Added video studio router and endpoints. Added research router and endpoints. Added youtube router and endpoints. Added onboarding utils router and endpoints. Added onboarding utils service. Added onboarding utils models. Added onboarding utils routes. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils. Added onboarding utils utils.
This commit is contained in:
ajaysi
@@ -40,26 +40,43 @@ class Step3ResearchService:
|
||||
async def discover_competitors_for_onboarding(
|
||||
self,
|
||||
user_url: str,
|
||||
session_id: str,
|
||||
user_id: str,
|
||||
industry_context: Optional[str] = None,
|
||||
num_results: int = 25,
|
||||
website_analysis_data: Optional[Dict[str, Any]] = None
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Discover competitors for onboarding Step 3.
|
||||
|
||||
|
||||
Args:
|
||||
user_url: The user's website URL
|
||||
session_id: Onboarding session ID
|
||||
user_id: Clerk user ID for finding the correct session
|
||||
industry_context: Industry context for better discovery
|
||||
num_results: Number of competitors to discover
|
||||
|
||||
|
||||
Returns:
|
||||
Dictionary containing competitor discovery results
|
||||
"""
|
||||
try:
|
||||
logger.info(f"Starting research analysis for session {session_id}, URL: {user_url}")
|
||||
|
||||
logger.info(f"Starting research analysis for user {user_id}, URL: {user_url}")
|
||||
|
||||
# Find the correct onboarding session for this user
|
||||
with get_db_session() as db:
|
||||
from models.onboarding import OnboardingSession
|
||||
session = db.query(OnboardingSession).filter(
|
||||
OnboardingSession.user_id == user_id
|
||||
).first()
|
||||
|
||||
if not session:
|
||||
logger.error(f"No onboarding session found for user {user_id}")
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"No onboarding session found for user {user_id}"
|
||||
}
|
||||
|
||||
actual_session_id = str(session.id) # Convert to string for consistency
|
||||
logger.info(f"Found onboarding session {actual_session_id} for user {user_id}")
|
||||
|
||||
# Step 1: Discover social media accounts
|
||||
logger.info("Step 1: Discovering social media accounts...")
|
||||
social_media_results = await self.exa_service.discover_social_media_accounts(user_url)
|
||||
@@ -92,7 +109,7 @@ class Step3ResearchService:
|
||||
|
||||
# Store research data in database
|
||||
await self._store_research_data(
|
||||
session_id=session_id,
|
||||
session_id=actual_session_id,
|
||||
user_url=user_url,
|
||||
competitors=enhanced_competitors,
|
||||
industry_context=industry_context,
|
||||
@@ -108,11 +125,11 @@ class Step3ResearchService:
|
||||
industry_context
|
||||
)
|
||||
|
||||
logger.info(f"Successfully discovered {len(enhanced_competitors)} competitors for session {session_id}")
|
||||
|
||||
logger.info(f"Successfully discovered {len(enhanced_competitors)} competitors for user {user_id}")
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"session_id": session_id,
|
||||
"session_id": actual_session_id,
|
||||
"user_url": user_url,
|
||||
"competitors": enhanced_competitors,
|
||||
"social_media_accounts": social_media_results.get("social_media_accounts", {}),
|
||||
@@ -129,7 +146,7 @@ class Step3ResearchService:
|
||||
return {
|
||||
"success": False,
|
||||
"error": str(e),
|
||||
"session_id": session_id,
|
||||
"session_id": actual_session_id if 'actual_session_id' in locals() else session_id,
|
||||
"user_url": user_url
|
||||
}
|
||||
|
||||
@@ -398,38 +415,62 @@ class Step3ResearchService:
|
||||
"""
|
||||
try:
|
||||
with get_db_session() as db:
|
||||
# Get or create onboarding session
|
||||
# Get onboarding session
|
||||
session = db.query(OnboardingSession).filter(
|
||||
OnboardingSession.id == session_id
