From c0a366269d51bdedb90fd3c9608f797085a05bc2 Mon Sep 17 00:00:00 2001 From: ajaysi Date: Fri, 12 Sep 2025 10:26:08 +0530 Subject: [PATCH] Added blog writer implementation - WIP --- backend/BILLING_SYSTEM_INTEGRATION.md | 256 +++++++ backend/api/blog_writer/__init__.py | 2 + backend/api/blog_writer/router.py | 107 +++ backend/app.py | 7 + backend/models/blog_models.py | 147 ++++ .../research_analysis_20250911_173832.json | 84 +++ .../research_analysis_20250911_174238.json | 206 ++++++ backend/scripts/create_billing_tables.py | 217 ++++++ backend/services/blog_writer/blog_service.py | 649 ++++++++++++++++++ .../gemini_provider.cpython-313.pyc | Bin 25405 -> 23725 bytes .../llm_providers/gemini_grounded_provider.py | 71 +- .../services/llm_providers/gemini_provider.py | 34 +- .../research/google_search_service.py | 53 +- backend/start_alwrity_backend.py | 71 +- backend/test_detailed.py | 43 ++ backend/test_gemini_direct.py | 60 ++ backend/test_research.py | 58 ++ backend/test_research_analysis.py | 115 ++++ backend/verify_billing_setup.py | 280 ++++++++ docs/AI_BLOG_WRITER_IMPLEMENTATION_SPEC.md | 237 +++++++ .../BILLING_FRONTEND_INTEGRATION_PLAN.md | 0 .../BILLING_IMPLEMENTATION_ROADMAP.md | 0 .../BILLING_IMPLEMENTATION_STATUS.md | 0 .../BILLING_TECHNICAL_SPECIFICATION.md | 0 .../SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md | 0 frontend/src/App.tsx | 2 + .../src/components/BlogWriter/BlogWriter.tsx | 581 ++++++++++++++++ .../src/components/BlogWriter/DiffPreview.tsx | 51 ++ .../BlogWriter/EnhancedOutlineEditor.tsx | 535 +++++++++++++++ .../BlogWriter/KeywordInputForm.tsx | 292 ++++++++ .../BlogWriter/RegisterBlogWriterActions.tsx | 21 + .../components/BlogWriter/ResearchAction.tsx | 108 +++ .../components/BlogWriter/ResearchResults.tsx | 351 ++++++++++ .../components/BlogWriter/SEOMiniPanel.tsx | 25 + .../components/BlogWriter/TitleSelector.tsx | 195 ++++++ frontend/src/services/blogWriterApi.ts | 124 ++++ test_research.json | 6 + test_research.py | 58 ++ 38 files changed, 4948 insertions(+), 98 deletions(-) create mode 100644 backend/BILLING_SYSTEM_INTEGRATION.md create mode 100644 backend/api/blog_writer/__init__.py create mode 100644 backend/api/blog_writer/router.py create mode 100644 backend/models/blog_models.py create mode 100644 backend/research_analysis_20250911_173832.json create mode 100644 backend/research_analysis_20250911_174238.json create mode 100644 backend/scripts/create_billing_tables.py create mode 100644 backend/services/blog_writer/blog_service.py create mode 100644 backend/test_detailed.py create mode 100644 backend/test_gemini_direct.py create mode 100644 backend/test_research.py create mode 100644 backend/test_research_analysis.py create mode 100644 backend/verify_billing_setup.py create mode 100644 docs/AI_BLOG_WRITER_IMPLEMENTATION_SPEC.md rename BILLING_FRONTEND_INTEGRATION_PLAN.md => docs/Billing_Subscription/BILLING_FRONTEND_INTEGRATION_PLAN.md (100%) rename BILLING_IMPLEMENTATION_ROADMAP.md => docs/Billing_Subscription/BILLING_IMPLEMENTATION_ROADMAP.md (100%) rename BILLING_IMPLEMENTATION_STATUS.md => docs/Billing_Subscription/BILLING_IMPLEMENTATION_STATUS.md (100%) rename BILLING_TECHNICAL_SPECIFICATION.md => docs/Billing_Subscription/BILLING_TECHNICAL_SPECIFICATION.md (100%) rename SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md => docs/Billing_Subscription/SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md (100%) create mode 100644 frontend/src/components/BlogWriter/BlogWriter.tsx create mode 100644 frontend/src/components/BlogWriter/DiffPreview.tsx create mode 100644 frontend/src/components/BlogWriter/EnhancedOutlineEditor.tsx create mode 100644 frontend/src/components/BlogWriter/KeywordInputForm.tsx create mode 100644 frontend/src/components/BlogWriter/RegisterBlogWriterActions.tsx create mode 100644 frontend/src/components/BlogWriter/ResearchAction.tsx create mode 100644 frontend/src/components/BlogWriter/ResearchResults.tsx create mode 100644 frontend/src/components/BlogWriter/SEOMiniPanel.tsx create mode 100644 frontend/src/components/BlogWriter/TitleSelector.tsx create mode 100644 frontend/src/services/blogWriterApi.ts create mode 100644 test_research.json create mode 100644 test_research.py diff --git a/backend/BILLING_SYSTEM_INTEGRATION.md b/backend/BILLING_SYSTEM_INTEGRATION.md new file mode 100644 index 00000000..ff9a9a08 --- /dev/null +++ b/backend/BILLING_SYSTEM_INTEGRATION.md @@ -0,0 +1,256 @@ +# ALwrity Billing & Subscription System Integration + +## Overview + +The ALwrity backend now includes a comprehensive billing and subscription system that automatically tracks API usage, calculates costs, and manages subscription limits. This system is fully integrated into the startup process and provides real-time monitoring capabilities. + +## ๐Ÿš€ Quick Start + +### 1. Start the Backend with Billing System + +```bash +# From the backend directory +python start_alwrity_backend.py +``` + +The startup script will automatically: +- โœ… Create billing and subscription database tables +- โœ… Initialize default pricing and subscription plans +- โœ… Set up usage tracking middleware +- โœ… Verify all billing components are working +- โœ… Start the server with billing endpoints enabled + +### 2. Verify Installation + +```bash +# Run the comprehensive verification script +python verify_billing_setup.py +``` + +### 3. Test API Endpoints + +```bash +# Get subscription plans +curl http://localhost:8000/api/subscription/plans + +# Get user usage (replace 'demo' with actual user ID) +curl http://localhost:8000/api/subscription/usage/demo + +# Get billing dashboard data +curl http://localhost:8000/api/subscription/dashboard/demo + +# Get API pricing information +curl http://localhost:8000/api/subscription/pricing +``` + +## ๐Ÿ“Š Database Tables + +The billing system creates the following tables: + +| Table Name | Purpose | +|------------|---------| +| `subscription_plans` | Available subscription tiers and pricing | +| `user_subscriptions` | User subscription assignments | +| `api_usage_logs` | Detailed API usage tracking | +| `usage_summaries` | Aggregated usage statistics | +| `api_provider_pricing` | Cost per token for each AI provider | +| `usage_alerts` | Usage limit warnings and notifications | +| `billing_history` | Historical billing records | + +## ๐Ÿ”ง System Components + +### 1. Database Models (`models/subscription_models.py`) +- **SubscriptionPlan**: Subscription tiers and pricing +- **UserSubscription**: User subscription assignments +- **APIUsageLog**: Detailed usage tracking +- **UsageSummary**: Aggregated statistics +- **APIProviderPricing**: Cost calculations +- **UsageAlert**: Limit notifications + +### 2. Services +- **PricingService** (`services/pricing_service.py`): Cost calculations and plan management +- **UsageTrackingService** (`services/usage_tracking_service.py`): Usage monitoring and limits +- **SubscriptionExceptionHandler** (`services/subscription_exception_handler.py`): Error handling + +### 3. API Endpoints (`api/subscription_api.py`) +- `GET /api/subscription/plans` - Available subscription plans +- `GET /api/subscription/usage/{user_id}` - User usage statistics +- `GET /api/subscription/dashboard/{user_id}` - Dashboard data +- `GET /api/subscription/pricing` - API pricing information +- `GET /api/subscription/trends/{user_id}` - Usage trends + +### 4. Middleware Integration +- **Monitoring Middleware** (`middleware/monitoring_middleware.py`): Automatic usage tracking +- **Exception Handling**: Graceful error handling for billing issues + +## ๐ŸŽฏ Frontend Integration + +The billing system is fully integrated with the frontend dashboard: + +### CompactBillingDashboard +- Real-time usage metrics +- Cost tracking +- System health monitoring +- Interactive tooltips and help text + +### EnhancedBillingDashboard +- Detailed usage breakdowns +- Provider-specific costs +- Usage trends and analytics +- Alert management + +## ๐Ÿ“ˆ Usage Tracking + +The system automatically tracks: + +- **API Calls**: Number of requests to each provider +- **Token Usage**: Input and output tokens for each request +- **Costs**: Real-time cost calculations +- **Response Times**: Performance monitoring +- **Error Rates**: Failed request tracking +- **User Activity**: Per-user usage patterns + +## ๐Ÿ’ฐ Pricing Configuration + +### Default AI Provider Pricing (per token) + +| Provider | Model | Input Cost | Output Cost | +|----------|-------|------------|-------------| +| OpenAI | GPT-4 | $0.00003 | $0.00006 | +| OpenAI | GPT-3.5-turbo | $0.0000015 | $0.000002 | +| Gemini | Gemini Pro | $0.0000005 | $0.0000015 | +| Anthropic | Claude-3 | $0.000008 | $0.000024 | +| Mistral | Mistral-7B | $0.0000002 | $0.0000006 | + +### Subscription Plans + +| Plan | Monthly Price | Yearly Price | API Limits | +|------|---------------|--------------|------------| +| Free | $0 | $0 | 1,000 calls/month | +| Starter | $29 | $290 | 10,000 calls/month | +| Professional | $99 | $990 | 100,000 calls/month | +| Enterprise | $299 | $2,990 | Unlimited | + +## ๐Ÿ” Monitoring & Alerts + +### Real-time Monitoring +- Usage tracking for all API calls +- Cost calculations in real-time +- Performance metrics +- Error rate monitoring + +### Alert System +- Usage approaching limits (80% threshold) +- Cost overruns +- System health issues +- Provider-specific problems + +## ๐Ÿ› ๏ธ Development Mode + +For development with auto-reload: + +```bash +# Development mode with auto-reload +python start_alwrity_backend.py --dev + +# Or with explicit reload flag +python start_alwrity_backend.py --reload +``` + +## ๐Ÿ“ Configuration + +### Environment Variables + +The system uses the following environment variables: + +```bash +# Database +DATABASE_URL=sqlite:///./alwrity.db + +# API Keys (configured through onboarding) +OPENAI_API_KEY=your_key_here +GEMINI_API_KEY=your_key_here +ANTHROPIC_API_KEY=your_key_here +MISTRAL_API_KEY=your_key_here + +# Server Configuration +HOST=0.0.0.0 +PORT=8000 +DEBUG=true +``` + +### Custom Pricing + +To modify pricing, update the `PricingService.initialize_default_pricing()` method in `services/pricing_service.py`. + +## ๐Ÿงช Testing + +### Run Verification Script +```bash +python verify_billing_setup.py +``` + +### Test Individual Components +```bash +# Test subscription system +python test_subscription_system.py + +# Test billing tables creation +python scripts/create_billing_tables.py +``` + +## ๐Ÿšจ Troubleshooting + +### Common Issues + +1. **Tables not created**: Run `python scripts/create_billing_tables.py` +2. **Missing dependencies**: Run `pip install -r requirements.txt` +3. **Database errors**: Check `DATABASE_URL` in environment +4. **API key issues**: Verify API keys are configured + +### Debug Mode + +Enable debug logging by setting `DEBUG=true` in your environment. + +## ๐Ÿ“š API Documentation + +Once the server is running, access the interactive API documentation: + +- **Swagger UI**: http://localhost:8000/api/docs +- **ReDoc**: http://localhost:8000/api/redoc + +## ๐Ÿ”„ Updates and Maintenance + +### Adding New Providers + +1. Add provider to `APIProvider` enum in `models/subscription_models.py` +2. Update pricing in `PricingService.initialize_default_pricing()` +3. Add provider detection in middleware +4. Update frontend provider chips + +### Modifying Plans + +1. Update `PricingService.initialize_default_plans()` +2. Modify plan limits and pricing +3. Test with verification script + +## ๐Ÿ“ž Support + +For issues or questions: + +1. Check the verification script output +2. Review the startup logs +3. Test individual components +4. Check database table creation + +## ๐ŸŽ‰ Success Indicators + +You'll know the billing system is working when: + +- โœ… Startup script shows "Billing and subscription tables created successfully" +- โœ… Verification script passes all checks +- โœ… API endpoints return data +- โœ… Frontend dashboard shows usage metrics +- โœ… Usage tracking middleware is active + +The billing system is now fully integrated and ready for production use! diff --git a/backend/api/blog_writer/__init__.py b/backend/api/blog_writer/__init__.py new file mode 100644 index 00000000..6b4c2118 --- /dev/null +++ b/backend/api/blog_writer/__init__.py @@ -0,0 +1,2 @@ +# Package init for AI Blog Writer API + diff --git a/backend/api/blog_writer/router.py b/backend/api/blog_writer/router.py new file mode 100644 index 00000000..4a5da1c2 --- /dev/null +++ b/backend/api/blog_writer/router.py @@ -0,0 +1,107 @@ +from fastapi import APIRouter, HTTPException +from typing import Any, Dict + +from models.blog_models import ( + BlogResearchRequest, + BlogResearchResponse, + BlogOutlineRequest, + BlogOutlineResponse, + BlogOutlineRefineRequest, + BlogSectionRequest, + BlogSectionResponse, + BlogOptimizeRequest, + BlogOptimizeResponse, + BlogSEOAnalyzeRequest, + BlogSEOAnalyzeResponse, + BlogSEOMetadataRequest, + BlogSEOMetadataResponse, + BlogPublishRequest, + BlogPublishResponse, + HallucinationCheckRequest, + HallucinationCheckResponse, +) +from services.blog_writer.blog_service import BlogWriterService + + +router = APIRouter(prefix="/api/blog", tags=["AI Blog Writer"]) + +service = BlogWriterService() + + +@router.get("/health") +async def health() -> Dict[str, Any]: + return {"status": "ok", "service": "ai_blog_writer"} + + +@router.post("/research", response_model=BlogResearchResponse) +async def research(request: BlogResearchRequest) -> BlogResearchResponse: + try: + return await service.research(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/outline/generate", response_model=BlogOutlineResponse) +async def generate_outline(request: BlogOutlineRequest) -> BlogOutlineResponse: + try: + return await service.generate_outline(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/outline/refine", response_model=BlogOutlineResponse) +async def refine_outline(request: BlogOutlineRefineRequest) -> BlogOutlineResponse: + try: + return await service.refine_outline(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/section/generate", response_model=BlogSectionResponse) +async def generate_section(request: BlogSectionRequest) -> BlogSectionResponse: + try: + return await service.generate_section(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/section/optimize", response_model=BlogOptimizeResponse) +async def optimize_section(request: BlogOptimizeRequest) -> BlogOptimizeResponse: + try: + return await service.optimize_section(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/quality/hallucination-check", response_model=HallucinationCheckResponse) +async def hallucination_check(request: HallucinationCheckRequest) -> HallucinationCheckResponse: + try: + return await service.hallucination_check(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/seo/analyze", response_model=BlogSEOAnalyzeResponse) +async def seo_analyze(request: BlogSEOAnalyzeRequest) -> BlogSEOAnalyzeResponse: + try: + return await service.seo_analyze(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/seo/metadata", response_model=BlogSEOMetadataResponse) +async def seo_metadata(request: BlogSEOMetadataRequest) -> BlogSEOMetadataResponse: + try: + return await service.seo_metadata(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + +@router.post("/publish", response_model=BlogPublishResponse) +async def publish(request: BlogPublishRequest) -> BlogPublishResponse: + try: + return await service.publish(request) + except Exception as e: + raise HTTPException(status_code=500, detail=str(e)) + + diff --git a/backend/app.py b/backend/app.py index 6a543303..b40b0ed1 100644 --- a/backend/app.py +++ b/backend/app.py @@ -457,6 +457,13 @@ app.include_router(content_planning_router) app.include_router(user_data_router) app.include_router(strategy_copilot_router) +# Include AI Blog Writer router +try: + from api.blog_writer.router import router as blog_writer_router + app.include_router(blog_writer_router) +except Exception as e: + logger.warning(f"AI Blog Writer router not mounted: {e}") + # Include persona router from api.persona_routes import router as persona_router app.include_router(persona_router) diff --git a/backend/models/blog_models.py b/backend/models/blog_models.py new file mode 100644 index 00000000..8cf1a080 --- /dev/null +++ b/backend/models/blog_models.py @@ -0,0 +1,147 @@ +from pydantic import BaseModel, Field +from typing import List, Optional, Dict, Any + + +class PersonaInfo(BaseModel): + persona_id: Optional[str] = None + tone: Optional[str] = None + audience: Optional[str] = None + industry: Optional[str] = None + + +class ResearchSource(BaseModel): + title: str + url: str + excerpt: Optional[str] = None + credibility_score: Optional[float] = None + published_at: Optional[str] = None + + +class BlogResearchRequest(BaseModel): + keywords: List[str] + topic: Optional[str] = None + industry: Optional[str] = None + target_audience: Optional[str] = None + tone: Optional[str] = None + word_count_target: Optional[int] = 1500 + persona: Optional[PersonaInfo] = None + + +class BlogResearchResponse(BaseModel): + success: bool = True + sources: List[ResearchSource] = [] + keyword_analysis: