: {exc}")
|
||||
task_manager.update_task_status(
|
||||
task_id,
|
||||
"failed",
|
||||
error=f"B-roll scene render failed: {str(exc)}",
|
||||
error_status=500,
|
||||
)
|
||||
|
||||
|
||||
class ChartPreviewRequest(BaseModel):
|
||||
"""Request model for chart preview generation."""
|
||||
chart_data: Dict[str, Any] = Field(..., description="Chart data (labels, before/after, etc.)")
|
||||
chart_type: str = Field(
|
||||
default="bar_comparison",
|
||||
description="bar_comparison | bar_horizontal | line_trend | pie | stacked_bar | bullet"
|
||||
)
|
||||
title: str = Field(default="", description="Chart title")
|
||||
subtitle: Optional[str] = Field(default="", description="Optional subtitle at bottom")
|
||||
|
||||
|
||||
class ChartPreviewResponse(BaseModel):
|
||||
"""Response for chart preview."""
|
||||
preview_url: str
|
||||
chart_id: str
|
||||
|
||||
|
||||
class BrollSceneRequest(BaseModel):
|
||||
"""Request for generating B-roll video for a scene."""
|
||||
scene_id: str
|
||||
key_insight: str
|
||||
supporting_stat: str
|
||||
chart_data: Optional[Dict[str, Any]] = None
|
||||
visual_cue: str = Field(default="bar_comparison", description="bar_comparison | bar_horizontal | line_trend | pie | stacked_bar | bullet_points | full_avatar")
|
||||
duration: float = Field(default=10.0, ge=3.0, le=60.0)
|
||||
background_image_url: str
|
||||
avatar_video_url: Optional[str] = None
|
||||
|
||||
|
||||
class BrollSceneResponse(BaseModel):
|
||||
"""Response for B-roll scene generation."""
|
||||
scene_id: str
|
||||
broll_video_url: str = ""
|
||||
broll_video_path: str = ""
|
||||
task_id: Optional[str] = None
|
||||
status: str = "completed"
|
||||
message: Optional[str] = None
|
||||
|
||||
|
||||
class BrollComposeRequest(BaseModel):
|
||||
"""Request for composing multiple B-roll videos."""
|
||||
scene_video_paths: List[str]
|
||||
output_filename: str = "final_broll.mp4"
|
||||
fade_dur: float = Field(default=0.5, ge=0.0, le=2.0)
|
||||
fps: int = Field(default=24, ge=12, le=60)
|
||||
|
||||
|
||||
class BrollComposeResponse(BaseModel):
|
||||
"""Response for B-roll composition."""
|
||||
final_video_url: str
|
||||
final_video_path: str
|
||||
|
||||
|
||||
@router.post("/preview/chart", response_model=ChartPreviewResponse)
|
||||
async def generate_chart_preview(
|
||||
request: ChartPreviewRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Generate a chart PNG preview (static image for Write phase).
|
||||
|
||||
This endpoint is called from the Write phase to show users chart previews
|
||||
before they commit to B-roll video generation.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
# Debug logging
|
||||
logger.warning(f"[Broll] Chart preview request: type={request.chart_type}, title={request.title}, chart_data keys={list(request.chart_data.keys())}, user_id={user_id}")
|
||||
|
||||
try:
|
||||
broll_service = get_broll_service(user_id=user_id)
|
||||
chart_id = uuid.uuid4().hex[:8]
|
||||
|
||||
preview_path = broll_service.generate_chart_preview(
|
||||
chart_data=request.chart_data,
|
||||
chart_type=request.chart_type,
|
||||
title=request.title,
|
||||
subtitle=request.subtitle or "",
|
||||
chart_id=chart_id,
|
||||
)
|
||||
|
||||
# If chart generation failed (empty path), return a placeholder instead of 500
|
||||
if not preview_path:
|
||||
# Return a fallback response so frontend doesn't crash
|
||||
logger.warning(f"[Broll] Chart preview skipped - invalid data for type: {request.chart_type}")
|
||||
return ChartPreviewResponse(
|
||||
preview_url="",
|
||||
chart_id=chart_id,
|
||||
)
|
||||
|
||||
preview_filename = Path(preview_path).name
|
||||
preview_url = f"/api/podcast/broll/preview/{chart_id}/{preview_filename}"
|
||||
|
||||
logger.warning(f"[Broll] Chart preview generated: chart_id={chart_id}, path={preview_path}, url={preview_url}")
|
||||
|
||||
return ChartPreviewResponse(
|
||||
preview_url=preview_url,
|
||||
chart_id=chart_id,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Broll] Chart preview generation failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Chart preview failed: {str(e)}")
|
||||
|
||||
|
||||
@router.post("/render/broll-scene", response_model=BrollSceneResponse)
|
||||
async def generate_broll_scene(
|
||||
request: BrollSceneRequest,
|
||||
background_tasks: BackgroundTasks,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Generate a B-roll video for a single scene.
