kunthawat/ALwrity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Research component integration, Copilotkit implementation, SEO copilotkit implementation, Wix SEO metadata complete, Wix SEO metadata review

Browse Source
This commit is contained in:
ajaysi
2025-11-03 16:01:44 +05:30
parent de4328175d
commit e69107b07c
94 changed files with 9748 additions and 1565 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
backend/services/blog_writer/outline/outline_generator.py
View File

@@ -42,10 +42,20 @@ class OutlineGenerator:
self.response_processor = ResponseProcessor()
self.parallel_processor = ParallelProcessor(self.source_mapper, self.grounding_engine)
async def generate(self, request: BlogOutlineRequest) -> BlogOutlineResponse:
async def generate(self, request: BlogOutlineRequest, user_id: str) -> BlogOutlineResponse:
"""
Generate AI-powered outline using research results
Generate AI-powered outline using research results.
Args:
request: Outline generation request with research data
user_id: User ID (required for subscription checks and usage tracking)
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for outline generation (subscription checks and usage tracking)")
# Extract research insights
research = request.research
primary_keywords = research.keyword_analysis.get('primary', [])
@@ -68,15 +78,15 @@ class OutlineGenerator:
# Define schema with proper property ordering (critical for Gemini API)
outline_schema = self.prompt_builder.get_outline_schema()
# Generate outline using structured JSON response with retry logic
outline_data = await self.response_processor.generate_with_retry(outline_prompt, outline_schema)
# Generate outline using structured JSON response with retry logic (user_id required)
outline_data = await self.response_processor.generate_with_retry(outline_prompt, outline_schema, user_id)
# Convert to BlogOutlineSection objects
outline_sections = self.response_processor.convert_to_sections(outline_data, sources)
# Run parallel processing for speed optimization
# Run parallel processing for speed optimization (user_id required)
mapped_sections, grounding_insights = await self.parallel_processor.run_parallel_processing_async(
outline_sections, research
outline_sections, research, user_id
)
# Enhance sections with grounding insights
@@ -85,9 +95,9 @@ class OutlineGenerator:
mapped_sections, research.grounding_metadata, grounding_insights
)
# Optimize outline for better flow, SEO, and engagement
# Optimize outline for better flow, SEO, and engagement (user_id required)
logger.info("Optimizing outline for better flow and engagement...")
optimized_sections = await self.outline_optimizer.optimize(grounding_enhanced_sections, "comprehensive optimization")
optimized_sections = await self.outline_optimizer.optimize(grounding_enhanced_sections, "comprehensive optimization", user_id)
# Rebalance word counts for optimal distribution
target_words = request.word_count or 1500
@@ -118,10 +128,21 @@ class OutlineGenerator:
research_coverage=research_coverage
)
async def generate_with_progress(self, request: BlogOutlineRequest, task_id: str) -> BlogOutlineResponse:
async def generate_with_progress(self, request: BlogOutlineRequest, task_id: str, user_id: str) -> BlogOutlineResponse:
"""
Outline generation method with progress updates for real-time feedback.
Args:
request: Outline generation request with research data
task_id: Task ID for progress updates
user_id: User ID (required for subscription checks and usage tracking)
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for outline generation (subscription checks and usage tracking)")
from api.blog_writer.task_manager import task_manager
# Extract research insights
@@ -150,17 +171,17 @@ class OutlineGenerator:
await task_manager.update_progress(task_id, "🔄 Making AI request to generate structured outline...")
# Generate outline using structured JSON response with retry logic
outline_data = await self.response_processor.generate_with_retry(outline_prompt, outline_schema, task_id)
# Generate outline using structured JSON response with retry logic (user_id required for subscription checks)
outline_data = await self.response_processor.generate_with_retry(outline_prompt, outline_schema, user_id, task_id)
await task_manager.update_progress(task_id, "📝 Processing outline structure and validating sections...")
# Convert to BlogOutlineSection objects
outline_sections = self.response_processor.convert_to_sections(outline_data, sources)
# Run parallel processing for speed optimization
# Run parallel processing for speed optimization (user_id required for subscription checks)
mapped_sections, grounding_insights = await self.parallel_processor.run_parallel_processing(
outline_sections, research, task_id
outline_sections, research, user_id, task_id
)
# Enhance sections with grounding insights (depends on both previous tasks)
@@ -169,9 +190,9 @@ class OutlineGenerator:
mapped_sections, research.grounding_metadata, grounding_insights
)
# Optimize outline for better flow, SEO, and engagement
# Optimize outline for better flow, SEO, and engagement (user_id required for subscription checks)
await task_manager.update_progress(task_id, "🎯 Optimizing outline for better flow and engagement...")
optimized_sections = await self.outline_optimizer.optimize(grounding_enhanced_sections, "comprehensive optimization")
optimized_sections = await self.outline_optimizer.optimize(grounding_enhanced_sections, "comprehensive optimization", user_id)
# Rebalance word counts for optimal distribution
await task_manager.update_progress(task_id, "⚖️ Rebalancing word count distribution...")