Dict[str, Any] = {} + competitor_analysis: Dict[str, Any] = {} + suggested_angles: List[str] = [] + search_widget: Optional[str] = None # HTML content for search widget + search_queries: List[str] = [] # Search queries generated by Gemini + + +class BlogOutlineSection(BaseModel): + id: str + heading: str + subheadings: List[str] = [] + key_points: List[str] = [] + references: List[ResearchSource] = [] + target_words: Optional[int] = None + keywords: List[str] = [] + + +class BlogOutlineRequest(BaseModel): + research: BlogResearchResponse + persona: Optional[PersonaInfo] = None + word_count: Optional[int] = 1500 + + +class BlogOutlineResponse(BaseModel): + success: bool = True + title_options: List[str] = [] + outline: List[BlogOutlineSection] = [] + + +class BlogOutlineRefineRequest(BaseModel): + outline: List[BlogOutlineSection] + operation: str + section_id: Optional[str] = None + payload: Optional[Dict[str, Any]] = None + + +class BlogSectionRequest(BaseModel): + section: BlogOutlineSection + keywords: List[str] = [] + tone: Optional[str] = None + persona: Optional[PersonaInfo] = None + + +class BlogSectionResponse(BaseModel): + success: bool = True + markdown: str + citations: List[ResearchSource] = [] + + +class BlogOptimizeRequest(BaseModel): + content: str + goals: List[str] = [] + + +class BlogOptimizeResponse(BaseModel): + success: bool = True + optimized: str + diff_preview: Optional[str] = None + + +class BlogSEOAnalyzeRequest(BaseModel): + content: str + keywords: List[str] = [] + + +class BlogSEOAnalyzeResponse(BaseModel): + success: bool = True + seo_score: float + density: Dict[str, Any] = {} + structure: Dict[str, Any] = {} + readability: Dict[str, Any] = {} + link_suggestions: List[Dict[str, Any]] = [] + image_alt_status: Dict[str, Any] = {} + recommendations: List[str] = [] + + +class BlogSEOMetadataRequest(BaseModel): + content: str + title: Optional[str] = None + keywords: List[str] = [] + + +class BlogSEOMetadataResponse(BaseModel): + success: bool = True + title_options: List[str] + meta_descriptions: List[str] + open_graph: Dict[str, Any] + twitter_card: Dict[str, Any] + schema_data: Dict[str, Any] + + +class BlogPublishRequest(BaseModel): + platform: str = Field(pattern="^(wix|wordpress)$") + html: str + metadata: BlogSEOMetadataResponse + schedule_time: Optional[str] = None + + +class BlogPublishResponse(BaseModel): + success: bool = True + platform: str + url: Optional[str] = None + post_id: Optional[str] = None + + +class HallucinationCheckRequest(BaseModel): + content: str + sources: List[str] = [] + + +class HallucinationCheckResponse(BaseModel): + success: bool = True + claims: List[Dict[str, Any]] = [] + suggestions: List[Dict[str, Any]] = [] + diff --git a/backend/research_analysis_20250911_173832.json b/backend/research_analysis_20250911_173832.json new file mode 100644 index 00000000..102f6169 --- /dev/null +++ b/backend/research_analysis_20250911_173832.json @@ -0,0 +1,84 @@ +{ + "success": true, + "sources": [ + { + "title": "Search: AI content generation trends 2024 2025 technology industry", + "url": "https://www.google.com/search?q=AI+content+generation+trends+2024+2025+technology+industry", + "excerpt": "Source from Search: AI content generation trends 2024 2025 technology industry", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "Search: AI content generation market statistics 2024 2025", + "url": "https://www.google.com/search?q=AI+content+generation+market+statistics+2024+2025", + "excerpt": "Source from Search: AI content generation market statistics 2024 2025", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "Search: AI content generation expert opinions 2024 2025", + "url": "https://www.google.com/search?q=AI+content+generation+expert+opinions+2024+2025", + "excerpt": "Source from Search: AI content generation expert opinions 2024 2025", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "Search: recent developments AI content generation 2024 2025", + "url": "https://www.google.com/search?q=recent+developments+AI+content+generation+2024+2025", + "excerpt": "Source from Search: recent developments AI content generation 2024 2025", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "Search: AI content generation market analysis forecast 2024 2025", + "url": "https://www.google.com/search?q=AI+content+generation+market+analysis+forecast+2024+2025", + "excerpt": "Source from Search: AI content generation market analysis forecast 2024 2025", + "credibility_score": 0.8, + "published_at": "2024-01-01" + } + ], + "keyword_analysis": { + "primary": [ + "AI content generation" + ], + "secondary": [ + "blog writing" + ], + "long_tail": [ + "AI content generation guide", + "blog writing guide" + ], + "search_intent": "informational", + "difficulty": 6, + "content_gaps": [ + "AI content generation best practices", + "blog writing best practices" + ], + "analysis_content": "## The AI Content Generation Revolution: Navigating 2024-2025 Trends for Strategic Advantage\n\nThe landscape of content creation is undergoing a seismic shift, powered by the rapid advancements in Arti" + }, + "competitor_analysis": { + "top_competitors": [], + "content_gaps": [], + "opportunities": [], + "analysis_notes": "Competitor analysis from research" + }, + "suggested_angles": [ + "How ALwrity content generation is Transforming Technology", + "Latest ALwrity content generation Trends: What You Need to Know", + "ALwrity content generation Best Practices for Technology", + "Case Study: ALwrity content generation Success Stories", + "The Future of ALwrity content generation in Technology" + ], + "search_widget": "\n
\n
\n \n \n \n \n \n \n \n \n \n \n \n \n \n
\n
\n
\n top AI content generation competitors market share 2024\n best practices AI content generation case studies 2024 2025\n AI content generation expert opinions 2024 2025\n AI content generation trends 2024 2025 technology industry\n AI content generation market statistics 2024 2025\n AI content generation market analysis forecast 2024 2025\n keywords for AI content generation technology\n recent developments AI content generation 2024 2025\n AI content generation content gaps\n
\n
\n", + "search_queries": [ + "AI content generation trends 2024 2025 technology industry", + "AI content generation market statistics 2024 2025", + "AI content generation expert opinions 2024 2025", + "recent developments AI content generation 2024 2025", + "AI content generation market analysis forecast 2024 2025", + "best practices AI content generation case studies 2024 2025", + "keywords for AI content generation technology", + "top AI content generation competitors market share 2024", + "AI content generation content gaps" + ] +} \ No newline at end of file diff --git a/backend/research_analysis_20250911_174238.json b/backend/research_analysis_20250911_174238.json new file mode 100644 index 00000000..8379d320 --- /dev/null +++ b/backend/research_analysis_20250911_174238.json @@ -0,0 +1,206 @@ +{ + "success": true, + "sources": [ + { + "title": "alwrity.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEbkhlVuzpjaGypNYMsWxvHBbX3AmqYaaOrbGeSKtT03vLSAx9LQlACNs0ulmX0oFvX610EvDErz6lWd9TTh7pSvrbWM-L6WaKh8HiAEucGVHXbKQ==", + "excerpt": "Source from alwrity.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "alwrity.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHI_UttMuqLpNEDZnP22X5mhTqjrqObIjM66Ks8UoMHPN_SlF5XenKZlUiOPGQRuYPoNDqRctDEeheEZOZMm3SqM5OkrActXWVNXaqsdk4WwPcI4Jhep8vo1cm27c4=", + "excerpt": "Source from alwrity.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "youtube.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGkWsMQ3Tjq8DewK8EikdNign9gcrLv11xR30xrMx-vq1sSfdmGk5w8s6vuDtIL4-YxqSyDcpb4ifwmwF9lq9tsKF_fd0Zenzd19PHrQ0-65vgeEO5CV6oGdO1TN7eZ0SCkLHsmFZ8=", + "excerpt": "Source from youtube.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "youtube.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEBvGGtIXARTEe4XR1DH-6yFwzEC8HkG7GXEz6OpKTwznIJPC3V2VWbU5BqZpEzdt5U82qbuAdo4iZ006PzcanX-OQWA8EVy0R5-Yz43snYK-kt9JfvniBxLGDHXdz70J4creDZoSY=", + "excerpt": "Source from youtube.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "beyondkey.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGRwVUwjgBma_K_ceWgs1ha6f5zat1idtf7AAXTnGW94yvWxNSSCA4615crchD8y4aSxXbVcyxj-mxDQP685ZvKevkDxPUTKdlTYvRWkT5Ewbc5vMo17qqvcw2MPF3SEvLjODMUT7hzUFJXb5gIehVh1Pq0g1MFz_3uW8jxdcHMend_PjiR6VE=", + "excerpt": "Source from beyondkey.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "medium.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQG3nG07PWqQhD9bLlXOBM9fBHVxgkZM_DEnKsUeHl-te61BWZcKL0fQbe8_oZUZWRFggLi4CgZxO__3Sfw5mfaYHDU6394PWEQ7qTa0UUwaTuKnLWBA2RX4A5LjGY0LglG01higs7_fetcOWwPTSvg-Y06d8pSZWUHHuiunoklPoQuR1tAQKvhKDvZbmJMIHPMkoLyovsag6rjmN_Chn0hqPf4=", + "excerpt": "Source from medium.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "quickcreator.io", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHedj-KoY0QaU_0xyYVSyIb6NJWQjYPx5OpFxdRefde4fxALVZZ_uCcDyODW8UOeCTEJl_ynXnE5yKlFd_6jgHND9koGUnCPfwLDeZ-XzVjHlgY5V2GnmH6B8bH-lvdzVYUBZlvI0iDtq5hoNxqfz10jLh834ZrIc6NjTtG7kXLR7ddMg7FjEQ57Cu49Ug=", + "excerpt": "Source from quickcreator.io", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "eimt.edu.eu", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFEyrobre2Q5LbCgLAYSxH1C8BCNy3Ln4iOIQ6_NGAD63_lp6EqMYourvzgiSOXtane5aLyRCzc0erIbMe0TIsO406sZ7jULZ8AbkaD93TTn34wRbNuUGOg9sCf9PcTAJSWMfX05cle8BfK6mhQU2t9EslhcSTEZBRTTGgPu_NmfMUVjZJ_9_6fT4qLUZtAuqpe", + "excerpt": "Source from eimt.edu.eu", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "youtube.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEgK2_pZbhzW_wihG2wmD383PgA3awfJLNUBdMoevHvDou8oDoI24xQeKAaJsDpHJ-LxtRIdhOlg6RZCwLSRsjKQlL3_mFddH30OLZU-_IXAZ8sLmMCGgM8J7isNuhWQZTNrkoT2x0=", + "excerpt": "Source from youtube.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "synthesia.io", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHMYC4-O4vRXhpwIZZ49Y7sJVJQ9pSJ6rDEN_dayRuoct0Q2ECmVH26wsyqdQAYiLPZLkQTlIgGZBIocrhqkZDj97UmGF66dGzvSGFUJXvOA127mFWYKXJ8TUYIr8Tjn9HQ", + "excerpt": "Source from synthesia.io", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "tryleap.ai", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGZKtSSrxOYpXnBKsFhUoAtpw01oVKooJkUIpyVYqEguhSDWcX7svylTkuFy_8RrxKmvKBkNJjRn6KE6OMCTHV4AOET0fUaPJhxfwcnyvY1BB8GHQeDa_B-VfchBp_qeAdeS2m-_IQuLOUI-jV7wFpaA9Gg3-rcK_uqwtmrprxZCztkyJM=", + "excerpt": "Source from tryleap.ai", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "hulkapps.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGcKDCewhOKAICoIWfiwqPDerQO3P6Ipm6vsTz-ujH7G-Vg9eo3LgACMbsTxk9IUCg7-fn_bV_QKah9N8VW0YEXBfyWZRqdTMbBbg07fswpACpIn1znpRmiJU3o_G3w99AgLNBtenIzIPpTnBj2ascMGNgEmrgDDznNFaX4LP5E0F6ToIWt3A3SrwJWpJwKyfyJ", + "excerpt": "Source from hulkapps.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "marketful.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGFSpjwPUVCdlTrnxsqCp-O7T2-kUk4_hZrVYYZDrfFxvDLp5knmTd8PSTcoDybNfq8Iiod5DLhYaFIrL5G8yl2oU3UCl4KNqkRb95U6alKy2LumA1iHzYE4xtXDlvPdoP31pWPt5Pi2P_1aMTt921v_0oE1s4=", + "excerpt": "Source from marketful.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "ics-digital.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHf0mDC8n9_pdUthEbF2f_FbRkiwcyc0I4GcRqa1dnbRzSU50Y9LiSWmWDpOM3-GYNmB3YmNZT7p0QBxbtKuju0ol7jA58RYphVUHtmJXwhea4lEwkKCAf8ONvIHtcGqpY4QdbsixE4rV2en6d9qoPER7i1QkPyknYsPw0QSJI=", + "excerpt": "Source from ics-digital.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "frase.io", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQG7h5MlbO5qp0jD2NFIyH1HUQff6CMreopPd0MExSZ00saW_ikR9QJTABCBmdR8CSdkAphaMJYOJG9i3qQQyoOlg_Seh_9JF8zQqdPj", + "excerpt": "Source from frase.io", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "thebusinessresearchcompany.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEEvY4sZPVx7eA9v_j8qaQ_Tj7ljjwZ0hIdrxERYykbSkTId97TlSY74VYyu9IlOmcRtXpwNSgp6Q35BUKB3gvb6o0o6-PNfoYoEPHx6N6sXZs6lrtvqqpcTLqc7sOskZ-jxmZ_IEKX_VeIRxp41XBTY603RDiU-1CqrNUUkjwbxNorilqmV-3Oa0bbi5TvqoSNS98GHQrV0VUN9d21jMLPSpj9xRcB", + "excerpt": "Source from thebusinessresearchcompany.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "grandviewresearch.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQE-1--CbRoZLTs6PrEs7_b5Q4D2eJViu2pZrVlDTS8QfRf1DSDepwb2KO0ozfq04iLJRHXeBjLnu8tV6bOD9mXTv8paG_3Irgow9cpOw5jsPrvvqXmAJA-IvebcDdISuIUk7rZsfn95_BpnMsm4cWR4HTlYwTLWfGR5zUOtuupKG0Od2E5HpnYIH3TmlZ45y2fvvhw0wk8qjA==", + "excerpt": "Source from grandviewresearch.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "verifiedmarketresearch.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEAPa_eY2-XR46ROJMDfq4b4YbZivGtdu2F0z2I3tHk10ZRr_j4HIPFZkmwFuvFm4iSBh7efJBbsvvp8TjelRmgskKKZSJw52f4oNsp4b-ewlmv5daOrwcH-to89YjZVvzpj-fs_hvCoKIDnmSQubcS62jqs_EVbWAomX-8cr7_gfg=", + "excerpt": "Source from verifiedmarketresearch.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "siegemedia.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHkqpyuKPcPnTPdEI0qp6aR_gS7FOAgmJMjST58kZQtmApd9g1eynllR3vtkjVg1Y4IjLifjICqueLx-32ugvMPISwXlqq8D8LgC5j_YLvvyTAaq9drZM56OpgaRscGt4cuD-YoEhMs53xX18h798fs7gbc3g==", + "excerpt": "Source from siegemedia.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "synthesia.io", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEtHmkgnrc-O2jG90jSY2OL_SvNN2ToZFl2CYmA7eSpPuDGvMWDpbg6NuTsAB8fFBwP4eRcRvqtoP74lJINPvxHw6uARdRuGIZmlBcldYRYiBvWLOz4oMcRzfIDNXSzzQUM57cmQwc=", + "excerpt": "Source from synthesia.io", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "makebot.ai", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGNko08ftgaMVm9H1Jh-4vsgHjfFRriAeloVI_KWg2Ee-1MIs1N6o7X3MC0n98C4YgVzeXWM8W_3R-pFze-6R6uJsu1tdZms_1MI3NPGi4oKdSVRULy2vaY_SQVOiEDyqM3JSkJ3z1QZos-lUEeuG46iLr43KX3bJHRR5dzTh7eNFDv43DjEupuGR2KYX60j7ui929PXdP-e92yNcQuOu18740to6Gto2FdPT0=", + "excerpt": "Source from makebot.ai", + "credibility_score": 0.8, + "published_at": "2024-01-01" + }, + { + "title": "medium.com", + "url": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQE2oEe411ttOlvnVvTUNZI60cD5iLva5mD7SDy0q1bGMM-DTyxXsNeAnegRIGY--svZZXEoqZrWnnA0K-j9T7KKZgZcqSodRYS8I5Qx_xKyuZ6OwJhKMUo4PFPhbvcid2mq1m9oS65rgHVM8iNFUBOtxyvYYOQGGf0tOsYGYevF68eQ5PaGJ-6iEbA=", + "excerpt": "Source from medium.com", + "credibility_score": 0.8, + "published_at": "2024-01-01" + } + ], + "keyword_analysis": { + "primary": [ + "AI content generation" + ], + "secondary": [ + "blog writing" + ], + "long_tail": [ + "AI content generation guide", + "blog writing guide" + ], + "search_intent": "informational", + "difficulty": 6, + "content_gaps": [ + "AI content generation best practices", + "blog writing best practices" + ], + "analysis_content": "## The Future of Content Creation: A Deep Dive into ALwrity and AI-Powered Content Generation (2024-2025)\n\nThe landscape of content creation is undergoing a profound transformation, largely driven by " + }, + "competitor_analysis": { + "top_competitors": [], + "content_gaps": [], + "opportunities": [], + "analysis_notes": "Competitor analysis from research" + }, + "suggested_angles": [ + "How ALwrity content generation is Transforming Technology", + "Latest ALwrity content generation Trends: What You Need to Know", + "ALwrity content generation Best Practices for Technology", + "Case Study: ALwrity content generation Success Stories", + "The Future of ALwrity content generation in Technology" + ], + "search_widget": "\n
\n
\n \n \n \n \n \n \n \n \n \n \n \n \n \n
\n
\n
\n expert opinions on AI content creation 2024 2025\n AI content writing market size forecast 2024 2025\n ALwrity content generation\n AI content generation trends 2024 2025\n best practices for AI-powered content strategy\n AI content generation tools comparison 2024\n recent developments in generative AI for content 2024 2025\n top AI content generators 2024\n keywords for AI content generation\n long tail keywords AI content writing\n AI content creation case studies 2024\n AI content writing software\n
\n