|
||||
|
||||
This creates a programmatic video with:
|
||||
- Background image with Ken Burns effect
|
||||
- Chart overlay (if chart_data provided)
|
||||
- Avatar circle in corner (if avatar_video_url provided)
|
||||
- Insight card at bottom
|
||||
|
||||
Returns a task_id for polling since video generation can take time.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
# Validate visual_cue
|
||||
valid_cues = ["bar_comparison", "bar_chart_comparison", "bar_horizontal", "line_trend", "pie", "stacked_bar", "bullet_points", "full_avatar"]
|
||||
if request.visual_cue not in valid_cues:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid visual_cue. Must be one of: {valid_cues}"
|
||||
)
|
||||
|
||||
background_img_path = _resolve_broll_background_image_path(request.background_image_url)
|
||||
avatar_video_path = _resolve_broll_avatar_video_path(request.avatar_video_url, user_id)
|
||||
|
||||
logger.info(f"[Broll] B-roll scene request for scene: {request.scene_id}")
|
||||
|
||||
# Scene rendering can be expensive, so use task manager/background execution.
|
||||
task_id = task_manager.create_task(
|
||||
"podcast_broll_scene_generation",
|
||||
metadata={"owner_user_id": user_id, "scene_id": request.scene_id},
|
||||
)
|
||||
|
||||
background_tasks.add_task(
|
||||
_execute_broll_scene_task,
|
||||
task_id=task_id,
|
||||
scene_id=request.scene_id,
|
||||
key_insight=request.key_insight,
|
||||
supporting_stat=request.supporting_stat,
|
||||
chart_data=request.chart_data,
|
||||
visual_cue=request.visual_cue,
|
||||
duration=request.duration,
|
||||
background_img_path=background_img_path,
|
||||
avatar_video_path=avatar_video_path,
|
||||
)
|
||||
|
||||
return BrollSceneResponse(
|
||||
scene_id=request.scene_id,
|
||||
task_id=task_id,
|
||||
status="pending",
|
||||
message="B-roll scene render started. Poll /api/podcast/task/{task_id}/status for progress.",
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"[Broll] B-roll scene generation failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"B-roll generation failed: {str(e)}")
|
||||
|
||||
|
||||
@router.post("/render/broll-compose", response_model=BrollComposeResponse)
|
||||
async def compose_broll_videos(
|
||||
request: BrollComposeRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Compose multiple B-roll scene videos into a final video.
|
||||
|
||||
Applies crossfade transitions between scenes.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
broll_service = get_broll_service()
|
||||
|
||||
final_path = broll_service.compose_final_video(
|
||||
video_paths=request.scene_video_paths,
|
||||
output_filename=request.output_filename,
|
||||
fade_dur=request.fade_dur,
|
||||
fps=request.fps,
|
||||
)
|
||||
|
||||
final_filename = final_path.split('/')[-1]
|
||||
final_url = f"/api/podcast/broll/final/{final_filename}"
|
||||
|
||||
return BrollComposeResponse(
|
||||
final_video_url=final_url,
|
||||
final_video_path=final_path,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Broll] Video composition failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Video composition failed: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/preview/{chart_id}/{filename}")
|
||||
async def serve_chart_preview(
|
||||
chart_id: str,
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user_with_query_token),
|
||||
):
|
||||
"""
|
||||
Serve chart preview PNG files.
|
||||
|
||||
Uses authentication via Authorization header or token query parameter,
|
||||
matching the pattern used by /api/podcast/images/ for browser <img> tags.
