63a0df2536
Phase 1: Dead Code Cleanup - Remove GeminiGroundedProvider import and property from linkedin_service.py - Remove fallback_provider property (gemini_provider imports) - Fix routers/linkedin.py edit endpoint to use llm_text_gen - Delete dead LinkedInImageEditor class - Remove dead _transform_gemini_sources from content_generator.py Phase 2: Research Infrastructure Alignment - Add user_id to _conduct_research() for pre-flight validation - Add validate_exa_research_operations() before Exa/Tavily calls - Pass user_id to provider.simple_search() for usage tracking - Inject research content into LLM prompts via _build_research_context() - Fix Google engine path to fallback to Exa - Add Exa → Tavily fallback on research failure Phase 3: Cosmetic Cleanup - Rename _generate_prompts_with_gemini → _generate_prompts_with_llm - Rename _build_gemini_prompt → _build_image_prompt - Rename _parse_gemini_response → _parse_llm_response - Remove all Gemini references from LinkedIn code (0 remaining) - Update docstrings and log messages Additional: - Research caching using existing ResearchCache - Shared ExaContentResearchProvider in services/research/ - Persona service uses llm_text_gen instead of gemini_structured_json_response - LinkedInWriter.tsx ChatMessage → ChatMsg type mapping fix - RegisterLinkedInActionsEnhanced.tsx content_format_rules typing fix
81 lines
3.0 KiB
Python
81 lines
3.0 KiB
Python
"""
|
|
Research Handler for LinkedIn Content Generation
|
|
|
|
Handles research operations and timing for content generation.
|
|
Uses common Exa/Tavily infrastructure with pre-flight validation.
|
|
"""
|
|
|
|
from typing import List, Optional
|
|
from datetime import datetime
|
|
from loguru import logger
|
|
from models.linkedin_models import ResearchSource
|
|
|
|
|
|
class ResearchHandler:
|
|
"""Handles research operations and timing for LinkedIn content."""
|
|
|
|
def __init__(self, linkedin_service):
|
|
self.linkedin_service = linkedin_service
|
|
|
|
async def conduct_research(
|
|
self,
|
|
request,
|
|
research_enabled: bool,
|
|
search_engine: str,
|
|
max_results: int = 10,
|
|
user_id: Optional[str] = None
|
|
) -> tuple[List[ResearchSource], float]:
|
|
"""
|
|
Conduct research if enabled and return sources with timing.
|
|
|
|
Args:
|
|
request: Generation request object
|
|
research_enabled: Whether research is enabled
|
|
search_engine: Search engine to use (exa, tavily)
|
|
max_results: Maximum number of results
|
|
user_id: User ID for pre-flight validation and usage tracking
|
|
|
|
Returns:
|
|
Tuple of (research_sources, research_time)
|
|
"""
|
|
research_sources = []
|
|
research_time = 0
|
|
|
|
if research_enabled:
|
|
logger.info(f"ResearchHandler: search_engine='{search_engine}' (type: {type(search_engine)})")
|
|
|
|
research_start = datetime.now()
|
|
research_sources = await self.linkedin_service._conduct_research(
|
|
topic=request.topic,
|
|
industry=request.industry,
|
|
search_engine=search_engine,
|
|
max_results=max_results,
|
|
user_id=user_id
|
|
)
|
|
research_time = (datetime.now() - research_start).total_seconds()
|
|
logger.info(f"Research completed in {research_time:.2f}s, found {len(research_sources)} sources")
|
|
|
|
return research_sources, research_time
|
|
|
|
def determine_grounding_enabled(self, request, research_sources: List[ResearchSource]) -> bool:
|
|
"""Determine if grounding should be enabled based on request and research results."""
|
|
# Normalize values from possible Enum or string
|
|
try:
|
|
level_raw = getattr(request, 'grounding_level', 'enhanced')
|
|
level = (getattr(level_raw, 'value', level_raw) or '').strip().lower()
|
|
except Exception:
|
|
level = 'enhanced'
|
|
try:
|
|
engine_raw = getattr(request, 'search_engine', 'google')
|
|
engine_val = getattr(engine_raw, 'value', engine_raw)
|
|
engine_str = str(engine_val).split('.')[-1].strip().lower()
|
|
except Exception:
|
|
engine_str = 'google'
|
|
research_enabled = bool(getattr(request, 'research_enabled', True))
|
|
|
|
if not research_enabled or level == 'none':
|
|
return False
|
|
|
|
# For other engines, require that research actually returned sources
|
|
return bool(research_sources)
|