\n", + "search_queries": [ + "ALwrity content generation", + "AI content generation trends 2024 2025", + "AI content writing market size forecast 2024 2025", + "expert opinions on AI content creation 2024 2025", + "recent developments in generative AI for content 2024 2025", + "best practices for AI-powered content strategy", + "AI content generation tools comparison 2024", + "AI content writing software", + "top AI content generators 2024", + "keywords for AI content generation", + "long tail keywords AI content writing", + "AI content creation case studies 2024" + ] +} \ No newline at end of file diff --git a/backend/scripts/create_billing_tables.py b/backend/scripts/create_billing_tables.py new file mode 100644 index 00000000..60b36726 --- /dev/null +++ b/backend/scripts/create_billing_tables.py @@ -0,0 +1,217 @@ +""" +Database Migration Script for Billing System +Creates all tables needed for billing, usage tracking, and subscription management. +""" + +import sys +import os +from pathlib import Path + +# Add the backend directory to Python path +backend_dir = Path(__file__).parent.parent +sys.path.insert(0, str(backend_dir)) + +from sqlalchemy import create_engine, text +from sqlalchemy.orm import sessionmaker +from loguru import logger +import traceback + +# Import models +from models.subscription_models import Base as SubscriptionBase +from services.database import DATABASE_URL +from services.pricing_service import PricingService + +def create_billing_tables(): + """Create all billing and subscription-related tables.""" + + try: + # Create engine + engine = create_engine(DATABASE_URL, echo=True) + + # Create all tables + logger.info("Creating billing and subscription system tables...") + SubscriptionBase.metadata.create_all(bind=engine) + logger.info("โœ… Billing and subscription tables created successfully") + + # Create session for data initialization + SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine) + db = SessionLocal() + + try: + # Initialize pricing and plans + pricing_service = PricingService(db) + + logger.info("Initializing default API pricing...") + pricing_service.initialize_default_pricing() + logger.info("โœ… Default API pricing initialized") + + logger.info("Initializing default subscription plans...") + pricing_service.initialize_default_plans() + logger.info("โœ… Default subscription plans initialized") + + except Exception as e: + logger.error(f"Error initializing default data: {e}") + logger.error(traceback.format_exc()) + db.rollback() + raise + finally: + db.close() + + logger.info("๐ŸŽ‰ Billing system setup completed successfully!") + + # Display summary + display_setup_summary(engine) + + except Exception as e: + logger.error(f"โŒ Error creating billing tables: {e}") + logger.error(traceback.format_exc()) + raise + +def display_setup_summary(engine): + """Display a summary of the created tables and data.""" + + try: + with engine.connect() as conn: + logger.info("\n" + "="*60) + logger.info("BILLING SYSTEM SETUP SUMMARY") + logger.info("="*60) + + # Check tables + tables_query = text(""" + SELECT name FROM sqlite_master + WHERE type='table' AND ( + name LIKE '%subscription%' OR + name LIKE '%usage%' OR + name LIKE '%billing%' OR + name LIKE '%pricing%' OR + name LIKE '%alert%' + ) + ORDER BY name + """) + + result = conn.execute(tables_query) + tables = result.fetchall() + + logger.info(f"\n๐Ÿ“Š Created Tables ({len(tables)}):") + for table in tables: + logger.info(f" โ€ข {table[0]}") + + # Check subscription plans + try: + plans_query = text("SELECT COUNT(*) FROM subscription_plans") + result = conn.execute(plans_query) + plan_count = result.fetchone()[0] + logger.info(f"\n๐Ÿ’ณ Subscription Plans: {plan_count}") + + if plan_count > 0: + plans_detail_query = text(""" + SELECT name, tier, price_monthly, price_yearly + FROM subscription_plans + ORDER BY price_monthly + """) + result = conn.execute(plans_detail_query) + plans = result.fetchall() + + for plan in plans: + name, tier, monthly, yearly = plan + logger.info(f" โ€ข {name} ({tier}): ${monthly}/month, ${yearly}/year") + except Exception as e: + logger.warning(f"Could not check subscription plans: {e}") + + # Check API pricing + try: + pricing_query = text("SELECT COUNT(*) FROM api_provider_pricing") + result = conn.execute(pricing_query) + pricing_count = result.fetchone()[0] + logger.info(f"\n๐Ÿ’ฐ API Pricing Entries: {pricing_count}") + + if pricing_count > 0: + pricing_detail_query = text(""" + SELECT provider, model_name, cost_per_input_token, cost_per_output_token + FROM api_provider_pricing + WHERE cost_per_input_token > 0 OR cost_per_output_token > 0 + ORDER BY provider, model_name + LIMIT 10 + """) + result = conn.execute(pricing_detail_query) + pricing_entries = result.fetchall() + + logger.info("\n LLM Pricing (per token) - Top 10:") + for entry in pricing_entries: + provider, model, input_cost, output_cost = entry + logger.info(f" โ€ข {provider}/{model}: ${input_cost:.8f} in, ${output_cost:.8f} out") + except Exception as e: + logger.warning(f"Could not check API pricing: {e}") + + logger.info("\n" + "="*60) + logger.info("NEXT STEPS:") + logger.info("="*60) + logger.info("1. Billing system is ready for use") + logger.info("2. API endpoints are available at:") + logger.info(" GET /api/subscription/plans") + logger.info(" GET /api/subscription/usage/{user_id}") + logger.info(" GET /api/subscription/dashboard/{user_id}") + logger.info(" GET /api/subscription/pricing") + logger.info("\n3. Frontend billing dashboard is integrated") + logger.info("4. Usage tracking middleware is active") + logger.info("5. Real-time cost monitoring is enabled") + logger.info("="*60) + + except Exception as e: + logger.error(f"Error displaying summary: {e}") + +def check_existing_tables(engine): + """Check if billing tables already exist.""" + + try: + with engine.connect() as conn: + # Check for billing tables + check_query = text(""" + SELECT name FROM sqlite_master + WHERE type='table' AND ( + name = 'subscription_plans' OR + name = 'user_subscriptions' OR + name = 'api_usage_logs' OR + name = 'usage_summaries' OR + name = 'api_provider_pricing' OR + name = 'usage_alerts' + ) + """) + + result = conn.execute(check_query) + existing_tables = result.fetchall() + + if existing_tables: + logger.warning(f"Found existing billing tables: {[t[0] for t in existing_tables]}") + logger.info("Tables already exist. Skipping creation to preserve data.") + return False + + return True + + except Exception as e: + logger.error(f"Error checking existing tables: {e}") + return True # Proceed anyway + +if __name__ == "__main__": + logger.info("๐Ÿš€ Starting billing system database migration...") + + try: + # Create engine to check existing tables + engine = create_engine(DATABASE_URL, echo=False) + + # Check existing tables + if not check_existing_tables(engine): + logger.info("โœ… Billing tables already exist, skipping creation") + sys.exit(0) + + # Create tables and initialize data + create_billing_tables() + + logger.info("โœ… Billing system migration completed successfully!") + + except KeyboardInterrupt: + logger.info("Migration cancelled by user") + sys.exit(0) + except Exception as e: + logger.error(f"โŒ Migration failed: {e}") + sys.exit(1) diff --git a/backend/services/blog_writer/blog_service.py b/backend/services/blog_writer/blog_service.py new file mode 100644 index 00000000..7bad6cfa --- /dev/null +++ b/backend/services/blog_writer/blog_service.py @@ -0,0 +1,649 @@ +from typing import Any, Dict, List +from loguru import logger +from services.llm_providers.gemini_provider import gemini_structured_json_response + +from models.blog_models import ( + BlogResearchRequest, + BlogResearchResponse, + BlogOutlineRequest, + BlogOutlineResponse, + BlogOutlineRefineRequest, + BlogSectionRequest, + BlogSectionResponse, + BlogOptimizeRequest, + BlogOptimizeResponse, + BlogSEOAnalyzeRequest, + BlogSEOAnalyzeResponse, + BlogSEOMetadataRequest, + BlogSEOMetadataResponse, + BlogPublishRequest, + BlogPublishResponse, + ResearchSource, + BlogOutlineSection, +) + + +class BlogWriterService: + """Service layer for AI Blog Writer (stub implementations for scaffolding).""" + + async def research(self, request: BlogResearchRequest) -> BlogResearchResponse: + """ + Stage 1: Research & Strategy (AI Orchestration) + Uses ONLY Gemini's native Google Search grounding - ONE API call for everything. + Follows LinkedIn service pattern for efficiency and cost optimization. + """ + from services.llm_providers.gemini_grounded_provider import GeminiGroundedProvider + + gemini = GeminiGroundedProvider() + + topic = request.topic or ", ".join(request.keywords) + industry = request.industry or (request.persona.industry if request.persona and request.persona.industry else "General") + target_audience = getattr(request.persona, 'target_audience', 'General') if request.persona else 'General' + + # Single comprehensive research prompt - Gemini handles Google Search automatically + research_prompt = f""" + Research the topic "{topic}" in the {industry} industry for {target_audience} audience. Provide a comprehensive analysis including: + + 1. Current trends and insights (2024-2025) + 2. Key statistics and data points with sources + 3. Industry expert opinions and quotes + 4. Recent developments and news + 5. Market analysis and forecasts + 6. Best practices and case studies + 7. Keyword analysis: primary, secondary, and long-tail opportunities + 8. Competitor analysis: top players and content gaps + 9. Content angle suggestions: 5 compelling angles for blog posts + + Focus on factual, up-to-date information from credible sources. + Include specific data points, percentages, and recent developments. + Structure your response with clear sections for each analysis area. + """ + + # Single Gemini call with native Google Search grounding - no fallbacks + gemini_result = await gemini.generate_grounded_content( + prompt=research_prompt, + content_type="research", + max_tokens=2000 + ) + + # Extract sources from grounding metadata + sources = self._extract_sources_from_grounding(gemini_result) + + # Extract search widget and queries for UI display + search_widget = gemini_result.get("search_widget", "") or "" + search_queries = gemini_result.get("search_queries", []) or [] + + # Parse the comprehensive response for different analysis components + content = gemini_result.get("content", "") + keyword_analysis = self._parse_keyword_analysis(content, request.keywords) + competitor_analysis = self._parse_competitor_analysis(content) + suggested_angles = self._parse_content_angles(content, topic, industry) + + logger.info(f"Research completed successfully with {len(sources)} sources and {len(search_queries)} search queries") + + return BlogResearchResponse( + success=True, + sources=sources, + keyword_analysis=keyword_analysis, + competitor_analysis=competitor_analysis, + suggested_angles=suggested_angles, + # Add search widget and queries for UI display + search_widget=search_widget if 'search_widget' in locals() else "", + search_queries=search_queries if 'search_queries' in locals() else [], + ) + + def _extract_sources_from_grounding(self, gemini_result: Dict[str, Any]) -> List[ResearchSource]: + """Extract sources from Gemini grounding metadata.""" + sources = [] + + # The Gemini grounded provider already extracts sources and puts them in the 'sources' field + raw_sources = gemini_result.get("sources", []) + for src in raw_sources: + source = ResearchSource( + title=src.get("title", "Untitled"), + url=src.get("url", ""), + excerpt=src.get("content", "")[:500] if src.get("content") else f"Source from {src.get('title', 'web')}", + credibility_score=float(src.get("credibility_score", 0.8)), + published_at=str(src.get("publication_date", "2024-01-01")) + ) + sources.append(source) + + return sources + + def _parse_keyword_analysis(self, content: str, original_keywords: List[str]) -> Dict[str, Any]: + """Parse keyword analysis from the research content.""" + # Extract keywords from content sections + lines = content.split('\n') + keyword_section = [] + in_keyword_section = False + + for line in lines: + if 'keyword' in line.lower() and ('analysis' in line.lower() or 'primary' in line.lower()): + in_keyword_section = True + continue + if in_keyword_section and line.strip(): + if line.startswith(('1.', '2.', '3.', '4.', '5.', '6.', '7.', '8.', '9.')): + break + keyword_section.append(line.strip()) + + return { + "primary": original_keywords[:1] if original_keywords else [], + "secondary": original_keywords[1:] if len(original_keywords) > 1 else [], + "long_tail": [f"{kw} guide" for kw in original_keywords[:2]] if original_keywords else [], + "search_intent": "informational", + "difficulty": 6, + "content_gaps": [f"{kw} best practices" for kw in original_keywords[:2]] if original_keywords else [], + "analysis_content": "\n".join(keyword_section) if keyword_section else content[:200] + } + + def _parse_competitor_analysis(self, content: str) -> Dict[str, Any]: + """Parse competitor analysis from the research content.""" + lines = content.split('\n') + competitor_section = [] + in_competitor_section = False + + for line in lines: + if 'competitor' in line.lower() and ('analysis' in line.lower() or 'top' in line.lower()): + in_competitor_section = True + continue + if in_competitor_section and line.strip(): + if line.startswith(('1.', '2.', '3.', '4.', '5.', '6.', '7.', '8.', '9.')): + break + competitor_section.append(line.strip()) + + return { + "top_competitors": [], + "content_gaps": [], + "opportunities": [], + "analysis_notes": "\n".join(competitor_section) if competitor_section else "Competitor analysis from research" + } + + def _parse_content_angles(self, content: str, topic: str, industry: str) -> List[str]: + """Parse content angles from the research content.""" + lines = content.split('\n') + angles_section = [] + in_angles_section = False + + for line in lines: + if 'angle' in line.lower() and ('suggest' in line.lower() or 'content' in line.lower()): + in_angles_section = True + continue + if in_angles_section and line.strip(): + if line.startswith(('1.', '2.', '3.', '4.', '5.', '6.', '7.', '8.', '9.')): + break + if line.strip() and not line.startswith(('โ€ข', '-', '*')): + angles_section.append(line.strip()) + + # If no angles found in content, use fallback + if not angles_section: + angles_section = [ + f"How {topic} is Transforming {industry}", + f"Latest {topic} Trends: What You Need to Know", + f"{topic} Best Practices for {industry}", + f"Case Study: {topic} Success Stories", + f"The Future of {topic} in {industry}" + ] + + return angles_section[:5] # Return top 5 angles + + + async def generate_outline(self, request: BlogOutlineRequest) -> BlogOutlineResponse: + """ + Stage 2: Content Planning with AI-generated outline using research results + Uses Gemini with research data to create comprehensive, SEO-optimized outline + """ + # Extract research insights + research = request.research + primary_keywords = research.keyword_analysis.get('primary', []) + secondary_keywords = research.keyword_analysis.get('secondary', []) + content_angles = research.suggested_angles + sources = research.sources + search_intent = research.keyword_analysis.get('search_intent', 'informational') + + # Build sophisticated outline generation prompt with advanced content strategy + outline_prompt = f""" + You are a world-class content strategist and SEO expert with 15+ years of experience creating viral, high-converting blog content. Your outlines have generated millions of views and driven significant business results. + + CONTENT STRATEGY BRIEF: + Topic: {', '.join(primary_keywords)} + Search Intent: {search_intent} + Target Word Count: {request.word_count or 1500} words + Industry Context: {getattr(request.persona, 'industry', 'General') if request.persona else 'General'} + Audience: {getattr(request.persona, 'target_audience', 'General') if request.persona else 'General'} + + RESEARCH INTELLIGENCE: + Primary Keywords: {', '.join(primary_keywords)} + Secondary Keywords: {', '.join(secondary_keywords)} + Long-tail Opportunities: {', '.join(research.keyword_analysis.get('long_tail', [])[:5])} + + Content Angles Discovered: + {chr(10).join([f"โ€ข {angle}" for angle in content_angles[:6]])} + + Research Sources Available: {len(sources)} authoritative sources with current data + + STRATEGIC OUTLINE REQUIREMENTS: + + 1. CONTENT ARCHITECTURE: + - Create 5-7 sections that follow a logical progression + - Each section must have a clear purpose and value proposition + - Build a narrative arc that keeps readers engaged throughout + - Include strategic content gaps that competitors miss + + 2. SEO OPTIMIZATION: + - Naturally integrate primary keywords in H2 headings (not forced) + - Use secondary keywords in subheadings and key points + - Include long-tail keywords in natural language + - Optimize for featured snippets and voice search + - Create semantic keyword clusters + + 3. READER ENGAGEMENT: + - Start with a compelling hook that addresses pain points + - Use storytelling elements and real-world examples + - Include actionable insights readers can implement immediately + - Create sections that encourage social sharing + - End with a strong call-to-action + + 4. CONTENT DEPTH: + - Each section: 2-4 specific, actionable subheadings + - Each section: 4-6 key points with research-backed insights + - Include data points, statistics, and case studies where relevant + - Address common objections and questions + - Provide unique angles not covered by competitors + + 5. WORD COUNT DISTRIBUTION: + - Introduction: 10-15% of total words + - Main sections: 70-80% of total words (distributed strategically) + - Conclusion: 10-15% of total words + - Total target: {request.word_count or 1500} words + + 6. COMPETITIVE ADVANTAGE: + - Include fresh perspectives from recent research + - Address emerging trends and future implications + - Provide deeper insights than surface-level content + - Include practical tools, frameworks, or templates + - Reference authoritative sources and data + + TITLE STRATEGY: + Create 3 distinct title options that: + - Include primary keywords naturally + - Promise clear value to readers + - Create curiosity and urgency + - Are optimized for click-through rates + - Work well for social