|
||||
"""
|
||||
from api.podcast.constants import get_podcast_media_dir
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
# Validate filename to prevent directory traversal
|
||||
if ".." in filename or "/" in filename or "\\" in filename:
|
||||
raise HTTPException(status_code=400, detail="Invalid filename")
|
||||
|
||||
logger.warning(f"[Broll] serve_chart_preview: chart_id={chart_id}, filename={filename}, user_id={user_id}")
|
||||
|
||||
charts_dir = get_podcast_media_dir("chart", user_id)
|
||||
file_path = charts_dir / filename
|
||||
|
||||
logger.warning(f"[Broll] serve_chart_preview: resolved path={file_path}, exists={file_path.exists()}")
|
||||
|
||||
if not file_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Chart preview not found")
|
||||
|
||||
# Security: ensure resolved path is within charts_dir
|
||||
if not str(file_path.resolve()).startswith(str(charts_dir.resolve())):
|
||||
raise HTTPException(status_code=403, detail="Access denied")
|
||||
|
||||
return FileResponse(
|
||||
path=str(file_path),
|
||||
media_type="image/png",
|
||||
filename=filename,
|
||||
)
|
||||
|
||||
|
||||
@router.get("/final/{filename}")
|
||||
async def serve_final_broll(
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""Serve final composed B-roll video files."""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
broll_service = get_broll_service()
|
||||
file_path = broll_service.output_dir / filename
|
||||
|
||||
if not file_path.exists():
|
||||
raise HTTPException(status_code=404, detail="Video not found")
|
||||
|
||||
return FileResponse(
|
||||
path=str(file_path),
|
||||
media_type="video/mp4",
|
||||
filename=filename,
|
||||
)
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
async def broll_health():
|
||||
"""Health check for B-roll service."""
|
||||
return {"status": "ok", "service": "broll"}
|
||||
@@ -1,522 +0,0 @@
|
||||
"""
|
||||
Podcast Dubbing Handlers
|
||||
|
||||
Audio dubbing endpoints for translating podcast audio to different languages.
|
||||
Supports both low-quality (DeepL) and high-quality (WaveSpeed) dubbing with voice cloning.
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
|
||||
from fastapi.responses import FileResponse
|
||||
from sqlalchemy.orm import Session
|
||||
from typing import Dict, Any, Optional
|
||||
from pathlib import Path
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
from services.database import get_db
|
||||
from middleware.auth_middleware import get_current_user
|
||||
from api.story_writer.utils.auth import require_authenticated_user
|
||||
from api.story_writer.task_manager import task_manager
|
||||
from loguru import logger
|
||||
|
||||
from ..models import (
|
||||
PodcastAudioDubRequest,
|
||||
PodcastAudioDubResponse,
|
||||
PodcastAudioDubResult,
|
||||
PodcastAudioDubEstimateRequest,
|
||||
PodcastAudioDubEstimateResponse,
|
||||
VoiceCloneRequest,
|
||||
VoiceCloneResponse,
|
||||
VoiceCloneResult,
|
||||
)
|
||||
from services.dubbing import AudioDubbingService
|
||||
from ..constants import get_podcast_media_read_dirs, get_podcast_media_dir
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
_dubbing_executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="podcast_dubbing")
|
||||
|
||||
_DUBBED_AUDIO_SUBDIR = Path("dubbed_audio")
|
||||
_LEGACY_DUBBED_AUDIO_DIR = Path(__file__).resolve().parents[3] / "data" / "media" / "dubbed_audio"
|
||||
|
||||
|
||||
def _get_dubbed_audio_dir(user_id: str, *, ensure_exists: bool = False) -> Path:
|
||||
"""Resolve tenant-scoped dubbed audio directory under podcast audio media."""
|
||||
base_dir = get_podcast_media_dir("audio", user_id, ensure_exists=ensure_exists)
|
||||
dubbed_dir = (base_dir / _DUBBED_AUDIO_SUBDIR).resolve()
|
||||
if ensure_exists:
|
||||
dubbed_dir.mkdir(parents=True, exist_ok=True)
|
||||
return dubbed_dir
|
||||
|
||||
|
||||
def _resolve_dubbed_audio_file(filename: str, user_id: str) -> Path:
|
||||
"""Resolve dubbed audio with traversal-safe checks (tenant first, then legacy fallback)."""