|
||||
OnboardingSession.id == int(session_id)
|
||||
).first()
|
||||
|
||||
|
||||
if not session:
|
||||
logger.error(f"Onboarding session {session_id} not found")
|
||||
return False
|
||||
|
||||
# Update session with research data
|
||||
research_data = {
|
||||
"step3_research_data": {
|
||||
"user_url": user_url,
|
||||
"competitors": competitors,
|
||||
"industry_context": industry_context,
|
||||
"analysis_metadata": analysis_metadata,
|
||||
"completed_at": datetime.utcnow().isoformat()
|
||||
}
|
||||
|
||||
# Store each competitor in CompetitorAnalysis table
|
||||
from models.onboarding import CompetitorAnalysis
|
||||
|
||||
for competitor in competitors:
|
||||
# Create competitor analysis record
|
||||
competitor_record = CompetitorAnalysis(
|
||||
session_id=session.id,
|
||||
competitor_url=competitor.get("url", ""),
|
||||
competitor_domain=competitor.get("domain", ""),
|
||||
analysis_data={
|
||||
"title": competitor.get("title", ""),
|
||||
"summary": competitor.get("summary", ""),
|
||||
"relevance_score": competitor.get("relevance_score", 0.5),
|
||||
"highlights": competitor.get("highlights", []),
|
||||
"favicon": competitor.get("favicon"),
|
||||
"image": competitor.get("image"),
|
||||
"published_date": competitor.get("published_date"),
|
||||
"author": competitor.get("author"),
|
||||
"competitive_analysis": competitor.get("competitive_insights", {}),
|
||||
"content_insights": competitor.get("content_insights", {}),
|
||||
"industry_context": industry_context,
|
||||
"analysis_metadata": analysis_metadata,
|
||||
"completed_at": datetime.utcnow().isoformat()
|
||||
}
|
||||
)
|
||||
|
||||
db.add(competitor_record)
|
||||
|
||||
# Store summary in session for quick access (backward compatibility)
|
||||
research_summary = {
|
||||
"user_url": user_url,
|
||||
"total_competitors": len(competitors),
|
||||
"industry_context": industry_context,
|
||||
"completed_at": datetime.utcnow().isoformat(),
|
||||
"analysis_metadata": analysis_metadata
|
||||
}
|
||||
|
||||
# Merge with existing data
|
||||
if session.step_data:
|
||||
session.step_data.update(research_data)
|
||||
else:
|
||||
session.step_data = research_data
|
||||
|
||||
|
||||
# Store summary in session (this requires step_data field to exist)
|
||||
# For now, we'll skip this since the model doesn't have step_data
|
||||
# TODO: Add step_data JSON column to OnboardingSession model if needed
|
||||
|
||||
db.commit()
|
||||
logger.info(f"Research data stored for session {session_id}")
|
||||
logger.info(f"Stored {len(competitors)} competitors in CompetitorAnalysis table for session {session_id}")
|
||||
return True
|
||||
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error storing research data: {str(e)}")
|
||||
logger.error(f"Error storing research data: {str(e)}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def get_research_data(self, session_id: str) -> Dict[str, Any]:
|
||||
|
||||
@@ -117,7 +117,7 @@ async def discover_competitors(
|
||||
# Perform competitor discovery with Clerk user ID
|
||||
result = await step3_research_service.discover_competitors_for_onboarding(
|
||||
user_url=request.user_url,
|
||||
session_id=clerk_user_id, # Use Clerk user ID for isolation
|
||||
user_id=clerk_user_id, # Use Clerk user ID to find correct session
|
||||
industry_context=request.industry_context,
|
||||
num_results=request.num_results,
|
||||
website_analysis_data=request.website_analysis_data
|
||||
|
||||
14
backend/api/research/__init__.py
Normal file
14
backend/api/research/__init__.py
Normal file
@@ -0,0 +1,14 @@
|
||||
"""
|
||||
Research API Module
|
||||
|
||||
Standalone API endpoints for the Research Engine.
|
||||
Can be used by any tool or directly via API.