media sharing + + CRITICAL: Respond ONLY with valid JSON. No additional text or explanations. + + JSON FORMAT: + {{ + "title_options": [ + "Compelling title with primary keyword and benefit", + "Question-based title that creates curiosity", + "How-to title with specific outcome promise" + ], + "outline": [ + {{ + "heading": "Strategic section title with primary keyword", + "subheadings": [ + "Specific, actionable subheading 1", + "Data-driven subheading 2", + "Case study or example subheading 3" + ], + "key_points": [ + "Research-backed insight with specific data", + "Actionable step readers can take immediately", + "Common mistake to avoid with explanation", + "Advanced tip that provides competitive advantage", + "Real-world example or case study" + ], + "target_words": 300, + "keywords": ["primary keyword", "secondary keyword", "long-tail phrase"] + }} + ] + }} + """ + + logger.info("Generating AI-powered outline using research results") + + # Define the schema for structured JSON response + outline_schema = { + "type": "object", + "properties": { + "title_options": { + "type": "array", + "items": {"type": "string"}, + "description": "3 SEO-optimized title options" + }, + "outline": { + "type": "array", + "items": { + "type": "object", + "properties": { + "id": {"type": "string"}, + "heading": {"type": "string"}, + "subheadings": { + "type": "array", + "items": {"type": "string"} + }, + "key_points": { + "type": "array", + "items": {"type": "string"} + }, + "word_count": {"type": "integer"}, + "keywords": { + "type": "array", + "items": {"type": "string"}, + "description": "Keywords to focus on in this section" + } + }, + "required": ["id", "heading", "subheadings", "key_points", "word_count", "keywords"] + } + } + }, + "required": ["title_options", "outline"] + } + + # Generate outline using structured JSON response (no grounding needed) + outline_data = gemini_structured_json_response( + prompt=outline_prompt, + schema=outline_schema, + temperature=0.3, + max_tokens=3000 + ) + + # Check for errors in the response + if isinstance(outline_data, dict) and 'error' in outline_data: + logger.error(f"Gemini structured response error: {outline_data['error']}") + raise ValueError(f"AI outline generation failed: {outline_data['error']}") + + # Validate required fields + if not isinstance(outline_data, dict) or 'outline' not in outline_data or not isinstance(outline_data['outline'], list): + logger.error(f"Invalid outline structure: {outline_data}") + raise ValueError("Invalid outline structure in Gemini response") + + # Convert to BlogOutlineSection objects + outline_sections = [] + for i, section_data in enumerate(outline_data.get('outline', [])): + if not isinstance(section_data, dict) or 'heading' not in section_data: + logger.warning(f"Skipping invalid section data at index {i}") + continue + + section = BlogOutlineSection( + id=f"s{i+1}", + heading=section_data.get('heading', f'Section {i+1}'), + subheadings=section_data.get('subheadings', []), + key_points=section_data.get('key_points', []), + references=sources[:2] if i < 2 else [], # Assign sources to first 2 sections + target_words=section_data.get('target_words', 300), + keywords=section_data.get('keywords', []) + ) + outline_sections.append(section) + + title_options = outline_data.get('title_options', []) + if not title_options: + raise ValueError("No title options provided in Gemini response") + + logger.info(f"Generated outline with {len(outline_sections)} sections and {len(title_options)} title options") + + return BlogOutlineResponse( + success=True, + title_options=title_options, + outline=outline_sections + ) + + + async def refine_outline(self, request: BlogOutlineRefineRequest) -> BlogOutlineResponse: + """ + Refine outline with HITL (Human-in-the-Loop) operations + Supports add, remove, move, merge, rename operations + """ + outline = request.outline.copy() + operation = request.operation.lower() + section_id = request.section_id + payload = request.payload or {} + + try: + if operation == 'add': + # Add new section + new_section = BlogOutlineSection( + id=f"s{len(outline) + 1}", + heading=payload.get('heading', 'New Section'), + subheadings=payload.get('subheadings', []), + key_points=payload.get('key_points', []), + references=[], + target_words=payload.get('target_words', 300) + ) + outline.append(new_section) + logger.info(f"Added new section: {new_section.heading}") + + elif operation == 'remove' and section_id: + # Remove section + outline = [s for s in outline if s.id != section_id] + logger.info(f"Removed section: {section_id}") + + elif operation == 'rename' and section_id: + # Rename section + for section in outline: + if section.id == section_id: + section.heading = payload.get('heading', section.heading) + break + logger.info(f"Renamed section {section_id} to: {payload.get('heading')}") + + elif operation == 'move' and section_id: + # Move section (reorder) + direction = payload.get('direction', 'down') # 'up' or 'down' + current_index = next((i for i, s in enumerate(outline) if s.id == section_id), -1) + + if current_index != -1: + if direction == 'up' and current_index > 0: + outline[current_index], outline[current_index - 1] = outline[current_index - 1], outline[current_index] + elif direction == 'down' and current_index < len(outline) - 1: + outline[current_index], outline[current_index + 1] = outline[current_index + 1], outline[current_index] + logger.info(f"Moved section {section_id} {direction}") + + elif operation == 'merge' and section_id: + # Merge with next section + current_index = next((i for i, s in enumerate(outline) if s.id == section_id), -1) + if current_index != -1 and current_index < len(outline) - 1: + current_section = outline[current_index] + next_section = outline[current_index + 1] + + # Merge sections + current_section.heading = f"{current_section.heading} & {next_section.heading}" + current_section.subheadings.extend(next_section.subheadings) + current_section.key_points.extend(next_section.key_points) + current_section.references.extend(next_section.references) + current_section.target_words = (current_section.target_words or 0) + (next_section.target_words or 0) + + # Remove the next section + outline.pop(current_index + 1) + logger.info(f"Merged section {section_id} with next section") + + elif operation == 'update' and section_id: + # Update section details + for section in outline: + if section.id == section_id: + if 'heading' in payload: + section.heading = payload['heading'] + if 'subheadings' in payload: + section.subheadings = payload['subheadings'] + if 'key_points' in payload: + section.key_points = payload['key_points'] + if 'target_words' in payload: + section.target_words = payload['target_words'] + break + logger.info(f"Updated section {section_id}") + + # Reassign IDs to maintain order + for i, section in enumerate(outline): + section.id = f"s{i+1}" + + return BlogOutlineResponse( + success=True, + title_options=["Refined Outline"], + outline=outline + ) + + except Exception as e: + logger.error(f"Outline refinement failed: {e}") + return BlogOutlineResponse( + success=False, + title_options=["Error"], + outline=request.outline + ) + + async def generate_section(self, request: BlogSectionRequest) -> BlogSectionResponse: + # TODO: Generate section markdown incorporating references and persona/tone + md = f"## {request.section.heading}\n\nThis section content will be generated here.\n" + return BlogSectionResponse(success=True, markdown=md, citations=request.section.references) + + async def optimize_section(self, request: BlogOptimizeRequest) -> BlogOptimizeResponse: + # TODO: Run readability/EEAT optimization and return diff + return BlogOptimizeResponse(success=True, optimized=request.content, diff_preview=None) + + async def hallucination_check(self, payload: Dict[str, Any]) -> Dict[str, Any]: + """Run hallucination detection on provided text using existing detector service.""" + text = str(payload.get("text", "") or "").strip() + if not text: + return {"success": False, "error": "No text provided"} + + # Prefer direct service use over HTTP proxy + try: + from services.hallucination_detector import HallucinationDetector + detector = HallucinationDetector() + result = await detector.detect_hallucinations(text) + + # Serialize dataclass-like result to dict + claims = [] + for c in result.claims: + claims.append({ + "text": c.text, + "confidence": c.confidence, + "assessment": c.assessment, + "supporting_sources": c.supporting_sources, + "refuting_sources": c.refuting_sources, + "reasoning": c.reasoning, + }) + + return { + "success": True, + "overall_confidence": result.overall_confidence, + "total_claims": result.total_claims, + "supported_claims": result.supported_claims, + "refuted_claims": result.refuted_claims, + "insufficient_claims": result.insufficient_claims, + "timestamp": result.timestamp, + "claims": claims, + } + except Exception as e: + return {"success": False, "error": str(e)} + + async def seo_analyze(self, request: BlogSEOAnalyzeRequest) -> BlogSEOAnalyzeResponse: + """Wrap existing SEO tools to produce unified analysis for blog content.""" + from services.seo_tools.on_page_seo_service import OnPageSEOService + from services.seo_tools.image_alt_service import ImageAltService + from services.seo_tools.content_strategy_service import ContentStrategyService + + content = request.content or "" + target_keywords = request.keywords or [] + + # On-page analysis (treat content as a virtual URL/document for now) + on_page = OnPageSEOService() + on_page_result = await on_page.analyze_on_page_seo(url="about:blank", target_keywords=target_keywords) + + # Image alt coverage (placeholder: no images in raw content yet) + try: + image_alt_service = ImageAltService() + image_alt_status = {"total_images": 0, "missing_alt": 0} + except Exception: + image_alt_status = {"total_images": 0, "missing_alt": 0} + + # Strategy hints (keywords/topics) + try: + strategy = ContentStrategyService() + strategy_hints = await strategy.analyze_content_topics(content=content) + except Exception: + strategy_hints = {"topics": [], "gaps": []} + + # Lightweight markdown parsing for headings/links/keywords + import re + content_text = content or "" + words = re.findall(r"[A-Za-z0-9']+", content_text) + total_words = max(len(words), 1) + heading_lines = content_text.splitlines() + h1 = sum(1 for ln in heading_lines if ln.startswith('# ')) + h2 = sum(1 for ln in heading_lines if ln.startswith('## ')) + h3 = sum(1 for ln in heading_lines if ln.startswith('### ')) + md_links = re.findall(r"\[([^\]]+)\]\(([^)]+)\)", content_text) + external_links = [u for (_t, u) in md_links if u.startswith('http')] + + # Keyword density + density_map: Dict[str, Any] = {"target_keywords": target_keywords} + for kw in target_keywords: + try: + occurrences = len(re.findall(re.escape(kw), content_text, flags=re.IGNORECASE)) + except re.error: + occurrences = 0 + density_map[kw] = { + "occurrences": occurrences, + "density": round(occurrences / total_words, 4) + } + + # Build unified response + recommendations: List[str] = [] + if isinstance(on_page_result.get("recommendations"), list): + recommendations.extend(on_page_result["recommendations"]) + if strategy_hints.get("gaps"): + recommendations.append("Cover missing topics: " + ", ".join(strategy_hints["gaps"])) + if not external_links: + recommendations.append("Add at least one credible external link to authoritative sources.") + if h2 < 2: + recommendations.append("Increase number of H2 sections for better structure.") + + # Internal link suggestions: generate anchors for H2s and propose cross-links + def to_anchor(h: str) -> str: + import re + a = re.sub(r"[^a-z0-9\s-]", "", h.lower()) + a = re.sub(r"\s+", "-", a).strip('-') + return a + h2_headings = [ln[3:].strip() for ln in heading_lines if ln.startswith('## ')] + anchors = [to_anchor(h) for h in h2_headings] + internal_link_suggestions = [] + for i in range(len(anchors)-1): + internal_link_suggestions.append({ + "from": h2_headings[i], + "to": h2_headings[i+1], + "anchor": f"#{anchors[i+1]}", + "suggestion": f"Add internal link from '{h2_headings[i]}' to '{h2_headings[i+1]}'" + }) + + return BlogSEOAnalyzeResponse( + success=True, + seo_score=float(on_page_result.get("overall_score", 75)), + density=density_map, + structure={ + **on_page_result.get("heading_structure", {}), + "markdown_headings": {"h1": h1, "h2": h2, "h3": h3}, + "links": {"total": len(md_links), "external": len(external_links)} + }, + readability=on_page_result.get("content_analysis", {}), + link_suggestions=([{"suggestion": "Add external citation links for key claims."}] if not external_links else []) + internal_link_suggestions, + image_alt_status=image_alt_status, + recommendations=recommendations, + ) + + async def seo_metadata(self, request: BlogSEOMetadataRequest) -> BlogSEOMetadataResponse: + # TODO: Generate SEO metadata using existing services + return BlogSEOMetadataResponse( + success=True, + title_options=[request.title or "Generated SEO Title"], + meta_descriptions=["Compelling meta description..."], + open_graph={"title": request.title or "OG Title", "image": ""}, + twitter_card={"card": "summary_large_image"}, + schema={"@type": "Article"}, + ) + + async def publish(self, request: BlogPublishRequest) -> BlogPublishResponse: + # TODO: Call Wix/WordPress adapters to publish + return BlogPublishResponse(success=True, platform=request.platform, url="https://example.com/post") + + diff --git a/backend/services/llm_providers/__pycache__/gemini_provider.cpython-313.pyc b/backend/services/llm_providers/__pycache__/gemini_provider.cpython-313.pyc index 3974b0884e365f9d6fd5c8f92faaedf22119d2bf..1433b72eed016a1f3e5d457f554dd37be872f1ac 100644 GIT binary patch delta 1123 zcmbu8ZA@EL7{|}Kx3^qNdkZ#{7lV|fsGV5A(rs)~C@+QJL~LoIX^Aas2`r^u&TTQ0 z;Rq&}Eykfw=F2Dcl57&QEm(CDUy?>_eT!*`G3FBEht13n#E{?zKkht(PGaIG&rN>k zfBxq=&pqed=YEl=*Vd@AV=@^CZ(CQsntUO=su-MtRR=|LZPw*{pEfyg4qMO|FuH|Z z{n&0tqAlqA4?v{tP>ab;cWv7}Z!ctDXD1l;eu<$MTcDh zDQWN;Cg=p|6dT9{Z6qOQX>A#awi1#w{X1KzB4|>GOW2$WOj?g3UNB7Ur)6-mkTUO2)&l-zW-k;>2Un;7Lwf#l2uPFQe{_7bEhkHH3 z2!&j4B$ePv7TSGQa?{q=L2}iU%Uq3sx~^Bp2kQ;B$PRxi?64D5uPtKYzY3U&yc8;B1OAHu=0M<2;@sY$$$(klB1?T-(BJGc3=`g%)hUZ|o tbcL{b)c8MX@>A2PSSAtoushkd=sVOhMQP)XNO;w33#hlB7h!XJ{4S1}1g-!8 delta 2564 zcmbtWZA?>F7``991?k7_xWyK*^dgjkVgUisDkzGee6)rRL_U-PWwMpRZmZ7Di8EQI z?nCix0k>>p$zpJeQ3DII>6FB6MnP`_8>C~|{+jHAM1CwW3p;P?g^4W7vP<%u=e*~6 zpZC1)OR~A0yiKVkrA6q%o2^6rbtYPa`FPK-ROMGFKE}7fd%l;U(4g4p zCrYKGL^DTbq2C>Ga*wJ?Rhf;l(zsYo63u7VVt-X-E(ocxC`0>{NDd-LjDwL89+jQJ ze0iAT)I2awdfJ!?1-Q&|9qTE`0M zkS81~90o_cg+gy;UMQh#*By)}sxYdRY$ft(BhgAG{@r_%WVEnG5KjD(J?h0pnjHEn z^^@<|5gU%+UKvN6jDWIU%1Gdn>Oyt$KzGBl`+=EOKDYVsnbky zsZwC&b~yO|Q$QMHTH-*?+FKD_{=5=bdz+_?7hK-X4v*KxAK`t6J6-uEFJ}9l z-hDpTOTL9&r&I8{TJT=T!#54e!+ZboMJ^V|vhsfY;&@n(PgYlX+dR*q2&=ivRP1!S z@rG}5How68I_B>Za^WEbpZe*>#zubxhUdK6qBwRJ8Y#-TgI}500A(ZbjUV6f0}Tx75wjS$7P^8RD z*AC`fjl97Qv*X!2#I-v`ed&ZuSvD(2UvFB|waC9;f5~vkAf@UzPbjxcaq&I*-T9MT zN`Oll=Tc7;&BzIj_H@_DuHFNatSP{nrZ`=XwcCm|O>(OO+^YT!lU#0q%bkih_K|&5 z@A~edpCx*x2*lX0FJ_W62g*1zsOY}v-VOLj7vJOW_M;|{ zYRt1y1Rk97lv0dYHxZdP6>Gh{HNe`%Nc$hNJ1NBG7nB_(39TNSIrBq;0t?OZ9_3l3 zXe_?@;>~8!P&%P0n@ZYxGwWuOm{=^<)Qb&Haj#RXX$t6?ztc27nqeUA(X1NT^BcQ9 zz;Ez)PKAjW;>&1aL`PyeqNjkzZHM@`>^2H7ccNp;dE!oL9OifFsB!