|
||||
clean_filename = filename.split("?", 1)[0].strip()
|
||||
if not clean_filename:
|
||||
raise HTTPException(status_code=400, detail="Invalid filename")
|
||||
|
||||
candidate_dirs: list[Path] = []
|
||||
for base_dir in get_podcast_media_read_dirs("audio", user_id):
|
||||
candidate_dirs.append((base_dir / _DUBBED_AUDIO_SUBDIR).resolve())
|
||||
candidate_dirs.append(_LEGACY_DUBBED_AUDIO_DIR.resolve())
|
||||
|
||||
for target_dir in candidate_dirs:
|
||||
candidate = (target_dir / clean_filename).resolve()
|
||||
if not str(candidate).startswith(str(target_dir)):
|
||||
logger.error(f"[Podcast][Dubbing] Attempted path traversal: {filename}")
|
||||
raise HTTPException(status_code=403, detail="Invalid audio path")
|
||||
if candidate.exists():
|
||||
return candidate
|
||||
|
||||
raise HTTPException(status_code=404, detail="Audio file not found")
|
||||
|
||||
|
||||
def _execute_dubbing_task(
|
||||
task_id: str,
|
||||
source_audio_url: str,
|
||||
source_language: Optional[str],
|
||||
target_language: str,
|
||||
quality: str,
|
||||
voice_id: str,
|
||||
speed: float,
|
||||
emotion: str,
|
||||
use_voice_clone: bool,
|
||||
custom_voice_id: Optional[str],
|
||||
voice_clone_accuracy: float,
|
||||
user_id: str,
|
||||
):
|
||||
"""Background task to dub audio."""
|
||||
try:
|
||||
task_manager.update_task_status(
|
||||
task_id, "processing", progress=5.0,
|
||||
message="Starting audio dubbing..."
|
||||
)
|
||||
|
||||
dubbed_audio_dir = _get_dubbed_audio_dir(user_id, ensure_exists=True)
|
||||
service = AudioDubbingService(output_dir=dubbed_audio_dir)
|
||||
|
||||
def progress_callback(progress: float, message: str):
|
||||
task_manager.update_task_status(
|
||||
task_id, "processing", progress=progress,
|
||||
message=message
|
||||
)
|
||||
|
||||
logger.info(f"[Dubbing] Task {task_id}: Starting dubbing with voice_clone={use_voice_clone}")
|
||||
|
||||
result = service.dub_audio(
|
||||
source_audio=source_audio_url,
|
||||
target_language=target_language,
|
||||
source_language=source_language,
|
||||
voice_id=voice_id,
|
||||
speed=speed,
|
||||
emotion=emotion,
|
||||
quality=quality,
|
||||
use_voice_clone=use_voice_clone,
|
||||
custom_voice_id=custom_voice_id,
|
||||
accuracy=voice_clone_accuracy,
|
||||
user_id=user_id,
|
||||
progress_callback=progress_callback,
|
||||
)
|
||||
|
||||
task_manager.update_task_status(
|
||||
task_id, "completed", progress=100.0,
|
||||
result={
|
||||
"dubbed_audio_url": result.dubbed_audio_url,
|
||||
"dubbed_audio_filename": Path(result.dubbed_audio_path).name,
|
||||
"original_transcript": result.original_transcript,
|
||||
"translated_transcript": result.translated_transcript,
|
||||
"source_language": result.source_language,
|
||||
"target_language": result.target_language,
|
||||
"voice_id": result.voice_id,
|
||||
"quality": result.quality,
|
||||
"duration_seconds": result.duration_seconds,
|
||||
"file_size": result.file_size,
|
||||
"cost": result.cost,
|
||||
"status": "completed",
|
||||
"voice_clone_used": result.voice_clone_used,
|
||||
"cloned_voice_id": result.cloned_voice_id,
|
||||
},
|
||||
message="Audio dubbing completed!"
|
||||
)
|
||||
|
||||
logger.info(f"[Dubbing] Task {task_id} completed successfully (voice_clone_used={result.voice_clone_used})")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Dubbing] Task {task_id} failed: {str(e)}")
|
||||
task_manager.update_task_status(
|
||||
task_id, "failed",
|
||||
error=str(e),
|
||||
message=f"Dubbing failed: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
def _execute_voice_clone_task(
|
||||
task_id: str,
|
||||
source_audio_url: str,
|
||||
custom_voice_id: Optional[str],
|
||||
accuracy: float,
|
||||
language_boost: Optional[str],
|
||||
user_id: str,
|
||||
):
|
||||
"""Background task to clone voice from audio."""