|
||||
|
||||
Author: ALwrity Team
|
||||
Version: 2.0
|
||||
"""
|
||||
|
||||
from .router import router
|
||||
|
||||
__all__ = ["router"]
|
||||
|
||||
739
backend/api/research/router.py
Normal file
739
backend/api/research/router.py
Normal file
@@ -0,0 +1,739 @@
|
||||
"""
|
||||
Research API Router
|
||||
|
||||
Standalone API endpoints for the Research Engine.
|
||||
These endpoints can be used by:
|
||||
- Frontend Research UI
|
||||
- Blog Writer (via adapter)
|
||||
- Podcast Maker
|
||||
- YouTube Creator
|
||||
- Any other content tool
|
||||
|
||||
Author: ALwrity Team
|
||||
Version: 2.0
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, BackgroundTasks
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import Optional, List, Dict, Any
|
||||
from loguru import logger
|
||||
import uuid
|
||||
import asyncio
|
||||
|
||||
from services.database import get_db
|
||||
from services.research.core import (
|
||||
ResearchEngine,
|
||||
ResearchContext,
|
||||
ResearchPersonalizationContext,
|
||||
ContentType,
|
||||
ResearchGoal,
|
||||
ResearchDepth,
|
||||
ProviderPreference,
|
||||
)
|
||||
from services.research.core.research_context import ResearchResult
|
||||
from middleware.auth_middleware import get_current_user
|
||||
|
||||
# Intent-driven research imports
|
||||
from models.research_intent_models import (
|
||||
ResearchIntent,
|
||||
IntentInferenceRequest,
|
||||
IntentInferenceResponse,
|
||||
IntentDrivenResearchResult,
|
||||
ResearchQuery,
|
||||
ExpectedDeliverable,
|
||||
ResearchPurpose,
|
||||
ContentOutput,
|
||||
ResearchDepthLevel,
|
||||
)
|
||||
from services.research.intent import (
|
||||
ResearchIntentInference,
|
||||
IntentQueryGenerator,
|
||||
IntentAwareAnalyzer,
|
||||
)
|
||||
|
||||
router = APIRouter(prefix="/api/research", tags=["Research Engine"])
|
||||
|
||||
|
||||
# Request/Response models
|
||||
class ResearchRequest(BaseModel):
|
||||
"""API request for research."""
|
||||
query: str = Field(..., description="Main research query or topic")
|
||||
keywords: List[str] = Field(default_factory=list, description="Additional keywords")
|
||||
|
||||
# Research configuration
|
||||
goal: Optional[str] = Field(default="factual", description="Research goal: factual, trending, competitive, etc.")
|
||||
depth: Optional[str] = Field(default="standard", description="Research depth: quick, standard, comprehensive, expert")
|
||||
provider: Optional[str] = Field(default="auto", description="Provider preference: auto, exa, tavily, google")
|
||||
|
||||
# Personalization
|
||||
content_type: Optional[str] = Field(default="general", description="Content type: blog, podcast, video, etc.")
|
||||
industry: Optional[str] = None
|
||||
target_audience: Optional[str] = None
|
||||
tone: Optional[str] = None
|
||||
|
||||
# Constraints
|
||||
max_sources: int = Field(default=10, ge=1, le=25)
|
||||
recency: Optional[str] = None # day, week, month, year
|
||||
|
||||
# Domain filtering
|
||||
include_domains: List[str] = Field(default_factory=list)
|
||||
exclude_domains: List[str] = Field(default_factory=list)
|
||||
|
||||
# Advanced mode
|
||||
advanced_mode: bool = False
|
||||
|
||||
# Raw provider parameters (only if advanced_mode=True)
|
||||
exa_category: Optional[str] = None
|
||||
exa_search_type: Optional[str] = None
|
||||
tavily_topic: Optional[str] = None
|
||||
tavily_search_depth: Optional[str] = None
|
||||
tavily_include_answer: bool = False
|
||||
tavily_time_range: Optional[str] = None
|
||||
|
||||
|
||||
class ResearchResponse(BaseModel):
|
||||
"""API response for research."""