~+S5?TA>*>*G zIS!5L85|ll(7<_Z#Y%cKC#k|fk72`=^q5|T<6{N}_)5@>nWF4EdMqQ+WQ(KkX-T}f z7pDR=o9xl_eI-QhM>BTaKtjPaMkyS{_Y}GS{OH$hKQaB74h;l~*a-G@h@QZZ#-vex z1L`iErV{062BHBe(8mRG$6;RFEqS0#-K%6!5B zSCDCSy1g!81jm9h&jGhPNLqx$up`$9pMv}|kSoI%y9j|$=kEgZqvq;#T@MH};ZOMI z5WWI%6`ij(rwn5nWbhY|&ntWZ;V%KM0n`Ir2lxs-tS(^gVY+)@-R>Vr#eIm100ES+ z=Lh*Qpy$xso~`7|XlrfGYWSE7FmVA|6d?5iAsB$eFH10TQ+r3t0k^9__+{YZ+8&ZC Wp~%FCG(qhmXDHw^&&p6)ebZksqEmJN diff --git a/backend/services/llm_providers/gemini_grounded_provider.py b/backend/services/llm_providers/gemini_grounded_provider.py index 2e627201..f0266de1 100644 --- a/backend/services/llm_providers/gemini_grounded_provider.py +++ b/backend/services/llm_providers/gemini_grounded_provider.py @@ -43,7 +43,7 @@ class GeminiGroundedProvider: # Initialize the Gemini client with timeout configuration self.client = genai.Client(api_key=self.api_key) - self.timeout = 30 # 30 second timeout for API calls + self.timeout = 60 # 60 second timeout for API calls (increased for research) logger.info("โœ… Gemini Grounded Provider initialized with native Google Search grounding") async def generate_grounded_content( @@ -239,8 +239,8 @@ class GeminiGroundedProvider: logger.info(f"Search queries: {grounding_metadata.web_search_queries}") # Extract sources from grounding chunks + sources = [] # Initialize sources list if hasattr(grounding_metadata, 'grounding_chunks') and grounding_metadata.grounding_chunks: - sources = [] for i, chunk in enumerate(grounding_metadata.grounding_chunks): logger.info(f"Chunk {i} attributes: {dir(chunk)}") if hasattr(chunk, 'web'): @@ -251,15 +251,29 @@ class GeminiGroundedProvider: 'type': 'web' } sources.append(source) - result['sources'] = sources - logger.info(f"Extracted {len(sources)} sources") + logger.info(f"Extracted {len(sources)} sources from grounding chunks") else: - logger.error("โŒ CRITICAL: No grounding chunks found in response") - logger.error(f"Grounding metadata structure: {dir(grounding_metadata)}") - if hasattr(grounding_metadata, 'grounding_chunks'): - logger.error(f"Grounding chunks type: {type(grounding_metadata.grounding_chunks)}") - logger.error(f"Grounding chunks value: {grounding_metadata.grounding_chunks}") - raise ValueError("No grounding chunks found - grounding is not working properly") + logger.warning("โš ๏ธ No grounding chunks found - this is normal for some queries") + logger.info(f"Grounding metadata available fields: {[attr for attr in dir(grounding_metadata) if not attr.startswith('_')]}") + + # Check if we have search queries - this means Google Search was triggered + if hasattr(grounding_metadata, 'web_search_queries') and grounding_metadata.web_search_queries: + logger.info(f"โœ… Google Search was triggered with {len(grounding_metadata.web_search_queries)} queries") + # Create sources based on search queries + for i, query in enumerate(grounding_metadata.web_search_queries[:5]): # Limit to 5 sources + source = { + 'index': i, + 'title': f"Search: {query}", + 'url': f"https://www.google.com/search?q={query.replace(' ', '+')}", + 'type': 'search_query', + 'query': query + } + sources.append(source) + logger.info(f"Created {len(sources)} sources from search queries") + else: + logger.warning("โš ๏ธ No search queries found either - grounding may not have been triggered") + + result['sources'] = sources # Extract citations from grounding supports if hasattr(grounding_metadata, 'grounding_supports') and grounding_metadata.grounding_supports: @@ -278,12 +292,37 @@ class GeminiGroundedProvider: result['citations'] = citations logger.info(f"Extracted {len(citations)} citations") else: - logger.error("โŒ CRITICAL: No grounding supports found in response") - logger.error(f"Grounding metadata structure: {dir(grounding_metadata)}") - if hasattr(grounding_metadata, 'grounding_supports'): - logger.error(f"Grounding supports type: {type(grounding_metadata.grounding_supports)}") - logger.error(f"Grounding supports value: {grounding_metadata.grounding_supports}") - raise ValueError("No grounding supports found - grounding is not working properly") + logger.warning("โš ๏ธ No grounding supports found - this is normal when no web sources are retrieved") + # Create basic citations from the content if we have sources + if sources: + citations = [] + for i, source in enumerate(sources[:3]): # Limit to 3 citations + citation = { + 'type': 'reference', + 'start_index': 0, + 'end_index': 0, + 'text': f"Source {i+1}", + 'source_indices': [i], + 'reference': f"Source {i+1}", + 'source': source + } + citations.append(citation) + result['citations'] = citations + logger.info(f"Created {len(citations)} basic citations from sources") + else: + result['citations'] = [] + logger.info("No citations created - no sources available") + + # Extract search entry point for UI display + if hasattr(grounding_metadata, 'search_entry_point') and grounding_metadata.search_entry_point: + if hasattr(grounding_metadata.search_entry_point, 'rendered_content'): + result['search_widget'] = grounding_metadata.search_entry_point.rendered_content + logger.info("โœ… Extracted search widget HTML for UI display") + + # Extract search queries for reference + if hasattr(grounding_metadata, 'web_search_queries') and grounding_metadata.web_search_queries: + result['search_queries'] = grounding_metadata.web_search_queries + logger.info(f"โœ… Extracted {len(grounding_metadata.web_search_queries)} search queries") logger.info(f"โœ… Successfully extracted {len(result['sources'])} sources and {len(result['citations'])} citations from grounding metadata") logger.info(f"Sources: {result['sources']}") diff --git a/backend/services/llm_providers/gemini_provider.py b/backend/services/llm_providers/gemini_provider.py index 4a1e7a14..0480e68e 100644 --- a/backend/services/llm_providers/gemini_provider.py +++ b/backend/services/llm_providers/gemini_provider.py @@ -389,43 +389,13 @@ def gemini_structured_json_response(prompt, schema, temperature=0.7, top_p=0.9, config=generation_config, ) - # Add debugging for response - logger.info("Gemini response | type=%s | has_text=%s | has_parsed=%s", - type(response), hasattr(response, 'text'), hasattr(response, 'parsed')) - - if hasattr(response, 'text'): - logger.info(f"Gemini response.text: {repr(response.text)}") - if hasattr(response, 'parsed'): - logger.info(f"Gemini response.parsed: {repr(response.parsed)}") - # According to the documentation, we should use response.parsed for structured output if hasattr(response, 'parsed') and response.parsed is not None: logger.info("Using response.parsed for structured output") return response.parsed - # Fallback to text if parsed is not available - if hasattr(response, 'text') and response.text: - logger.info("Falling back to response.text parsing") - text = response.text.strip() - - # Strip markdown code fences if present - if text.startswith('```'): - if text.lower().startswith('```json'): - text = text[7:] - else: - text = text[3:] - if text.endswith('```'): - text = text[:-3] - text = text.strip() - - try: - return json.loads(text) - except json.JSONDecodeError as e: - logger.error(f"Failed to parse response.text as JSON: {e}") - return {"error": f"Failed to parse JSON response: {e}", "raw_response": text[:500]} - - logger.error("No valid response content found") - return {"error": "No valid response content found", "raw_response": ""} + logger.error("No valid structured response content found") + return {"error": "No valid structured response content found"} except ValueError as e: # API key related errors diff --git a/backend/services/research/google_search_service.py b/backend/services/research/google_search_service.py index 1112c3d6..50fcea15 100644 --- a/backend/services/research/google_search_service.py +++ b/backend/services/research/google_search_service.py @@ -45,8 +45,7 @@ class GoogleSearchService: self.base_url = "https://www.googleapis.com/customsearch/v1" if not self.api_key or not self.search_engine_id: - logger.warning("Google Search API credentials not configured. Service will use fallback methods.") - self.enabled = False + raise ValueError("Google Search API credentials not configured. Please set GOOGLE_SEARCH_API_KEY and GOOGLE_SEARCH_ENGINE_ID environment variables.") else: self.enabled = True logger.info("Google Search Service initialized successfully") @@ -69,8 +68,7 @@ class GoogleSearchService: List of search results with credibility scoring """ if not self.enabled: - logger.warning("Google Search Service not enabled, using fallback research") - return await self._fallback_research(topic, industry) + raise RuntimeError("Google Search Service is not enabled. Please configure API credentials.") try: # Construct industry-specific search query @@ -99,7 +97,7 @@ class GoogleSearchService: except Exception as e: logger.error(f"Google search failed: {str(e)}") - return await self._fallback_research(topic, industry) + raise RuntimeError(f"Google search failed: {str(e)}") def _build_search_query(self, topic: str, industry: str) -> str: """ @@ -465,45 +463,6 @@ class GoogleSearchService: "statistics": statistics } - async def _fallback_research(self, topic: str, industry: str) -> Dict[str, Any]: - """ - Fallback research method when Google Search is not available. - - Args: - topic: The research topic - industry: The industry context - - Returns: - Fallback research data - """ - logger.info(f"Using fallback research for {topic} in {industry}") - - return { - "sources": [ - { - "title": f"Industry insights on {topic} in {industry}", - "url": f"https://example.com/{topic.lower().replace(' ', '-')}", - "content": f"Professional insights and trends related to {topic} in the {industry} sector...", - "relevance_score": 0.8, - "credibility_score": 0.6, - "domain_authority": 0.5, - "source_type": "general", - "grounding_enabled": False - } - ], - "key_insights": [ - f"{topic} is transforming {industry} operations", - f"Industry leaders are investing in {topic}", - f"Expected growth in {topic} adoption within {industry}" - ], - "statistics": [ - f"85% of {industry} companies are exploring {topic}", - f"Investment in {topic} increased by 40% this year" - ], - "grounding_enabled": False, - "search_query": f"{topic} {industry} trends", - "timestamp": datetime.utcnow().isoformat() - } async def test_api_connection(self) -> Dict[str, Any]: """ @@ -513,11 +472,7 @@ class GoogleSearchService: Test results and status information """ if not self.enabled: - return { - "status": "disabled", - "message": "Google Search API credentials not configured", - "enabled": False - } + raise RuntimeError("Google Search Service is not enabled. Please configure API credentials.") try: # Perform a simple test search diff --git a/backend/start_alwrity_backend.py b/backend/start_alwrity_backend.py index 1156e5e6..5c344a4b 100644 --- a/backend/start_alwrity_backend.py +++ b/backend/start_alwrity_backend.py @@ -91,6 +91,37 @@ def setup_monitoring_tables(): print(" Monitoring will be disabled. Continuing startup...") return True # Don't fail startup for monitoring issues +def setup_billing_tables(): + """Set up billing and subscription database tables.""" + print("๐Ÿ’ณ Setting up billing and subscription tables...") + + try: + # Import and run the billing table creation + sys.path.append(str(Path(__file__).parent)) + from scripts.create_billing_tables import create_billing_tables, check_existing_tables + from services.database import DATABASE_URL + from sqlalchemy import create_engine + + # Create engine to check existing tables + engine = create_engine(DATABASE_URL, echo=False) + + # Check existing tables + if not check_existing_tables(engine): + print("โœ… Billing tables already exist, skipping creation") + return True + + if create_billing_tables(): + print("โœ… Billing and subscription tables created successfully!") + return True + else: + print("โš ๏ธ Warning: Failed to create billing tables, continuing anyway...") + return True # Don't fail startup for billing issues + + except Exception as e: + print(f"โš ๏ธ Warning: Could not set up billing tables: {e}") + print(" Billing system will be disabled. Continuing startup...") + return True # Don't fail startup for billing issues + def setup_monitoring_middleware(): """Set up monitoring middleware in app.py if not already present.""" print("๐Ÿ” Setting up API monitoring middleware...") @@ -168,7 +199,8 @@ def check_dependencies(): 'openai', 'google.generativeai', 'anthropic', - 'mistralai' + 'mistralai', + 'sqlalchemy' ] missing_packages = [] @@ -212,6 +244,9 @@ def setup_environment(): setup_monitoring_tables() setup_monitoring_middleware() + # Set up billing and subscription system + setup_billing_tables() + print("โœ… Environment setup complete") def verify_persona_tables(): @@ -238,6 +273,35 @@ def verify_persona_tables(): print(f"โš ๏ธ Warning: Could not verify persona tables: {e}") return False +def verify_billing_tables(): + """Verify that billing and subscription tables exist and are accessible.""" + print("๐Ÿ” Verifying billing and subscription tables...") + try: + from services.database import get_db_session + from models.subscription_models import ( + SubscriptionPlan, UserSubscription, APIUsageLog, + UsageSummary, APIProviderPricing, UsageAlert + ) + + session = get_db_session() + if session: + # Try to query all billing tables to verify they exist + session.query(SubscriptionPlan).first() + session.query(UserSubscription).first() + session.query(APIUsageLog).first() + session.query(UsageSummary).first() + session.query(APIProviderPricing).first() + session.query(UsageAlert).first() + session.close() + print("โœ… All billing and subscription tables verified successfully") + return True + else: + print("โš ๏ธ Warning: Could not get database session") + return False + except Exception as e: + print(f"โš ๏ธ Warning: Could not verify billing tables: {e}") + return False + def start_backend(enable_reload=False): """Start the backend server.""" print("๐Ÿš€ Starting ALwrity Backend...") @@ -276,11 +340,16 @@ def start_backend(enable_reload=False): # Verify persona tables exist verify_persona_tables() + # Verify billing tables exist + verify_billing_tables() + print("\n๐ŸŒ Backend is starting...") print(" ๐Ÿ“– API Documentation: http://localhost:8000/api/docs") print(" ๐Ÿ” Health Check: http://localhost:8000/health") print(" ๐Ÿ“Š ReDoc: http://localhost:8000/api/redoc") print(" ๐Ÿ“ˆ API Monitoring: http://localhost:8000/api/content-planning/monitoring/health") + print(" ๐Ÿ’ณ Billing Dashboard: http://localhost:8000/api/subscription/plans") + print(" ๐Ÿ“Š Usage Tracking: http://localhost:8000/api/subscription/usage/demo") print("\nโน๏ธ Press Ctrl+C to stop the server") print("=" * 60) print("\n๐Ÿ’ก Usage:") diff --git a/backend/test_detailed.py b/backend/test_detailed.py new file mode 100644 index 00000000..9426ff62 --- /dev/null +++ b/backend/test_detailed.py @@ -0,0 +1,43 @@ +import requests +import json + +# Test the research endpoint with more detailed output +url = "http://localhost:8000/api/blog/research" +payload = { + "keywords": ["AI content generation", "blog writing"], + "topic": "ALwrity content generation", + "industry": "Technology", + "target_audience": "content creators" +} + +try: + print("Sending request to research endpoint...") + response = requests.post(url, json=payload, timeout=60) + print(f"Status Code: {response.status_code}") + + if response.status_code == 200: + data = response.json() + print("\n=== FULL RESPONSE ===") + print(json.dumps(data, indent=2)) + + # Check if we got the expected fields + expected_fields = ['success', 'sources', 'keyword_analysis', 'competitor_analysis', 'suggested_angles', 'search_widget', 'search_queries'] + print(f"\n=== FIELD ANALYSIS ===") + for field in expected_fields: + value = data.get(field) + if field == 'sources': + print(f"{field}: {len(value) if value else 0} items") + elif field == 'search_queries': + print(f"{field}: {len(value) if value else 0} items") + elif field == 'search_widget': + print(f"{field}: {'Present' if value else 'Missing'}") + else: + print(f"{field}: {type(value).__name__} - {str(value)[:100]}...") + + else: + print(f"Error Response: {response.text}") + +except Exception as e: + print(f"Request failed: {e}") + import traceback + traceback.print_exc() diff --git a/backend/test_gemini_direct.py b/backend/test_gemini_direct.py new file mode 100644 index 00000000..7084f5e4 --- /dev/null +++ b/backend/test_gemini_direct.py @@ -0,0 +1,60 @@ +import asyncio +from services.llm_providers.gemini_grounded_provider import GeminiGroundedProvider + +async def test_gemini_direct(): + gemini = GeminiGroundedProvider() + + prompt = """ + Research the topic "AI content generation" in the Technology industry for content creators audience. Provide a comprehensive analysis including: + + 1. Current trends and insights (2024-2025) + 2. Key statistics and data points with sources + 3. Industry expert opinions and quotes + 4. Recent developments and news + 5. Market analysis and forecasts + 6. Best practices and case studies + 7. Keyword analysis: primary, secondary, and long-tail opportunities + 8. Competitor analysis: top players and content gaps + 9. Content angle suggestions: 5 compelling angles for blog posts + + Focus on factual, up-to-date information from credible sources. + Include specific data points, percentages, and recent developments. + Structure your response with clear sections for each analysis area. + """ + + try: + result = await gemini.generate_grounded_content( + prompt=prompt, + content_type="research", + max_tokens=2000 + ) + + print("=== GEMINI RESULT ===") + print(f"Type: {type(result)}") + print(f"Keys: {list(result.keys()) if isinstance(result, dict) else 'Not a dict'}") + + if isinstance(result, dict): + print(f"Sources count: {len(result.get('sources', []))}") + print(f"Search queries count: {len(result.get('search_queries', []))}") + print(f"Has search widget: {bool(result.get('search_widget'))}") + print(f"Content length: {len(result.get('content', ''))}") + + print("\n=== FIRST SOURCE ===") + sources = result.get('sources', []) + if sources: + print(f"Source: {sources[0]}") + + print("\n=== SEARCH QUERIES (First 3) ===") + queries = result.get('search_queries', []) + for i, query in enumerate(queries[:3]): + print(f"{i+1}. {query}") + else: + print(f"Result is not a dict: {result}") + + except Exception as e: + print(f"Error: {e}") + import traceback + traceback.print_exc() + +if __name__ == "__main__": + asyncio.run(test_gemini_direct()) diff --git a/backend/test_research.py b/backend/test_research.py new file mode 100644 index 00000000..e2f18301 --- /dev/null +++ b/backend/test_research.py @@ -0,0 +1,58 @@ +import requests +import json + +# Test the research endpoint +url = "http://localhost:8000/api/blog/research" +payload = { + "keywords": ["AI content generation", "blog writing"], + "topic": "ALwrity content generation", + "industry": "Technology", + "target_audience": "content creators" +} + +try: + response = requests.post(url, json=payload) + print(f"Status