|
||||
try:
|
||||
task_manager.update_task_status(
|
||||
task_id, "processing", progress=10.0,
|
||||
message="Starting voice cloning..."
|
||||
)
|
||||
|
||||
dubbed_audio_dir = _get_dubbed_audio_dir(user_id, ensure_exists=True)
|
||||
service = AudioDubbingService(output_dir=dubbed_audio_dir)
|
||||
|
||||
task_manager.update_task_status(
|
||||
task_id, "processing", progress=30.0,
|
||||
message="Processing audio..."
|
||||
)
|
||||
|
||||
voice_info = service.clone_voice_from_audio(
|
||||
source_audio=source_audio_url,
|
||||
custom_voice_id=custom_voice_id,
|
||||
accuracy=accuracy,
|
||||
language_boost=language_boost,
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
task_manager.update_task_status(
|
||||
task_id, "completed", progress=100.0,
|
||||
result={
|
||||
"voice_id": voice_info.voice_id,
|
||||
"voice_url": voice_info.voice_url,
|
||||
"source_language": voice_info.source_language,
|
||||
"accuracy": voice_info.accuracy,
|
||||
"file_size": voice_info.file_size,
|
||||
"status": "completed",
|
||||
},
|
||||
message="Voice cloning completed!"
|
||||
)
|
||||
|
||||
logger.info(f"[VoiceClone] Task {task_id} completed: {voice_info.voice_id}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[VoiceClone] Task {task_id} failed: {str(e)}")
|
||||
task_manager.update_task_status(
|
||||
task_id, "failed",
|
||||
error=str(e),
|
||||
message=f"Voice cloning failed: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
@router.post("/dub/audio", response_model=PodcastAudioDubResponse)
|
||||
async def create_audio_dubbing_task(
|
||||
request: PodcastAudioDubRequest,
|
||||
background_tasks: BackgroundTasks,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Create an audio dubbing task.
|
||||
|
||||
Translates podcast audio to a target language using STT → Translate → TTS pipeline.
|
||||
|
||||
For high-quality dubbing with voice preservation, set use_voice_clone=True.
|
||||
|
||||
- **source_audio_url**: URL or path to source audio file
|
||||
- **target_language**: Target language code (e.g., 'es', 'Spanish')
|
||||
- **source_language**: Source language (auto-detected if not provided)
|
||||
- **quality**: 'low' (DeepL, cheaper) or 'high' (WaveSpeed, better quality)
|
||||
- **voice_id**: Voice ID for TTS (default: 'Wise_Woman')
|
||||
- **speed**: Speech speed 0.5-2.0 (default: 1.0)
|
||||
- **use_voice_clone**: Use voice cloning to preserve original speaker's voice
|
||||
- **custom_voice_id**: Custom name for the cloned voice
|
||||
- **voice_clone_accuracy**: Voice cloning accuracy 0.1-1.0 (default: 0.7)
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
task_id = task_manager.create_task(
|
||||
"audio_dubbing",
|
||||
metadata={"owner_user_id": user_id},
|
||||
)
|
||||
|
||||
background_tasks.add_task(
|
||||
_execute_dubbing_task,
|
||||
task_id=task_id,
|
||||
source_audio_url=request.source_audio_url,
|
||||
source_language=request.source_language,
|
||||
target_language=request.target_language,
|
||||
quality=request.quality,
|
||||
voice_id=request.voice_id or "Wise_Woman",
|
||||
speed=request.speed or 1.0,
|
||||
emotion=request.emotion or "happy",
|
||||
use_voice_clone=request.use_voice_clone or False,
|
||||
custom_voice_id=request.custom_voice_id,
|
||||
voice_clone_accuracy=request.voice_clone_accuracy or 0.7,
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
logger.info(f"[Dubbing] Created task {task_id} for user {user_id} (voice_clone={request.use_voice_clone})")
|
||||
|
||||
return PodcastAudioDubResponse(
|
||||
task_id=task_id,
|
||||
status="pending",
|
||||
message="Audio dubbing task created"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/dub/{task_id}/result", response_model=PodcastAudioDubResult)
|
||||
async def get_dubbing_result(
|
||||
task_id: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Get the result of a completed dubbing task.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