|
||||
success: bool
|
||||
task_id: Optional[str] = None # For async requests
|
||||
|
||||
# Results (if synchronous)
|
||||
sources: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
keyword_analysis: Dict[str, Any] = Field(default_factory=dict)
|
||||
competitor_analysis: Dict[str, Any] = Field(default_factory=dict)
|
||||
suggested_angles: List[str] = Field(default_factory=list)
|
||||
|
||||
# Metadata
|
||||
provider_used: Optional[str] = None
|
||||
search_queries: List[str] = Field(default_factory=list)
|
||||
|
||||
# Error handling
|
||||
error_message: Optional[str] = None
|
||||
error_code: Optional[str] = None
|
||||
|
||||
|
||||
class ProviderStatusResponse(BaseModel):
|
||||
"""API response for provider status."""
|
||||
exa: Dict[str, Any]
|
||||
tavily: Dict[str, Any]
|
||||
google: Dict[str, Any]
|
||||
|
||||
|
||||
# In-memory task storage for async research
|
||||
_research_tasks: Dict[str, Dict[str, Any]] = {}
|
||||
|
||||
|
||||
def _convert_to_research_context(request: ResearchRequest, user_id: str) -> ResearchContext:
|
||||
"""Convert API request to ResearchContext."""
|
||||
|
||||
# Map string enums
|
||||
goal_map = {
|
||||
"factual": ResearchGoal.FACTUAL,
|
||||
"trending": ResearchGoal.TRENDING,
|
||||
"competitive": ResearchGoal.COMPETITIVE,
|
||||
"educational": ResearchGoal.EDUCATIONAL,
|
||||
"technical": ResearchGoal.TECHNICAL,
|
||||
"inspirational": ResearchGoal.INSPIRATIONAL,
|
||||
}
|
||||
|
||||
depth_map = {
|
||||
"quick": ResearchDepth.QUICK,
|
||||
"standard": ResearchDepth.STANDARD,
|
||||
"comprehensive": ResearchDepth.COMPREHENSIVE,
|
||||
"expert": ResearchDepth.EXPERT,
|
||||
}
|
||||
|
||||
provider_map = {
|
||||
"auto": ProviderPreference.AUTO,
|
||||
"exa": ProviderPreference.EXA,
|
||||
"tavily": ProviderPreference.TAVILY,
|
||||
"google": ProviderPreference.GOOGLE,
|
||||
"hybrid": ProviderPreference.HYBRID,
|
||||
}
|
||||
|
||||
content_type_map = {
|
||||
"blog": ContentType.BLOG,
|
||||
"podcast": ContentType.PODCAST,
|
||||
"video": ContentType.VIDEO,
|
||||
"social": ContentType.SOCIAL,
|
||||
"email": ContentType.EMAIL,
|
||||
"newsletter": ContentType.NEWSLETTER,
|
||||
"whitepaper": ContentType.WHITEPAPER,
|
||||
"general": ContentType.GENERAL,
|
||||
}
|
||||
|
||||
# Build personalization context
|
||||
personalization = ResearchPersonalizationContext(
|
||||
creator_id=user_id,
|
||||
content_type=content_type_map.get(request.content_type or "general", ContentType.GENERAL),
|
||||
industry=request.industry,
|
||||
target_audience=request.target_audience,
|
||||
tone=request.tone,
|
||||
)
|
||||
|
||||
return ResearchContext(
|
||||
query=request.query,
|
||||
keywords=request.keywords,
|
||||
goal=goal_map.get(request.goal or "factual", ResearchGoal.FACTUAL),
|
||||
depth=depth_map.get(request.depth or "standard", ResearchDepth.STANDARD),
|
||||
provider_preference=provider_map.get(request.provider or "auto", ProviderPreference.AUTO),
|
||||
personalization=personalization,
|
||||
max_sources=request.max_sources,
|
||||
recency=request.recency,
|
||||
include_domains=request.include_domains,
|
||||
exclude_domains=request.exclude_domains,
|
||||
advanced_mode=request.advanced_mode,
|
||||
exa_category=request.exa_category,
|
||||
exa_search_type=request.exa_search_type,
|
||||
tavily_topic=request.tavily_topic,
|
||||
tavily_search_depth=request.tavily_search_depth,
|
||||
tavily_include_answer=request.tavily_include_answer,
|
||||
tavily_time_range=request.tavily_time_range,
|
||||
)
|
||||
|
||||
|
||||
@router.get("/providers/status", response_model=ProviderStatusResponse)
|
||||
async def get_provider_status():
|
||||
"""
|
||||
Get status of available research providers.