Code: {response.status_code}") + print(f"Response Headers: {dict(response.headers)}") + + if response.status_code == 200: + data = response.json() + print("\n=== RESEARCH RESPONSE ===") + print(f"Success: {data.get('success')}") + print(f"Sources Count: {len(data.get('sources', []))}") + print(f"Search Queries Count: {len(data.get('search_queries', []))}") + print(f"Has Search Widget: {bool(data.get('search_widget'))}") + print(f"Suggested Angles Count: {len(data.get('suggested_angles', []))}") + + print("\n=== SOURCES ===") + for i, source in enumerate(data.get('sources', [])[:3]): + print(f"Source {i+1}: {source.get('title', 'No title')}") + print(f" URL: {source.get('url', 'No URL')}") + print(f" Type: {source.get('type', 'Unknown')}") + + print("\n=== SEARCH QUERIES (First 5) ===") + for i, query in enumerate(data.get('search_queries', [])[:5]): + print(f"{i+1}. {query}") + + print("\n=== SUGGESTED ANGLES ===") + for i, angle in enumerate(data.get('suggested_angles', [])[:3]): + print(f"{i+1}. {angle}") + + print("\n=== KEYWORD ANALYSIS ===") + kw_analysis = data.get('keyword_analysis', {}) + print(f"Primary: {kw_analysis.get('primary', [])}") + print(f"Secondary: {kw_analysis.get('secondary', [])}") + print(f"Search Intent: {kw_analysis.get('search_intent', 'Unknown')}") + + print("\n=== SEARCH WIDGET (First 200 chars) ===") + widget = data.get('search_widget', '') + if widget: + print(widget[:200] + "..." if len(widget) > 200 else widget) + else: + print("No search widget provided") + + else: + print(f"Error: {response.text}") + +except Exception as e: + print(f"Request failed: {e}") diff --git a/backend/test_research_analysis.py b/backend/test_research_analysis.py new file mode 100644 index 00000000..df76c75c --- /dev/null +++ b/backend/test_research_analysis.py @@ -0,0 +1,115 @@ +import requests +import json +from datetime import datetime + +# Test the research endpoint and capture full response +url = "http://localhost:8000/api/blog/research" +payload = { + "keywords": ["AI content generation", "blog writing"], + "topic": "ALwrity content generation", + "industry": "Technology", + "target_audience": "content creators" +} + +try: + print("Sending request to research endpoint...") + response = requests.post(url, json=payload, timeout=120) + print(f"Status Code: {response.status_code}") + + if response.status_code == 200: + data = response.json() + + # Create analysis file with timestamp + timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") + filename = f"research_analysis_{timestamp}.json" + + # Save full response to file + with open(filename, 'w', encoding='utf-8') as f: + json.dump(data, f, indent=2, ensure_ascii=False) + + print(f"\n=== RESEARCH RESPONSE ANALYSIS ===") + print(f"โœ… Full response saved to: {filename}") + print(f"Success: {data.get('success')}") + print(f"Sources Count: {len(data.get('sources', []))}") + print(f"Search Queries Count: {len(data.get('search_queries', []))}") + print(f"Has Search Widget: {bool(data.get('search_widget'))}") + print(f"Suggested Angles Count: {len(data.get('suggested_angles', []))}") + + print(f"\n=== SOURCES ANALYSIS ===") + sources = data.get('sources', []) + for i, source in enumerate(sources[:5]): # Show first 5 + print(f"Source {i+1}: {source.get('title', 'No title')}") + print(f" URL: {source.get('url', 'No URL')[:100]}...") + print(f" Type: {source.get('type', 'Unknown')}") + print(f" Credibility: {source.get('credibility_score', 'N/A')}") + + print(f"\n=== SEARCH QUERIES ANALYSIS ===") + queries = data.get('search_queries', []) + print(f"Total queries: {len(queries)}") + for i, query in enumerate(queries[:10]): # Show first 10 + print(f"{i+1:2d}. {query}") + + print(f"\n=== SEARCH WIDGET ANALYSIS ===") + widget = data.get('search_widget', '') + if widget: + print(f"Widget HTML length: {len(widget)} characters") + print(f"Contains Google branding: {'Google' in widget}") + print(f"Contains search chips: {'chip' in widget}") + print(f"Contains carousel: {'carousel' in widget}") + print(f"First 200 chars: {widget[:200]}...") + else: + print("No search widget provided") + + print(f"\n=== KEYWORD ANALYSIS ===") + kw_analysis = data.get('keyword_analysis', {}) + print(f"Primary keywords: {kw_analysis.get('primary', [])}") + print(f"Secondary keywords: {kw_analysis.get('secondary', [])}") + print(f"Long-tail keywords: {kw_analysis.get('long_tail', [])}") + print(f"Search intent: {kw_analysis.get('search_intent', 'Unknown')}") + print(f"Difficulty score: {kw_analysis.get('difficulty', 'N/A')}") + + print(f"\n=== SUGGESTED ANGLES ===") + angles = data.get('suggested_angles', []) + for i, angle in enumerate(angles): + print(f"{i+1}. {angle}") + + print(f"\n=== UI REPRESENTATION RECOMMENDATIONS ===") + print("Based on the response, here's what should be displayed in the Editor UI:") + print(f"1. Research Sources Panel: {len(sources)} real web sources") + print(f"2. Search Widget: Interactive Google search chips ({len(queries)} queries)") + print(f"3. Keyword Analysis: Primary/Secondary/Long-tail breakdown") + print(f"4. Content Angles: {len(angles)} suggested blog post angles") + print(f"5. Search Queries: {len(queries)} research queries for reference") + + # Additional analysis for UI components + print(f"\n=== UI COMPONENT BREAKDOWN ===") + + # Sources for UI + print("SOURCES FOR UI:") + for i, source in enumerate(sources[:3]): + print(f" - {source.get('title')} (Credibility: {source.get('credibility_score')})") + + # Search widget for UI + print(f"\nSEARCH WIDGET FOR UI:") + print(f" - HTML length: {len(widget)} chars") + print(f" - Can be embedded directly in UI") + print(f" - Contains {len(queries)} search suggestions") + + # Keywords for UI + print(f"\nKEYWORDS FOR UI:") + print(f" - Primary: {', '.join(kw_analysis.get('primary', []))}") + print(f" - Secondary: {', '.join(kw_analysis.get('secondary', []))}") + print(f" - Long-tail: {', '.join(kw_analysis.get('long_tail', []))}") + + # Angles for UI + print(f"\nCONTENT ANGLES FOR UI:") + for i, angle in enumerate(angles[:3]): + print(f" - {angle}") + + else: + print(f"Error: {response.text}") + +except Exception as e: + print(f"Request failed: {e}") + import traceback + traceback.print_exc() diff --git a/backend/verify_billing_setup.py b/backend/verify_billing_setup.py new file mode 100644 index 00000000..d9647b42 --- /dev/null +++ b/backend/verify_billing_setup.py @@ -0,0 +1,280 @@ +""" +Comprehensive verification script for billing and subscription system setup. +Checks that all files are created, tables exist, and the system is properly integrated. +""" + +import os +import sys +from pathlib import Path + +def check_file_exists(file_path, description): + """Check if a file exists and report status.""" + if os.path.exists(file_path): + print(f"โœ… {description}: {file_path}") + return True + else: + print(f"โŒ {description}: {file_path} - NOT FOUND") + return False + +def check_file_content(file_path, search_terms, description): + """Check if file contains expected content.""" + try: + with open(file_path, 'r', encoding='utf-8') as f: + content = f.read() + + missing_terms = [] + for term in search_terms: + if term not in content: + missing_terms.append(term) + + if not missing_terms: + print(f"โœ… {description}: All expected content found") + return True + else: + print(f"โŒ {description}: Missing content - {missing_terms}") + return False + except Exception as e: + print(f"โŒ {description}: Error reading file - {e}") + return False + +def check_database_tables(): + """Check if billing database tables exist.""" + print("\n๐Ÿ—„๏ธ Checking Database Tables:") + print("-" * 30) + + try: + # Add backend to path + backend_dir = Path(__file__).parent + sys.path.insert(0, str(backend_dir)) + + from services.database import get_db_session, DATABASE_URL + from sqlalchemy import text + + session = get_db_session() + if not session: + print("โŒ Could not get database session") + return False + + # Check for billing tables + tables_query = text(""" + SELECT name FROM sqlite_master + WHERE type='table' AND ( + name LIKE '%subscription%' OR + name LIKE '%usage%' OR + name LIKE '%billing%' OR + name LIKE '%pricing%' OR + name LIKE '%alert%' + ) + ORDER BY name + """) + + result = session.execute(tables_query) + tables = result.fetchall() + + expected_tables = [ + 'api_provider_pricing', + 'api_usage_logs', + 'subscription_plans', + 'usage_alerts', + 'usage_summaries', + 'user_subscriptions' + ] + + found_tables = [t[0] for t in tables] + print(f"Found tables: {found_tables}") + + missing_tables = [t for t in expected_tables if t not in found_tables] + if missing_tables: + print(f"โŒ Missing tables: {missing_tables}") + return False + + # Check table data + for table in ['subscription_plans', 'api_provider_pricing']: + count_query = text(f"SELECT COUNT(*) FROM {table}") + result = session.execute(count_query) + count = result.fetchone()[0] + print(f"โœ… {table}: {count} records") + + session.close() + return True + + except Exception as e: + print(f"โŒ Database check failed: {e}") + return False + +def main(): + """Main verification function.""" + + print("๐Ÿ” ALwrity Billing & Subscription System Setup Verification") + print("=" * 70) + + backend_dir = Path(__file__).parent + + # Files to check + files_to_check = [ + (backend_dir / "models" / "subscription_models.py", "Subscription Models"), + (backend_dir / "services" / "pricing_service.py", "Pricing Service"), + (backend_dir / "services" / "usage_tracking_service.py", "Usage Tracking Service"), + (backend_dir / "services" / "subscription_exception_handler.py", "Exception Handler"), + (backend_dir / "api" / "subscription_api.py", "Subscription API"), + (backend_dir / "scripts" / "create_billing_tables.py", "Billing Migration Script"), + (backend_dir / "scripts" / "create_subscription_tables.py", "Subscription Migration Script"), + (backend_dir / "start_alwrity_backend.py", "Backend Startup Script"), + ] + + # Check file existence + print("\n๐Ÿ“ Checking File Existence:") + print("-" * 30) + files_exist = 0 + for file_path, description in files_to_check: + if check_file_exists(file_path, description): + files_exist += 1 + + # Check content of key files + print("\n๐Ÿ“ Checking File Content:") + print("-" * 30) + + content_checks = [ + ( + backend_dir / "models" / "subscription_models.py", + ["SubscriptionPlan", "APIUsageLog", "UsageSummary", "APIProviderPricing"], + "Subscription Models Content" + ), + ( + backend_dir / "services" / "pricing_service.py", + ["calculate_api_cost", "check_usage_limits", "initialize_default_pricing"], + "Pricing Service Content" + ), + ( + backend_dir / "services" / "usage_tracking_service.py", + ["track_api_usage", "get_user_usage_stats", "enforce_usage_limits"], + "Usage Tracking Content" + ), + ( + backend_dir / "api" / "subscription_api.py", + ["get_user_usage", "get_subscription_plans", "get_dashboard_data"], + "API Endpoints Content" + ), + ( + backend_dir / "start_alwrity_backend.py", + ["setup_billing_tables", "verify_billing_tables"], + "Backend Startup Integration" + ) + ] + + content_valid = 0 + for file_path, search_terms, description in content_checks: + if os.path.exists(file_path): + if check_file_content(file_path, search_terms, description): + content_valid += 1 + else: + print(f"โŒ {description}: File not found") + + # Check database tables + database_ok = check_database_tables() + + # Check middleware integration + print("\n๐Ÿ”ง Checking Middleware Integration:") + print("-" * 30) + + middleware_file = backend_dir / "middleware" / "monitoring_middleware.py" + middleware_terms = [ + "UsageTrackingService", + "detect_api_provider", + "track_api_usage", + "check_usage_limits_middleware" + ] + + middleware_ok = check_file_content( + middleware_file, + middleware_terms, + "Middleware Integration" + ) + + # Check app.py integration + print("\n๐Ÿš€ Checking FastAPI Integration:") + print("-" * 30) + + app_file = backend_dir / "app.py" + app_terms = [ + "from api.subscription_api import router as subscription_router", + "app.include_router(subscription_router)" + ] + + app_ok = check_file_content( + app_file, + app_terms, + "FastAPI App Integration" + ) + + # Check database service integration + print("\n๐Ÿ’พ Checking Database Integration:") + print("-" * 30) + + db_file = backend_dir / "services" / "database.py" + db_terms = [ + "from models.subscription_models import Base as SubscriptionBase", + "SubscriptionBase.metadata.create_all(bind=engine)" + ] + + db_ok = check_file_content( + db_file, + db_terms, + "Database Service Integration" + ) + + # Summary + print("\n" + "=" * 70) + print("๐Ÿ“Š VERIFICATION SUMMARY") + print("=" * 70) + + total_files = len(files_to_check) + total_content = len(content_checks) + + print(f"Files Created: {files_exist}/{total_files}") + print(f"Content Valid: {content_valid}/{total_content}") + print(f"Database Tables: {'โœ…' if database_ok else 'โŒ'}") + print(f"Middleware Integration: {'โœ…' if middleware_ok else 'โŒ'}") + print(f"FastAPI Integration: {'โœ…' if app_ok else 'โŒ'}") + print(f"Database Integration: {'โœ…' if db_ok else 'โŒ'}") + + # Overall status + all_checks = [ + files_exist == total_files, + content_valid == total_content, + database_ok, + middleware_ok, + app_ok, + db_ok + ] + + if all(all_checks): + print("\n๐ŸŽ‰ ALL CHECKS PASSED!") + print("โœ… Billing and subscription system setup is complete and ready to use.") + + print("\n" + "=" * 70) + print("๐Ÿš€ NEXT STEPS:") + print("=" * 70) + print("1. Start the backend server:") + print(" python start_alwrity_backend.py") + print("\n2. Test the API endpoints:") + print(" GET http://localhost:8000/api/subscription/plans") + print(" GET http://localhost:8000/api/subscription/usage/demo") + print(" GET http://localhost:8000/api/subscription/dashboard/demo") + print(" GET http://localhost:8000/api/subscription/pricing") + print("\n3. Access the frontend billing dashboard") + print("4. Monitor usage through the API monitoring middleware") + print("5. Set up user identification for production use") + print("=" * 70) + + else: + print("\nโŒ SOME CHECKS FAILED!") + print("Please review the errors above and fix any issues.") + return False + + return True + +if __name__ == "__main__": + success = main() + if not success: + sys.exit(1) diff --git a/docs/AI_BLOG_WRITER_IMPLEMENTATION_SPEC.md b/docs/AI_BLOG_WRITER_IMPLEMENTATION_SPEC.md new file mode 100644 index 00000000..1ebb5ac0 --- /dev/null +++ b/docs/AI_BLOG_WRITER_IMPLEMENTATION_SPEC.md @@ -0,0 +1,237 @@ +## AI Blog Writer โ€” Implementation Specification (Copilot-first, Research-led) + +### Overview +- **Goal**: Build a SOTA AI blog writer that guides non-technical users end-to-end: research โ†’ outline โ†’ section generation โ†’ quality/SEO โ†’ publishing. +- **Approach**: Copilot-first UX using CopilotKit. Reuse LinkedIn assistive writing patterns: Google Search grounding, Exa research, hallucination detector, quality analysis, citations. +- **User Interaction Model**: The user only talks to the Copilot; the editor reflects all state and changes via generative UI and HITL confirmations. + +### Key Principles +- **AI-first, HITL**: The assistant leads with intelligent suggestions; the user approves via render-and-wait HITL components where appropriate. +- **Research fidelity**: Google grounding + Exa researcher; hallucination detection with claim verification; pervasive citations. +- **Persona-aware**: Import blog writing persona from DB and apply it across planning/generation/optimizations. +- **SEO-excellent**: Real-time SEO analysis, metadata generation, schema, and image alt handling. +- **Publish-ready**: Smooth handoff to Wix/WordPress; preview and scheduling. + +--- + +## 1) Workflow (4 Stages) + +### Stage 1: Research & Strategy (AI Orchestration) +Inputs +- `keywords: string[]`, `industry: string`, `targetAudience: string`, `tone: string`, `wordCountTarget: number`, `userId` +- Persona is fetched from DB and persisted in session + +Backend/Services +- Reuse LinkedIn research handler patterns: Google native grounding (Gemini provider), optional Exa research. +- Reuse hallucination detector service and models: `/api/hallucination-detector/*` for claim extraction and verification. + +CopilotKit Actions +- `getPersonaFromDB(userId)` โ†’ persona constraints and style. +- `analyzeKeywords(keywords, industry, audience)` โ†’ search intent, primary/secondary/long-tail, difficulty, volume. +- `researchTopic(topic, depth, sources=['google','exa'])` โ†’ aggregated research sources (with credibility + timestamps). +- `analyzeCompetitors(keywords, industry)` โ†’ top pages, headings used, gaps/opportunities. + +Generative UI (render-only) +- Research Summary card: sources, credibility score, proposed angles. +- Suggested Keywords: chip list; add/remove HITL. + +Suggestions (programmatic) +- โ€œConfirm researchโ€, โ€œRefine keywordsโ€, โ€œAdd competitorโ€, โ€œProceed to outlineโ€. + +--- + +### Stage 2: Content Planning (AI + Human) +Deliverables +- Structured outline (H1/H2/H3), per-section key points, citations to use, target word counts. + +CopilotKit Actions +- `generateOutline(research, persona, wordCount)` โ†’ full outline with per-section targets and suggested refs. +- `refineOutline(operation, sectionId, payload?)