task_status = task_manager.get_task_status(task_id, requester_user_id=user_id)
|
||||
|
||||
if not task_status:
|
||||
raise HTTPException(status_code=404, detail="Task not found")
|
||||
|
||||
if task_status.get("status") == "failed":
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=task_status.get("error", "Dubbing failed")
|
||||
)
|
||||
|
||||
if task_status.get("status") != "completed":
|
||||
return PodcastAudioDubResult(
|
||||
task_id=task_id,
|
||||
status=task_status.get("status", "pending"),
|
||||
dubbed_audio_url="",
|
||||
dubbed_audio_filename="",
|
||||
original_transcript="",
|
||||
translated_transcript="",
|
||||
source_language="",
|
||||
target_language="",
|
||||
voice_id="",
|
||||
quality="",
|
||||
duration_seconds=0,
|
||||
file_size=0,
|
||||
cost=0.0,
|
||||
voice_clone_used=False,
|
||||
cloned_voice_id=None,
|
||||
)
|
||||
|
||||
result_data = task_status.get("result", {})
|
||||
|
||||
return PodcastAudioDubResult(
|
||||
task_id=task_id,
|
||||
status="completed",
|
||||
dubbed_audio_url=result_data.get("dubbed_audio_url", ""),
|
||||
dubbed_audio_filename=result_data.get("dubbed_audio_filename", ""),
|
||||
original_transcript=result_data.get("original_transcript", ""),
|
||||
translated_transcript=result_data.get("translated_transcript", ""),
|
||||
source_language=result_data.get("source_language", ""),
|
||||
target_language=result_data.get("target_language", ""),
|
||||
voice_id=result_data.get("voice_id", ""),
|
||||
quality=result_data.get("quality", ""),
|
||||
duration_seconds=result_data.get("duration_seconds", 0),
|
||||
file_size=result_data.get("file_size", 0),
|
||||
cost=result_data.get("cost", 0.0),
|
||||
voice_clone_used=result_data.get("voice_clone_used", False),
|
||||
cloned_voice_id=result_data.get("cloned_voice_id"),
|
||||
)
|
||||
|
||||
|
||||
@router.get("/dub/audio/{filename}")
|
||||
async def serve_dubbed_audio(
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Serve a dubbed audio file.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
audio_path = _resolve_dubbed_audio_file(filename, user_id)
|
||||
|
||||
return FileResponse(
|
||||
path=audio_path,
|
||||
media_type="audio/mpeg",
|
||||
filename=filename,
|
||||
)
|
||||
|
||||
|
||||
@router.post("/dub/estimate", response_model=PodcastAudioDubEstimateResponse)
|
||||
async def estimate_dubbing_cost(
|
||||
request: PodcastAudioDubEstimateRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Estimate the cost for audio dubbing.
|
||||
|
||||
Set use_voice_clone=True to include voice cloning cost ($0.05).
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
dubbed_audio_dir = _get_dubbed_audio_dir(user_id, ensure_exists=True)
|
||||
service = AudioDubbingService(output_dir=dubbed_audio_dir)
|
||||
|
||||
cost_estimate = service.estimate_cost(
|
||||
audio_duration_seconds=request.audio_duration_seconds,
|
||||
target_language=request.target_language,
|
||||
quality=request.quality,
|
||||
use_voice_clone=request.use_voice_clone or False,
|
||||
)
|
||||
|
||||
return PodcastAudioDubEstimateResponse(**cost_estimate)
|
||||
|
||||
|
||||
@router.get("/dub/languages")
|
||||
async def get_supported_dubbing_languages(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Get list of supported languages for dubbing.
|
||||
"""
|
||||
from services.translation import list_supported_languages
|
||||
|
||||
languages = list_supported_languages()
|
||||
|
||||
return {
|
||||
"languages": [
|
||||
{"code": code, "name": name}
|
||||
for code, name in sorted(languages.items(), key=lambda x: x[1])
|
||||
],
|
||||
"count": len(languages),
|
||||
}
|
||||
|
||||
|
||||
@router.get("/dub/voices")
|
||||
async def get_available_voices(
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Get list of available TTS voices for dubbing.