22
backend/services/blog_writer/outline/outline_optimizer.py
View File

@@ -13,8 +13,23 @@ from models.blog_models import BlogOutlineSection
class OutlineOptimizer:
"""Optimizes outlines for better flow, SEO, and engagement."""
async def optimize(self, outline: List[BlogOutlineSection], focus: str = "general optimization") -> List[BlogOutlineSection]:
"""Optimize entire outline for better flow, SEO, and engagement."""
async def optimize(self, outline: List[BlogOutlineSection], focus: str, user_id: str) -> List[BlogOutlineSection]:
"""Optimize entire outline for better flow, SEO, and engagement.
Args:
outline: List of outline sections to optimize
focus: Optimization focus (e.g., "general optimization")
user_id: User ID (required for subscription checks and usage tracking)
Returns:
List of optimized outline sections
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for outline optimization (subscription checks and usage tracking)")
outline_text = "\n".join([f"{i+1}. {s.heading}" for i, s in enumerate(outline)])
optimization_prompt = f"""Optimize this blog outline for better flow, engagement, and SEO:
@@ -67,7 +82,8 @@ Return JSON format:
optimized_data = llm_text_gen(
prompt=optimization_prompt,
json_struct=optimization_schema,
system_prompt=None
system_prompt=None,
user_id=user_id
)
# Handle the new schema format with "outline" wrapper

24
backend/services/blog_writer/outline/outline_service.py
View File

@@ -29,11 +29,21 @@ class OutlineService:
self.outline_optimizer = OutlineOptimizer()
self.section_enhancer = SectionEnhancer()
async def generate_outline(self, request: BlogOutlineRequest) -> BlogOutlineResponse:
async def generate_outline(self, request: BlogOutlineRequest, user_id: str) -> BlogOutlineResponse:
"""
Stage 2: Content Planning with AI-generated outline using research results
Uses Gemini with research data to create comprehensive, SEO-optimized outline
Stage 2: Content Planning with AI-generated outline using research results.
Uses Gemini with research data to create comprehensive, SEO-optimized outline.
Args:
request: Outline generation request with research data
user_id: User ID (required for subscription checks and usage tracking)
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for outline generation (subscription checks and usage tracking)")
# Extract cache parameters - use original user keywords for consistent caching
keywords = request.research.original_keywords or request.research.keyword_analysis.get('primary', [])
industry = getattr(request.persona, 'industry', 'general') if request.persona else 'general'
@@ -56,9 +66,9 @@ class OutlineService:
logger.info(f"Using cached outline for keywords: {keywords}")
return BlogOutlineResponse(**cached_result)
# Generate new outline if not cached
# Generate new outline if not cached (user_id required)
logger.info(f"Generating new outline for keywords: {keywords}")
result = await self.outline_generator.generate(request)
result = await self.outline_generator.generate(request, user_id)
# Cache the result
persistent_outline_cache.cache_outline(
@@ -73,7 +83,7 @@ class OutlineService:
return result
async def generate_outline_with_progress(self, request: BlogOutlineRequest, task_id: str) -> BlogOutlineResponse:
async def generate_outline_with_progress(self, request: BlogOutlineRequest, task_id: str, user_id: str) -> BlogOutlineResponse:
"""
Outline generation method with progress updates for real-time feedback.
"""
@@ -104,7 +114,7 @@ class OutlineService:
# Generate new outline if not cached
logger.info(f"Generating new outline for keywords: {keywords} (with progress updates)")
result = await self.outline_generator.generate_with_progress(request, task_id)
result = await self.outline_generator.generate_with_progress(request, task_id, user_id)
# Cache the result
persistent_outline_cache.cache_outline(