` โ†’ add/remove/move/merge sections (HITL diff in UI). +- `attachReferences(sectionId, sourceIds[])` โ†’ associate sources to sections. + +Generative UI (HITL) +- Outline Editor: draggable sections/subsections, per-section references and target words, persona style hints. + +Suggestions +- โ€œGenerate [Section 1]โ€, โ€œRegenerate [Section 2]โ€, โ€œAttach sources to [Section]โ€, โ€œGenerate All Sectionsโ€. + +--- + +### Stage 3: Content Generation (CopilotKit-only, no multi-agent) +Deliverables +- Long-form markdown content with inline citations, persona-aligned tone, and sectioned structure. + +CopilotKit Actions +- `generateSection(sectionPlan, keywords, tone, persona, refs[])` โ†’ returns markdown + inline cites. +- `generateAllSections(outline)` โ†’ sequential section generation with progress render. +- `optimizeSection(content, goals[])` โ†’ readability/EEAT/examples/data improvements; UI shows diff preview (HITL confirm). +- `runHallucinationCheck(content)` โ†’ uses `/api/hallucination-detector/detect` to flag claims + propose fixes. + +Editor/UI Updates +- Per-section markdown tabs; word count; inline citation chips; section mini-SEO score. +- DiffPreview component for any AI edit prior to apply. + +Suggestions +- โ€œAdd table/figureโ€, โ€œInsert case study with sourceโ€, โ€œStrengthen introductionโ€, โ€œTighten conclusion CTAโ€. + +--- + +### Stage 4: Optimization & Publishing (AI + Human) +SEO Optimization +- `analyzeSEO(content, keywords)` โ†’ density, heading structure, links, readability, image alt coverage, overall SEO score. +- `generateSEOMetadata(content, title, keywords)` โ†’ title options, meta description, OG/Twitter cards, schema Article/FAQ. +- `applySEOFixes(suggestions[])` โ†’ diff preview + HITL apply. + +Publishing +- `prepareForPublish(platform: 'wix' | 'wordpress')` โ†’ HTML + images + metadata packaging. +- `publishToPlatform(platform, schedule?)` โ†’ uses Wix/WordPress clients (ToBeMigrated integrations). Shows URL/status. + +Suggestions +- โ€œRun SEO analysisโ€, โ€œApply recommended fixesโ€, โ€œGenerate metadataโ€, โ€œPublish to WordPressโ€, โ€œSchedule on Wixโ€. + +--- + +## 2) SEO Tools Integration & Metadata + +Existing Services to Wrap +- Meta Description, OpenGraph, Image Alt, On-Page SEO, Technical SEO, Content Strategy (see `backend/services/seo_tools/*` and docs). + +Unified Endpoints +- `POST /api/blog/seo/analyze` โ†’ { seoScore, density, structure, readability, link suggestions, image alt status, recs } +- `POST /api/blog/seo/metadata` โ†’ { titleOptions, metaDescriptionOptions, openGraph, twitterCard, schema: { Article, FAQ?, Breadcrumb, Org/Person } } + +Editor SEO Panel +- Live density and distribution, readability (Flesch-Kincaid), heading hierarchy, internal/external link suggestions. +- One-click โ€œApply Fixโ€ with diff preview. + +Schema +- Default Article schema; optional FAQ when Q&A snippets exist; Breadcrumb, Organization/Person as applicable. + +--- + +## 3) Dedicated Blog Editor Design (Copilot-first) + +Layout +- Left: Markdown Editor (per-section tabs), word count, persona cues, inline citation chips. +- Right: Live Preview (desktop/mobile), SEO SERP snippet preview, social preview (OG/Twitter). +- Sidebar Panels: Research (sources, claims), SEO (scores/fixes), Media (AI images + alt text), History (versions). + +Core Components +- `BlogResearchCard` (render-only): sources, credibility scores, add-to-outline. +- `OutlineEditor` (HITL): drag-drop H2/H3, per-section refs and target words. +- `SectionEditor`: markdown area with persona/tone badges; per-section SEO mini-score. +- `DiffPreview` (HITL): apply/reject AI edits. +- `SEOPanel`: density/structure/readability + apply fix. +- `MediaPanel`: AI images, compression, automatic alt-text. + +CopilotKit Integrations +- Suggestions: set programmatically (`useCopilotChatHeadless_c`) or via `CopilotSidebar` props. +- Generative UI: `useCopilotAction({ render })` for research cards, outline editor, diff preview, publish dialog. +- HITL: `renderAndWaitForResponse` for approvals at outline, diff apply, and publish steps. +- References: CopilotKit docs โ€” Frontend Actions, Generative UI, Suggestions, HITL. + +Persistence +- Persist outline, per-section content, references, persona snapshot, SEO state, metadata drafts. +- Auto-save every 30s; version history for undo. + +--- + +## 4) Backend APIs + +New Blog Endpoints +- `POST /api/blog/research` โ†’ inputs: keywords/industry/audience/tone/wordCount, personaId?; returns research bundle. +- `POST /api/blog/outline/generate` โ†’ returns structured outline with targets and ref suggestions. +- `POST /api/blog/outline/refine` โ†’ returns updated outline (operation-based). +- `POST /api/blog/section/generate` โ†’ returns markdown + inline citations. +- `POST /api/blog/section/optimize` โ†’ returns optimized content + rationale. +- `POST /api/blog/quality/hallucination-check` โ†’ proxies hallucination detector results for blog. +- `POST /api/blog/seo/analyze` โ†’ wraps SEO analyzers; returns scores/suggestions. +- `POST /api/blog/seo/metadata` โ†’ returns title/meta/OG/Twitter/schema. +- `POST /api/blog/publish` โ†’ platform: wix|wordpress, schedule?; returns URL/status. + +Reuse +- `/api/hallucination-detector/detect|extract-claims|verify-claim|health` (already implemented). + +Models (indicative) +- `BlogResearchRequest`, `BlogResearchResponse` +- `BlogOutline`, `BlogOutlineRefinement` +- `BlogSectionRequest`, `BlogSectionResponse` +- `BlogSEOAnalysisRequest`, `BlogSEOMetadataResponse` + +--- + +## 5) CopilotKit Action Inventory + +Research +- `getPersonaFromDB`, `analyzeKeywords`, `researchTopic`, `analyzeCompetitors` + +Planning +- `generateOutline`, `refineOutline`, `attachReferences` + +Generation +- `generateSection`, `generateAllSections`, `optimizeSection`, `runHallucinationCheck` + +SEO +- `analyzeSEO`, `generateSEOMetadata`, `applySEOFixes` + +Publishing +- `prepareForPublish`, `publishToPlatform` + +UX/Render-only/HITL +- `showResearchCard`, `showOutlineEditor`, `showDiffPreview`, `showSEOPanel`, `showPublishDialog` + +--- + +## 6) Intelligent Suggestions (states) + +Before research +- โ€œLoad personaโ€, โ€œAnalyze keywordsโ€, โ€œResearch topicโ€ + +After research +- โ€œGenerate outlineโ€, โ€œAdd competitor H2sโ€, โ€œAttach sourcesโ€ + +Outline ready +- โ€œGenerate [Section 1]โ€, โ€œโ€ฆโ€, โ€œGenerate all sectionsโ€ + +Draft ready +- โ€œRun fact-checkโ€, โ€œRun SEO analysisโ€, โ€œGenerate metadataโ€ + +Final +- โ€œPublish to WordPressโ€, โ€œSchedule on Wixโ€ + +--- + +## 7) Delivery Plan / Milestones + +Milestone 1: Research + Outline +- Actions: persona load, analyze keywords, research topic, generate outline, outline editor (HITL) + +Milestone 2: Section Generation + Quality +- generateSection/generateAllSections, optimizeSection with diff preview, hallucination check + fixes + +Milestone 3: SEO & Metadata +- analyzeSEO panel, generateSEOMetadata (title/meta/OG/Twitter/schema), apply fixes + +Milestone 4: Publishing +- prepareForPublish, publishToPlatform (Wix/WordPress), schedule, success URL + +Milestone 5: Polish +- Readability aids, version history, performance, accessibility + +--- + +## 8) References +- CopilotKit Quickstart, Frontend Actions, Generative UI, HITL, Suggestions + - Quickstart: https://docs.copilotkit.ai/direct-to-llm/guides/quickstart + - Frontend Actions: https://docs.copilotkit.ai/frontend-actions + - Generative UI: https://docs.copilotkit.ai/direct-to-llm/guides/generative-ui + - Headless + Suggestions + HITL: https://docs.copilotkit.ai/premium/headless-ui + +--- + +## 9) Notes on Reuse from LinkedIn Writer +- Research handler; Gemini grounded provider; citation manager; quality analyzer. +- Hallucination detector + Exa verification endpoints. +- CopilotKit integration patterns: actions, suggestions, render/HITL, state persistence. + + diff --git a/BILLING_FRONTEND_INTEGRATION_PLAN.md b/docs/Billing_Subscription/BILLING_FRONTEND_INTEGRATION_PLAN.md similarity index 100% rename from BILLING_FRONTEND_INTEGRATION_PLAN.md rename to docs/Billing_Subscription/BILLING_FRONTEND_INTEGRATION_PLAN.md diff --git a/BILLING_IMPLEMENTATION_ROADMAP.md b/docs/Billing_Subscription/BILLING_IMPLEMENTATION_ROADMAP.md similarity index 100% rename from BILLING_IMPLEMENTATION_ROADMAP.md rename to docs/Billing_Subscription/BILLING_IMPLEMENTATION_ROADMAP.md diff --git a/BILLING_IMPLEMENTATION_STATUS.md b/docs/Billing_Subscription/BILLING_IMPLEMENTATION_STATUS.md similarity index 100% rename from BILLING_IMPLEMENTATION_STATUS.md rename to docs/Billing_Subscription/BILLING_IMPLEMENTATION_STATUS.md diff --git a/BILLING_TECHNICAL_SPECIFICATION.md b/docs/Billing_Subscription/BILLING_TECHNICAL_SPECIFICATION.md similarity index 100% rename from BILLING_TECHNICAL_SPECIFICATION.md rename to docs/Billing_Subscription/BILLING_TECHNICAL_SPECIFICATION.md diff --git a/SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md b/docs/Billing_Subscription/SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md similarity index 100% rename from SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md rename to docs/Billing_Subscription/SUBSCRIPTION_IMPLEMENTATION_SUMMARY.md diff --git a/frontend/src/App.tsx b/frontend/src/App.tsx index 446fd4f2..7d3b353f 100644 --- a/frontend/src/App.tsx +++ b/frontend/src/App.tsx @@ -9,6 +9,7 @@ import SEODashboard from './components/SEODashboard/SEODashboard'; import ContentPlanningDashboard from './components/ContentPlanningDashboard/ContentPlanningDashboard'; import FacebookWriter from './components/FacebookWriter/FacebookWriter'; import LinkedInWriter from './components/LinkedInWriter/LinkedInWriter'; +import BlogWriter from './components/BlogWriter/BlogWriter'; import { apiClient } from './api/client'; @@ -187,6 +188,7 @@ const App: React.FC = () => { } /> } /> } /> + } /> diff --git a/frontend/src/components/BlogWriter/BlogWriter.tsx b/frontend/src/components/BlogWriter/BlogWriter.tsx new file mode 100644 index 00000000..e1ec8b90 --- /dev/null +++ b/frontend/src/components/BlogWriter/BlogWriter.tsx @@ -0,0 +1,581 @@ +import React, { useMemo, useState } from 'react'; +import { CopilotSidebar } from '@copilotkit/react-ui'; +import { useCopilotAction } from '@copilotkit/react-core'; +import '@copilotkit/react-ui/styles.css'; +import { blogWriterApi, BlogOutlineSection, BlogResearchResponse, BlogSEOMetadataResponse, BlogSEOAnalyzeResponse } from '../../services/blogWriterApi'; +import EnhancedOutlineEditor from './EnhancedOutlineEditor'; +import TitleSelector from './TitleSelector'; +import DiffPreview from './DiffPreview'; +import SEOMiniPanel from './SEOMiniPanel'; +import ResearchResults from './ResearchResults'; +import KeywordInputForm from './KeywordInputForm'; +import ResearchAction from './ResearchAction'; + +const useCopilotActionTyped = useCopilotAction as any; + +export const BlogWriter: React.FC = () => { + const [research, setResearch] = useState(null); + const [outline, setOutline] = useState([]); + const [titleOptions, setTitleOptions] = useState([]); + const [selectedTitle, setSelectedTitle] = useState(''); + const [sections, setSections] = useState>({}); + const [seoAnalysis, setSeoAnalysis] = useState(null); + const [seoMetadata, setSeoMetadata] = useState(null); + const [hallucinationResult, setHallucinationResult] = useState(null); + + const buildFullMarkdown = () => { + if (!outline.length) return ''; + return outline.map(s => `## ${s.heading}\n\n${sections[s.id] || ''}`).join('\n\n'); + }; + + // Sentence-level claim mapping and patching helpers + const normalized = (s: string) => s.toLowerCase().replace(/\s+/g, ' ').trim(); + + const fuzzyScore = (a: string, b: string) => { + // Dice's coefficient over word bigrams for robustness (no deps) + const bigrams = (s: string) => { + const t = s.split(/\W+/).filter(Boolean); + const grams: string[] = []; + for (let i = 0; i < t.length - 1; i++) grams.push(`${t[i]} ${t[i+1]}`); + return grams; + }; + const A = new Set(bigrams(a)); + const B = new Set(bigrams(b)); + if (!A.size || !B.size) return 0; + let overlap = 0; + A.forEach(g => { if (B.has(g)) overlap++; }); + return (2 * overlap) / (A.size + B.size); + }; + + const findSentenceForClaim = (md: string, claimText: string) => { + const text = md || ''; + // Split by sentence enders; keep delimiters + const sentences = text.split(/(?<=[.!?])\s+/); + const normalizedClaim = claimText.trim().toLowerCase(); + // Direct includes first + let bestIndex = sentences.findIndex(s => s.toLowerCase().includes(normalizedClaim)); + if (bestIndex >= 0) return { sentence: sentences[bestIndex], index: bestIndex, sentences }; + // Fallback: overlap ratio by words + const claimWords = normalizedClaim.split(/\W+/).filter(Boolean); + let bestScore = 0; bestIndex = -1; + sentences.forEach((s, i) => { + const sw = s.toLowerCase().split(/\W+/).filter(Boolean); + const overlap = claimWords.filter(w => sw.includes(w)).length; + const score = overlap / Math.max(claimWords.length, 1); + if (score > bestScore) { bestScore = score; bestIndex = i; } + }); + // Second fallback: Dice coefficient on normalized strings + if (bestIndex < 0) { + let diceBest = 0; let diceIdx = -1; + sentences.forEach((s, i) => { + const sc = fuzzyScore(normalized(s), normalized(claimText)); + if (sc > diceBest) { diceBest = sc; diceIdx = i; } + }); + if (diceIdx >= 0) return { sentence: sentences[diceIdx], index: diceIdx, sentences }; + } + if (bestIndex >= 0) return { sentence: sentences[bestIndex], index: bestIndex, sentences }; + return { sentence: '', index: -1, sentences }; + }; + + const buildUpdatedMarkdownForClaim = (claimText: string, supportingUrl?: string) => { + const md = buildFullMarkdown(); + const { sentence, index, sentences } = findSentenceForClaim(md, claimText); + if (!sentence || index < 0) return { original: '', updated: '', updatedMarkdown: md }; + const alreadyHasLink = /\[[^\]]+\]\(([^)]+)\)/.test(sentence); + const fix = supportingUrl && !alreadyHasLink ? `${sentence} [source](${supportingUrl})` : sentence; + const updatedSentences = [...sentences]; + updatedSentences[index] = fix; + const updatedMarkdown = updatedSentences.join(' '); + return { original: sentence, updated: fix, updatedMarkdown }; + }; + + const applyClaimFix = (claimText: string, supportingUrl?: string) => { + // Naive fix: append citation footnote to the first occurrence of claim text + const { updatedMarkdown } = buildUpdatedMarkdownForClaim(claimText, supportingUrl); + const updated = updatedMarkdown; + // Re-split content back to per-section, by headings + const parts = updated.split(/^## /gm).filter(Boolean); + const newSections: Record = {}; + outline.forEach((s, idx) => { + const body = parts[idx] ? parts[idx].replace(new RegExp(`^${s.heading}\n\n?`), '') : (sections[s.id] || ''); + newSections[s.id] = body; + }); + setSections(newSections); + }; + + // Handle research completion + const handleResearchComplete = (researchData: BlogResearchResponse) => { + setResearch(researchData); + }; + + useCopilotActionTyped({ + name: 'generateOutline', + description: 'Generate outline from research results using AI analysis', + parameters: [], + handler: async () => { + if (!research) return { success: false, message: 'No research yet. Please research a topic first.' }; + + try { + const res = await blogWriterApi.generateOutline({ research }); + if (res?.outline) { + setOutline(res.outline); + setTitleOptions(res.title_options || []); + if (res.title_options && res.title_options.length > 0) { + setSelectedTitle(res.title_options[0]); // Auto-select first title + } + + const outlineCount = res.outline.length; + const primaryKeywords = research.keyword_analysis?.primary || []; + + return { + success: true, + message: `๐Ÿงฉ Outline generated successfully! Created ${outlineCount} sections based on your research. The outline incorporates your primary keywords (${primaryKeywords.join(', ')}) and follows the content angles we discovered. You can now review the outline structure, choose a title, and generate content for individual sections.`, + outline_summary: { + sections: outlineCount, + primary_keywords: primaryKeywords, + research_sources: research.sources?.length || 0, + title_options: res.title_options?.length || 0 + } + }; + } + } catch (error) { + console.error('Outline generation failed:', error); + const errorMessage = error instanceof Error ? error.message : 'Unknown error'; + return { + success: false, + message: `โŒ Outline generation failed: ${errorMessage}. The AI system encountered an issue while creating your outline. Please try again or contact support if the problem persists.` + }; + } + return { + success: false, + message: 'Failed to generate outline. The AI outline generation system encountered an issue. Please try again or contact support if the problem persists.' + }; + }, + render: ({ status }: any) => { + console.log('generateOutline render called with status:', status); + if (status === 'inProgress' || status === 'executing') { + return ( +
+
+
+