|
||||
"""
|
||||
return {
|
||||
"voices": [
|
||||
{"id": "Wise_Woman", "name": "Wise Woman", "gender": "female"},
|
||||
{"id": "Warm_Woman", "name": "Warm Woman", "gender": "female"},
|
||||
{"id": "Young_Woman", "name": "Young Woman", "gender": "female"},
|
||||
{"id": "Mature_Woman", "name": "Mature Woman", "gender": "female"},
|
||||
{"id": "Gentle_Woman", "name": "Gentle Woman", "gender": "female"},
|
||||
{"id": "Confident_Man", "name": "Confident Man", "gender": "male"},
|
||||
{"id": "Warm_Man", "name": "Warm Man", "gender": "male"},
|
||||
{"id": "Young_Man", "name": "Young Man", "gender": "male"},
|
||||
{"id": "Mature_Man", "name": "Mature Man", "gender": "male"},
|
||||
{"id": "Default", "name": "Default", "gender": "neutral"},
|
||||
],
|
||||
"count": 10,
|
||||
"note": "Voice cloning creates custom voices from audio samples. Use /dub/voices/clone to create one."
|
||||
}
|
||||
|
||||
|
||||
@router.post("/dub/voices/clone", response_model=VoiceCloneResponse)
|
||||
async def create_voice_clone_task(
|
||||
request: VoiceCloneRequest,
|
||||
background_tasks: BackgroundTasks,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Clone a voice from an audio sample.
|
||||
|
||||
Creates a custom voice that can be used for dubbing with preserved speaker identity.
|
||||
|
||||
- **source_audio_url**: URL or path to source audio (10-60 seconds recommended)
|
||||
- **custom_voice_id**: Custom name for the cloned voice
|
||||
- **accuracy**: Cloning accuracy 0.1-1.0 (higher = better quality but more processing)
|
||||
- **language_boost**: Language to optimize the voice for
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
task_id = task_manager.create_task(
|
||||
"voice_clone",
|
||||
metadata={"owner_user_id": user_id},
|
||||
)
|
||||
|
||||
background_tasks.add_task(
|
||||
_execute_voice_clone_task,
|
||||
task_id=task_id,
|
||||
source_audio_url=request.source_audio_url,
|
||||
custom_voice_id=request.custom_voice_id,
|
||||
accuracy=request.accuracy or 0.7,
|
||||
language_boost=request.language_boost,
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
logger.info(f"[VoiceClone] Created task {task_id} for user {user_id}")
|
||||
|
||||
return VoiceCloneResponse(
|
||||
task_id=task_id,
|
||||
status="pending",
|
||||
message="Voice cloning task created"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/dub/voices/{task_id}/result", response_model=VoiceCloneResult)
|
||||
async def get_voice_clone_result(
|
||||
task_id: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Get the result of a completed voice cloning task.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
task_status = task_manager.get_task_status(task_id, requester_user_id=user_id)
|
||||
|
||||
if not task_status:
|
||||
raise HTTPException(status_code=404, detail="Task not found")
|
||||
|
||||
if task_status.get("status") == "failed":
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=task_status.get("error", "Voice cloning failed")
|
||||
)
|
||||
|
||||
if task_status.get("status") != "completed":
|
||||
return VoiceCloneResult(
|
||||
task_id=task_id,
|
||||
voice_id="",
|
||||
voice_url="",
|
||||
source_language="",
|
||||
accuracy=0.0,
|
||||
file_size=0,
|
||||
status=task_status.get("status", "pending"),
|
||||
)
|
||||
|
||||
result_data = task_status.get("result", {})
|
||||
|
||||
return VoiceCloneResult(
|
||||
task_id=task_id,
|
||||
voice_id=result_data.get("voice_id", ""),
|
||||
voice_url=result_data.get("voice_url", ""),
|
||||
source_language=result_data.get("source_language", ""),
|
||||
accuracy=result_data.get("accuracy", 0.7),
|
||||
file_size=result_data.get("file_size", 0),
|
||||
status="completed",
|
||||
)
|
||||
|
||||
|
||||
@router.get("/dub/voices/audio/{filename}")
|
||||
async def serve_voice_audio(
|
||||
filename: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Serve a voice sample audio file.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
|
||||
try:
|
||||
audio_path = _resolve_dubbed_audio_file(filename, user_id)
|
||||
except HTTPException as exc:
|
||||
if exc.status_code == 404:
|
||||
raise HTTPException(status_code=404, detail="Voice audio file not found") from exc
|
||||
raise
|
||||
|
||||
return FileResponse(
|
||||
path=audio_path,
|
||||
media_type="audio/mpeg",
|
||||
filename=filename,
|
||||
)
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user