30
backend/services/blog_writer/outline/parallel_processor.py
View File

@@ -17,18 +17,25 @@ class ParallelProcessor:
self.source_mapper = source_mapper
self.grounding_engine = grounding_engine
async def run_parallel_processing(self, outline_sections, research, task_id: str = None) -> Tuple[Any, Any]:
async def run_parallel_processing(self, outline_sections, research, user_id: str, task_id: str = None) -> Tuple[Any, Any]:
"""
Run source mapping and grounding insights extraction in parallel.
Args:
outline_sections: List of outline sections to process
research: Research data object
user_id: User ID (required for subscription checks and usage tracking)
task_id: Optional task ID for progress updates
Returns:
Tuple of (mapped_sections, grounding_insights)
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for parallel processing (subscription checks and usage tracking)")
if task_id:
from api.blog_writer.task_manager import task_manager
await task_manager.update_progress(task_id, "⚡ Running parallel processing for maximum speed...")
@@ -37,7 +44,7 @@ class ParallelProcessor:
# Run these tasks in parallel to save time
source_mapping_task = asyncio.create_task(
self._run_source_mapping(outline_sections, research, task_id)
self._run_source_mapping(outline_sections, research, task_id, user_id)
)
grounding_insights_task = asyncio.create_task(
@@ -52,22 +59,29 @@ class ParallelProcessor:
return mapped_sections, grounding_insights
async def run_parallel_processing_async(self, outline_sections, research) -> Tuple[Any, Any]:
async def run_parallel_processing_async(self, outline_sections, research, user_id: str) -> Tuple[Any, Any]:
"""
Run parallel processing without progress updates (for non-progress methods).
Args:
outline_sections: List of outline sections to process
research: Research data object
user_id: User ID (required for subscription checks and usage tracking)
Returns:
Tuple of (mapped_sections, grounding_insights)
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for parallel processing (subscription checks and usage tracking)")
logger.info("Running parallel processing for maximum speed...")
# Run these tasks in parallel to save time
source_mapping_task = asyncio.create_task(
self._run_source_mapping_async(outline_sections, research)
self._run_source_mapping_async(outline_sections, research, user_id)
)
grounding_insights_task = asyncio.create_task(
@@ -82,12 +96,12 @@ class ParallelProcessor:
return mapped_sections, grounding_insights
async def _run_source_mapping(self, outline_sections, research, task_id):
async def _run_source_mapping(self, outline_sections, research, task_id, user_id: str):
"""Run source mapping in parallel."""
if task_id:
from api.blog_writer.task_manager import task_manager
await task_manager.update_progress(task_id, "🔗 Applying intelligent source-to-section mapping...")
return self.source_mapper.map_sources_to_sections(outline_sections, research)
return self.source_mapper.map_sources_to_sections(outline_sections, research, user_id)
async def _run_grounding_insights_extraction(self, research, task_id):
"""Run grounding insights extraction in parallel."""
@@ -96,10 +110,10 @@ class ParallelProcessor:
await task_manager.update_progress(task_id, "🧠 Extracting grounding metadata insights...")
return self.grounding_engine.extract_contextual_insights(research.grounding_metadata)
async def _run_source_mapping_async(self, outline_sections, research):
async def _run_source_mapping_async(self, outline_sections, research, user_id: str):
"""Run source mapping in parallel (async version without progress updates)."""
logger.info("Applying intelligent source-to-section mapping...")
return self.source_mapper.map_sources_to_sections(outline_sections, research)
return self.source_mapper.map_sources_to_sections(outline_sections, research, user_id)
async def _run_grounding_insights_extraction_async(self, research):
"""Run grounding insights extraction in parallel (async version without progress updates)."""

20
backend/services/blog_writer/outline/response_processor.py
View File

@@ -18,8 +18,21 @@ class ResponseProcessor:
"""Initialize the response processor."""
pass
async def generate_with_retry(self, prompt: str, schema: Dict[str, Any], task_id: str = None) -> Dict[str, Any]:
"""Generate outline with retry logic for API failures."""
async def generate_with_retry(self, prompt: str, schema: Dict[str, Any], user_id: str, task_id: str = None) -> Dict[str, Any]:
"""Generate outline with retry logic for API failures.
Args:
prompt: The prompt for outline generation
schema: JSON schema for structured response
user_id: User ID (required for subscription checks and usage tracking)
task_id: Optional task ID for progress updates
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for outline generation (subscription checks and usage tracking)")
from services.llm_providers.main_text_generation import llm_text_gen
from api.blog_writer.task_manager import task_manager
@@ -34,7 +47,8 @@ class ResponseProcessor:
outline_data = llm_text_gen(
prompt=prompt,
json_struct=schema,
system_prompt=None
system_prompt=None,
user_id=user_id
)
# Log response for debugging