๐Ÿงฉ Generating Outline

+
+
+

โ€ข Analyzing research results and content angles...

+

โ€ข Structuring content based on keyword analysis...

+

โ€ข Creating logical flow and section hierarchy...

+

โ€ข Optimizing for SEO and reader engagement...

+
+ +
+ ); + } + return null; + } + }); + + useCopilotActionTyped({ + name: 'generateSection', + description: 'Generate content for a specific section using research and outline', + parameters: [ { name: 'sectionId', type: 'string', description: 'Section ID', required: true } ], + handler: async ({ sectionId }: { sectionId: string }) => { + const section = outline.find(s => s.id === sectionId); + if (!section) return { success: false, message: 'Section not found. Please generate an outline first.' }; + + try { + const res = await blogWriterApi.generateSection({ section }); + if (res?.markdown) { + setSections(prev => ({ ...prev, [sectionId]: res.markdown })); + + return { + success: true, + message: `โœ๏ธ Content generated for "${section.heading}"! The section incorporates your research findings and primary keywords. You can now review the content, run SEO analysis, or generate more sections.`, + section_summary: { + heading: section.heading, + content_length: res.markdown.length, + primary_keywords: research?.keyword_analysis?.primary || [] + } + }; + } + } catch (error) { + console.error('Section generation failed:', error); + const errorMessage = error instanceof Error ? error.message : 'Unknown error'; + return { + success: false, + message: `โŒ Content generation failed for "${section.heading}": ${errorMessage}. Please try again or contact support if the problem persists.` + }; + } + return { success: false, message: 'Failed to generate section content. Please try again.' }; + }, + render: ({ status }: any) => { + if (status === 'inProgress' || status === 'executing') { + return ( +
+
+
+

โœ๏ธ Generating Section Content

+
+
+

โ€ข Analyzing section requirements and research data...

+

โ€ข Incorporating primary keywords and SEO best practices...

+

โ€ข Writing engaging content with proper structure...

+

โ€ข Ensuring factual accuracy and readability...

+
+ +
+ ); + } + return null; + } + }); + + useCopilotActionTyped({ + name: 'generateAllSections', + description: 'Generate content for every section in the outline', + parameters: [], + handler: async () => { + for (const s of outline) { + const res = await blogWriterApi.generateSection({ section: s }); + setSections(prev => ({ ...prev, [s.id]: res.markdown })); + } + return { success: true }; + }, + render: ({ status }: any) => (status === 'inProgress' || status === 'executing') ?
Generating all sectionsโ€ฆ
: null + }); + + // Outline refinement (basic op pass-through) + useCopilotActionTyped({ + name: 'refineOutline', + description: 'Refine the outline (add/remove/move/merge)', + parameters: [ + { name: 'operation', type: 'string', description: 'add|remove|move|merge|rename', required: true }, + { name: 'sectionId', type: 'string', description: 'Target section ID', required: false }, + { name: 'payload', type: 'string', description: 'JSON payload for operation', required: false }, + ], + handler: async ({ operation, sectionId, payload }: { operation: string; sectionId?: string; payload?: string }) => { + const payloadObj = payload ? (() => { try { return JSON.parse(payload); } catch { return {}; } })() : undefined; + const res = await blogWriterApi.refineOutline({ outline, operation, section_id: sectionId, payload: payloadObj }); + if (res?.outline) setOutline(res.outline); + return { success: true }; + } + }); + + // Optimize section with HITL diff preview + useCopilotActionTyped({ + name: 'optimizeSection', + description: 'Optimize a section for readability/EEAT/examples/data with HITL diff', + parameters: [ + { name: 'sectionId', type: 'string', description: 'Section ID', required: true }, + { name: 'goals', type: 'string', description: 'Comma-separated goals', required: false }, + ], + handler: async ({ sectionId, goals }: { sectionId: string; goals?: string }) => { + const current = sections[sectionId] || ''; + if (!current) return { success: false, message: 'No content yet for this section' }; + const res = await blogWriterApi.seoAnalyze({ content: current, keywords: [] }); + setSeoAnalysis(res); + return { success: true, message: 'Analysis ready' }; + }, + renderAndWaitForResponse: ({ respond, args, status }: any) => { + if (status === 'complete') return
Optimization applied.
; + return ( +
+
Optimization preview
+
Goals: {args.goals || 'readability, EEAT'}
+ +
+ ); + } + }); + + // SEO analyze full draft + useCopilotActionTyped({ + name: 'runSEOAnalyze', + description: 'Analyze SEO for the full draft', + parameters: [ { name: 'keywords', type: 'string', description: 'Comma-separated keywords', required: false } ], + handler: async ({ keywords }: { keywords?: string }) => { + const content = buildFullMarkdown(); + const res = await blogWriterApi.seoAnalyze({ content, keywords: keywords ? keywords.split(',').map(k => k.trim()) : [] }); + setSeoAnalysis(res); + return { success: true, seo_score: res.seo_score }; + }, + render: ({ status, result }: any) => status === 'complete' ? ( +
+
SEO Score: {result?.seo_score ?? 'โ€”'}
+
+ ) : null + }); + + // SEO metadata generate + HITL accept + useCopilotActionTyped({ + name: 'generateSEOMetadata', + description: 'Generate SEO metadata for the full draft', + parameters: [ { name: 'title', type: 'string', description: 'Preferred title', required: false } ], + handler: async ({ title }: { title?: string }) => { + const content = buildFullMarkdown(); + const res = await blogWriterApi.seoMetadata({ content, title, keywords: [] }); + setSeoMetadata(res); + return { success: true }; + }, + renderAndWaitForResponse: ({ respond }: any) => ( +
+
SEO Metadata Ready
+
Review the generated title, meta description, and OG/Twitter tags in the editor.
+ +
+ ) + }); + + // Hallucination check with HITL apply-fix + useCopilotActionTyped({ + name: 'runHallucinationCheck', + description: 'Run hallucination detector on full draft and view claims', + parameters: [], + handler: async () => { + const content = buildFullMarkdown(); + const res = await fetch('/api/blog/quality/hallucination-check', { + method: 'POST', + headers: { 'Content-Type': 'application/json' }, + body: JSON.stringify({ text: content }) + }); + const data = await res.json(); + setHallucinationResult(data); + return { success: true, total_claims: data?.total_claims }; + }, + renderAndWaitForResponse: ({ respond, result }: any) => { + if (!result) return null; + const claims = hallucinationResult?.claims || []; + return ( +
+
Hallucination Check
+
Total claims: {hallucinationResult?.total_claims ?? 0}
+
    + {claims.slice(0, 5).map((c: any, i: number) => { + const supporting = (c.supporting_sources && c.supporting_sources[0]?.url) || undefined; + const { original, updated } = buildUpdatedMarkdownForClaim(c.text, supporting); + return ( +
  • +
    [{c.assessment}] {c.text} (conf: {Math.round((c.confidence || 0)*100)/100})
    + {original && updated ? ( + { applyClaimFix(c.text, supporting); respond?.('applied'); }} + onDiscard={() => { respond?.('discarded'); }} + /> + ) : ( +
    No matching sentence found for preview.
    + )} +
    • + ); + })} +
+ +
+ ); + } + }); + + // Publish (convert markdown -> HTML rudimentary; TODO: replace with proper converter like marked) + useCopilotActionTyped({ + name: 'publishToPlatform', + description: 'Publish the blog to Wix or WordPress', + parameters: [ + { name: 'platform', type: 'string', description: 'wix|wordpress', required: true }, + { name: 'schedule_time', type: 'string', description: 'Optional ISO datetime', required: false } + ], + handler: async ({ platform, schedule_time }: { platform: 'wix' | 'wordpress'; schedule_time?: string }) => { + const md = buildFullMarkdown(); + const html = md + .replace(/^### (.*$)/gim, '

$1

') + .replace(/^## (.*$)/gim, '

$1

') + .replace(/^# (.*$)/gim, '

$1

') + .replace(/\*\*(.*)\*\*/gim, '$1') + .replace(/\*(.*)\*/gim, '$1') + .replace(/\n\n/g, '

'); + if (!seoMetadata) return { success: false, message: 'Generate SEO metadata first' }; + const res = await blogWriterApi.publish({ platform, html, metadata: seoMetadata, schedule_time }); + return { success: true, url: res.url }; + }, + render: ({ status, result }: any) => status === 'complete' ? ( +
Published: {result?.url || 'Success'}
+ ) : null + }); + + const suggestions = useMemo(() => { + const items = [] as { title: string; message: string }[]; + if (!research) items.push({ title: '๐Ÿ”Ž Start research', message: "I want to research a topic for my blog" }); + if (research && outline.length === 0) items.push({ title: '๐Ÿงฉ Create Outline', message: 'Let\'s proceed to create an outline based on the research results' }); + if (outline.length > 0) { + items.push({ title: '๐Ÿ“ Generate all sections', message: 'Generate all sections of my blog post' }); + outline.forEach(s => items.push({ title: `โœ๏ธ Generate ${s.heading}`, message: `Generate the section: ${s.heading}` })); + items.push({ title: '๐Ÿ”ง Refine outline', message: 'Help me refine the outline structure' }); + items.push({ title: '๐Ÿ“ˆ Run SEO analysis', message: 'Analyze SEO for my blog post' }); + items.push({ title: '๐Ÿงพ Generate SEO metadata', message: 'Generate SEO metadata and title' }); + items.push({ title: '๐Ÿงช Hallucination check', message: 'Check for any false claims in my content' }); + items.push({ title: '๐Ÿš€ Publish to WordPress', message: 'Publish my blog to WordPress' }); + } + return items; + }, [research, outline]); + + return ( +
+ {/* Extracted Components */} + + + +
+

AI Blog Writer

+
+
+
+ {!research && ( +
+
๐Ÿ”
+

Ready to Research Your Blog Topic

+

Start by asking the copilot to research your topic.

+
+ )} + {research && outline.length === 0 && } + {outline.length > 0 && ( +
+ {/* Title Selection */} + {titleOptions.length > 0 && ( + { + setTitleOptions(prev => [...prev, title]); + setSelectedTitle(title); + }} + /> + )} + + {/* Enhanced Outline Editor */} + blogWriterApi.refineOutline({ outline, operation: op, section_id: id, payload }).then(res => setOutline(res.outline))} + /> + + {outline.map(s => ( +
+

{s.heading}

+ {sections[s.id] ? ( + <> + 
{sections[s.id]}
+ + + ) : ( +
Ask the copilot to generate this section.
+ )} +
+ ))} +
+ )} +
+
+ + { + // Get current state information + const hasResearch = research !== null; + const hasOutline = outline.length > 0; + const researchInfo = hasResearch ? { + sources: research.sources?.length || 0, + queries: research.search_queries?.length || 0, + angles: research.suggested_angles?.length || 0, + primaryKeywords: research.keyword_analysis?.primary || [], + searchIntent: research.keyword_analysis?.search_intent || 'informational' + } : null; + + const toolGuide = ` +You are the ALwrity Blog Writing Assistant. You MUST call the appropriate frontend actions (tools) to fulfill user requests. + +CURRENT STATE: +${hasResearch && researchInfo ? ` +โœ… RESEARCH COMPLETED: +- Found ${researchInfo.sources} sources with Google Search grounding +- Generated ${researchInfo.queries} search queries +- Created ${researchInfo.angles} content angles +- Primary keywords: ${researchInfo.primaryKeywords.join(', ')} +- Search intent: ${researchInfo.searchIntent} +` : 'โŒ No research completed yet'} + +${hasOutline ? `โœ… OUTLINE GENERATED: ${outline.length} sections created` : 'โŒ No outline generated yet'} + +Available tools: +- getResearchKeywords(prompt?: string) - Get keywords from user for research +- performResearch(formData: string) - Perform research with collected keywords (formData is JSON string with keywords and blogLength) +- researchTopic(keywords: string, industry?: string, target_audience?: string) +- generateOutline() +- generateSection(sectionId: string) +- generateAllSections() +- refineOutline(operation: add|remove|move|merge|rename, sectionId?: string, payload?: object) +- runSEOAnalyze(keywords?: string) +- generateSEOMetadata(title?: string) +- runHallucinationCheck() +- publishToPlatform(platform: 'wix'|'wordpress', schedule_time?: string) + + CRITICAL BEHAVIOR: + - When user wants to research ANY topic, IMMEDIATELY call getResearchKeywords() to get their input + - When user asks to research something, call getResearchKeywords() first to collect their keywords + - After getResearchKeywords() completes, IMMEDIATELY call performResearch() with the collected data + - When user asks for outline, call generateOutline() + - When user asks to generate content, call generateSection or generateAllSections + - DO NOT ask for clarification - take action immediately with the information provided + - Always call the appropriate tool instead of just talking about what you could do + - Be aware of the current state and reference research results when relevant + - Guide users through the process: Research โ†’ Outline โ†’ Content โ†’ SEO โ†’ Publish +`; + return [toolGuide, additional].filter(Boolean).join('\n\n'); + }} + /> +
+ ); +}; + +export default BlogWriter; \ No newline at end of file diff --git a/frontend/src/components/BlogWriter/DiffPreview.tsx b/frontend/src/components/BlogWriter/DiffPreview.tsx new file mode 100644 index 00000000..798098fb --- /dev/null +++ b/frontend/src/components/BlogWriter/DiffPreview.tsx @@ -0,0 +1,51 @@ +import React from 'react'; + +interface Props { + original: string; + updated: string; + onApply: () => void; + onDiscard: () => void; +} + +function highlightDiff(a: string, b: string) { + // Simple common prefix/suffix highlighting + let i = 0; + while (i < a.length && i < b.length && a[i] === b[i]) i++; + let j = 0; + while (j < a.length - i && j < b.length - i && a[a.length - 1 - j] === b[b.length - 1 - j]) j++; + const aMid = a.substring(i, a.length - j); + const bMid = b.substring(i, b.length - j); + const aHtml = `${escapeHtml(a.substring(0, i))}${escapeHtml(aMid)}${escapeHtml(a.substring(a.length - j))}`; + const bHtml = `${escapeHtml(b.substring(0, i))}${escapeHtml(bMid)}${escapeHtml(b.substring(b.length - j))}`; + return { aHtml, bHtml }; +} + +function escapeHtml(s: string) { + return s + .replace(/&/g, '&') + .replace(//g, '>') + .replace(/"/g, '"') + .replace(/'/g, '''); +} + +const DiffPreview: React.FC = ({ original, updated, onApply, onDiscard }) => { + const { aHtml, bHtml } = highlightDiff(original, updated); + return ( +
+
Preview Changes
+
+
+
+
+
+ + +
+
+ ); +}; + +export default DiffPreview; + + diff --git a/frontend/src/components/BlogWriter/EnhancedOutlineEditor.tsx b/frontend/src/components/BlogWriter/EnhancedOutlineEditor.tsx new file mode 100644 index 00000000..20c1ed4f --- /dev/null +++ b/frontend/src/components/BlogWriter/EnhancedOutlineEditor.tsx @@ -0,0 +1,535 @@ +import React, { useState } from 'react'; +import { BlogOutlineSection } from '../../services/blogWriterApi'; + +interface Props { + outline: BlogOutlineSection[]; + onRefine: (operation: string, sectionId?: string, payload?: any) => void; + research?: any; // Research data for context +} + +const EnhancedOutlineEditor: React.FC = ({ outline, onRefine, research }) => { + const [editingSection, setEditingSection] = useState(null); + const [expandedSections, setExpandedSections] = useState>(new Set()); + const [showAddSection, setShowAddSection] = useState(false); + const [newSectionData, setNewSectionData] = useState({ + heading: '', + subheadings: '', + key_points: '', + target_words: 300 + }); + + const toggleExpanded = (sectionId: string) => { + const newExpanded = new Set(expandedSections); + if (newExpanded.has(sectionId)) { + newExpanded.delete(sectionId); + } else { + newExpanded.add(sectionId); + } + setExpandedSections(newExpanded); + }; + + const handleRename = (sectionId: string, newHeading: string) => { + if (newHeading.trim()) { + onRefine('rename', sectionId, { heading: newHeading.trim() }); + } + setEditingSection(null); + }; + + const handleMove = (sectionId: string, direction: 'up' | 'down') => { + onRefine('move', sectionId, { direction }); + }; + + const handleAddSection = () => { + if (newSectionData.heading.trim()) { + const subheadings = newSectionData.subheadings + .split('\n') + .map(s => s.trim()) + .filter(s => s.length > 0); + + const keyPoints = newSectionData.key_points + .split('\n') + .map(s => s.trim()) + .filter(s => s.length > 0); + + onRefine('add', undefined, { + heading: newSectionData.heading.trim(), + subheadings, + key_points: keyPoints, + target_words: newSectionData.target_words + }); + + setNewSectionData({ + heading: '', + subheadings: '', + key_points: '', + target_words: 300 + }); + setShowAddSection(false); + } + }; + + const getTotalWords = () => { + return outline.reduce((total, section) => total + (section.target_words || 0), 0); + }; + + + return ( +
+ {/* Header */} +
+
+
+

+ ๐Ÿ“‹ Blog Outline +

+

+ {outline.length} sections โ€ข {getTotalWords()} words total +

+
+ +
+
+ + {/* Add Section Form */} + {showAddSection && ( +
+

Add New Section

+
+
+ + setNewSectionData({...newSectionData, heading: e.target.value})} + placeholder="Enter section title..." + style={{ + width: '100%', + padding: '8px 12px', + border: '1px solid #ddd', + borderRadius: '6px', + fontSize: '14px' + }} + /> +
+
+
+ +