|
||||
|
||||
Returns availability and priority of Exa, Tavily, and Google providers.
|
||||
"""
|
||||
engine = ResearchEngine()
|
||||
return engine.get_provider_status()
|
||||
|
||||
|
||||
@router.post("/execute", response_model=ResearchResponse)
|
||||
async def execute_research(
|
||||
request: ResearchRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Execute research synchronously.
|
||||
|
||||
For quick research needs. For longer research, use /start endpoint.
|
||||
"""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = str(current_user.get('id', ''))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID in authentication token")
|
||||
|
||||
logger.info(f"[Research API] Execute request: {request.query[:50]}...")
|
||||
|
||||
engine = ResearchEngine()
|
||||
context = _convert_to_research_context(request, user_id)
|
||||
|
||||
result = await engine.research(context)
|
||||
|
||||
return ResearchResponse(
|
||||
success=result.success,
|
||||
sources=result.sources,
|
||||
keyword_analysis=result.keyword_analysis,
|
||||
competitor_analysis=result.competitor_analysis,
|
||||
suggested_angles=result.suggested_angles,
|
||||
provider_used=result.provider_used,
|
||||
search_queries=result.search_queries,
|
||||
error_message=result.error_message,
|
||||
error_code=result.error_code,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Research API] Execute failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.post("/start", response_model=ResearchResponse)
|
||||
async def start_research(
|
||||
request: ResearchRequest,
|
||||
background_tasks: BackgroundTasks,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Start research asynchronously.
|
||||
|
||||
Returns a task_id that can be used to poll for status.
|
||||
Use this for comprehensive research that may take longer.
|
||||
"""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = str(current_user.get('id', ''))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID in authentication token")
|
||||
|
||||
logger.info(f"[Research API] Start async request: {request.query[:50]}...")
|
||||
|
||||
task_id = str(uuid.uuid4())
|
||||
|
||||
# Initialize task
|
||||
_research_tasks[task_id] = {
|
||||
"status": "pending",
|
||||
"progress_messages": [],
|
||||
"result": None,
|
||||
"error": None,
|
||||
}
|
||||
|
||||
# Start background task
|
||||
context = _convert_to_research_context(request, user_id)
|
||||
background_tasks.add_task(_run_research_task, task_id, context)
|
||||
|
||||
return ResearchResponse(
|
||||
success=True,
|
||||
task_id=task_id,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Research API] Start failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
async def _run_research_task(task_id: str, context: ResearchContext):
|
||||
"""Background task to run research."""
|
||||
try:
|
||||
_research_tasks[task_id]["status"] = "running"
|
||||
|
||||
def progress_callback(message: str):
|
||||
_research_tasks[task_id]["progress_messages"].append(message)
|
||||
|
||||
engine = ResearchEngine()
|
||||
result = await engine.research(context, progress_callback=progress_callback)
|
||||
|
||||
_research_tasks[task_id]["status"] = "completed"
|
||||
_research_tasks[task_id]["result"] = result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Research API] Task {task_id} failed: {e}")
|
||||
_research_tasks[task_id]["status"] = "failed"
|
||||
_research_tasks[task_id]["error"] = str(e)
|
||||
|
||||
|
||||
@router.get("/status/{task_id}")
|
||||
async def get_research_status(task_id: str):
|
||||
"""
|
||||
Get status of an async research task.
|
||||
|
||||
Poll this endpoint to get progress updates and final results.