22
backend/services/blog_writer/outline/section_enhancer.py
View File

@@ -12,8 +12,23 @@ from models.blog_models import BlogOutlineSection
class SectionEnhancer:
"""Enhances individual outline sections using AI."""
async def enhance(self, section: BlogOutlineSection, focus: str = "general improvement") -> BlogOutlineSection:
"""Enhance a section using AI with research context."""
async def enhance(self, section: BlogOutlineSection, focus: str, user_id: str) -> BlogOutlineSection:
"""Enhance a section using AI with research context.
Args:
section: Outline section to enhance
focus: Enhancement focus (e.g., "general improvement")
user_id: User ID (required for subscription checks and usage tracking)
Returns:
Enhanced outline section
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for section enhancement (subscription checks and usage tracking)")
enhancement_prompt = f"""
Enhance the following blog section to make it more engaging, comprehensive, and valuable:
@@ -61,7 +76,8 @@ class SectionEnhancer:
enhanced_data = llm_text_gen(
prompt=enhancement_prompt,
json_struct=enhancement_schema,
system_prompt=None
system_prompt=None,
user_id=user_id
)
if isinstance(enhanced_data, dict) and 'error' not in enhanced_data:

40
backend/services/blog_writer/outline/source_mapper.py
View File

@@ -52,7 +52,8 @@ class SourceToSectionMapper:
def map_sources_to_sections(
self,
sections: List[BlogOutlineSection],
research_data: BlogResearchResponse
research_data: BlogResearchResponse,
user_id: str
) -> List[BlogOutlineSection]:
"""
Map research sources to outline sections using intelligent algorithms.
@@ -60,10 +61,17 @@ class SourceToSectionMapper:
Args:
sections: List of outline sections to map sources to
research_data: Research data containing sources and metadata
user_id: User ID (required for subscription checks and usage tracking)
Returns:
List of outline sections with intelligently mapped sources
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for source mapping (subscription checks and usage tracking)")
if not sections or not research_data.sources:
logger.warning("No sections or sources to map")
return sections
@@ -73,8 +81,8 @@ class SourceToSectionMapper:
# Step 1: Algorithmic mapping
mapping_results = self._algorithmic_source_mapping(sections, research_data)
# Step 2: AI validation and improvement (single prompt)
validated_mapping = self._ai_validate_mapping(mapping_results, research_data)
# Step 2: AI validation and improvement (single prompt, user_id required for subscription checks)
validated_mapping = self._ai_validate_mapping(mapping_results, research_data, user_id)
# Step 3: Apply validated mapping to sections
mapped_sections = self._apply_mapping_to_sections(sections, validated_mapping)
@@ -261,7 +269,8 @@ class SourceToSectionMapper:
def _ai_validate_mapping(
self,
mapping_results: Dict[str, List[Tuple[ResearchSource, float]]],
research_data: BlogResearchResponse
research_data: BlogResearchResponse,
user_id: str
) -> Dict[str, List[Tuple[ResearchSource, float]]]:
"""
Use AI to validate and improve the algorithmic mapping results.
@@ -269,18 +278,25 @@ class SourceToSectionMapper:
Args:
mapping_results: Algorithmic mapping results
research_data: Research data for context
user_id: User ID (required for subscription checks and usage tracking)
Returns:
AI-validated and improved mapping results
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for AI validation (subscription checks and usage tracking)")
try:
logger.info("Starting AI validation of source-to-section mapping...")
# Build AI validation prompt
validation_prompt = self._build_validation_prompt(mapping_results, research_data)
# Get AI validation response
validation_response = self._get_ai_validation_response(validation_prompt)
# Get AI validation response (user_id required for subscription checks)
validation_response = self._get_ai_validation_response(validation_prompt, user_id)
# Parse and apply AI validation results
validated_mapping = self._parse_validation_response(validation_response, mapping_results, research_data)
@@ -548,23 +564,31 @@ Analyze the mapping and provide your recommendations.
return prompt
def _get_ai_validation_response(self, prompt: str) -> str:
def _get_ai_validation_response(self, prompt: str, user_id: str) -> str:
"""
Get AI validation response using LLM provider.
Args:
prompt: Validation prompt
user_id: User ID (required for subscription checks and usage tracking)
Returns:
AI validation response
Raises:
ValueError: If user_id is not provided
"""
if not user_id:
raise ValueError("user_id is required for AI validation response (subscription checks and usage tracking)")
try:
from services.llm_providers.main_text_generation import llm_text_gen
response = llm_text_gen(
prompt=prompt,
json_struct=None,
system_prompt=None
system_prompt=None,
user_id=user_id
)
return response