|
||||
"""
|
||||
if task_id not in _research_tasks:
|
||||
raise HTTPException(status_code=404, detail="Task not found")
|
||||
|
||||
task = _research_tasks[task_id]
|
||||
|
||||
response = {
|
||||
"task_id": task_id,
|
||||
"status": task["status"],
|
||||
"progress_messages": task["progress_messages"],
|
||||
}
|
||||
|
||||
if task["status"] == "completed" and task["result"]:
|
||||
result = task["result"]
|
||||
response["result"] = {
|
||||
"success": result.success,
|
||||
"sources": result.sources,
|
||||
"keyword_analysis": result.keyword_analysis,
|
||||
"competitor_analysis": result.competitor_analysis,
|
||||
"suggested_angles": result.suggested_angles,
|
||||
"provider_used": result.provider_used,
|
||||
"search_queries": result.search_queries,
|
||||
}
|
||||
|
||||
# Clean up completed task after returning
|
||||
# In production, use Redis or database for persistence
|
||||
|
||||
elif task["status"] == "failed":
|
||||
response["error"] = task["error"]
|
||||
|
||||
return response
|
||||
|
||||
|
||||
@router.delete("/status/{task_id}")
|
||||
async def cancel_research(task_id: str):
|
||||
"""
|
||||
Cancel a running research task.
|
||||
"""
|
||||
if task_id not in _research_tasks:
|
||||
raise HTTPException(status_code=404, detail="Task not found")
|
||||
|
||||
task = _research_tasks[task_id]
|
||||
|
||||
if task["status"] in ["pending", "running"]:
|
||||
task["status"] = "cancelled"
|
||||
return {"message": "Task cancelled", "task_id": task_id}
|
||||
|
||||
return {"message": f"Task already {task['status']}", "task_id": task_id}
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# Intent-Driven Research Endpoints
|
||||
# ============================================================================
|
||||
|
||||
class AnalyzeIntentRequest(BaseModel):
|
||||
"""Request to analyze user research intent."""
|
||||
user_input: str = Field(..., description="User's keywords, question, or goal")
|
||||
keywords: List[str] = Field(default_factory=list, description="Extracted keywords")
|
||||
use_persona: bool = Field(True, description="Use research persona for context")
|
||||
use_competitor_data: bool = Field(True, description="Use competitor data for context")
|
||||
|
||||
|
||||
class AnalyzeIntentResponse(BaseModel):
|
||||
"""Response from intent analysis."""
|
||||
success: bool
|
||||
intent: Dict[str, Any]
|
||||
analysis_summary: str
|
||||
suggested_queries: List[Dict[str, Any]]
|
||||
suggested_keywords: List[str]
|
||||
suggested_angles: List[str]
|
||||
quick_options: List[Dict[str, Any]]
|
||||
error_message: Optional[str] = None
|
||||
|
||||
|
||||
class IntentDrivenResearchRequest(BaseModel):
|
||||
"""Request for intent-driven research."""
|
||||
# Intent from previous analyze step, or minimal input for auto-inference
|
||||
user_input: str = Field(..., description="User's original input")
|
||||
|
||||
# Optional: Confirmed intent from UI (if user modified the inferred intent)
|
||||
confirmed_intent: Optional[Dict[str, Any]] = None
|
||||
|
||||
# Optional: Specific queries to run (if user selected from suggested)
|
||||
selected_queries: Optional[List[Dict[str, Any]]] = None
|
||||
|
||||
# Research configuration
|
||||
max_sources: int = Field(default=10, ge=1, le=25)
|
||||
include_domains: List[str] = Field(default_factory=list)
|
||||
exclude_domains: List[str] = Field(default_factory=list)
|
||||
|
||||
# Skip intent inference (for re-runs with same intent)
|
||||
skip_inference: bool = False
|
||||
|
||||
|
||||
class IntentDrivenResearchResponse(BaseModel):
|
||||
"""Response from intent-driven research."""
|
||||
success: bool
|
||||
|
||||
# Direct answers
|
||||
primary_answer: str = ""
|
||||
secondary_answers: Dict[str, str] = Field(default_factory=dict)
|
||||
|
||||
# Deliverables
|
||||
statistics: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
expert_quotes: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
case_studies: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
trends: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
comparisons: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
best_practices: List[str] = Field(default_factory=list)
|
||||
step_by_step: List[str] = Field(default_factory=list)
|
||||
pros_cons: Optional[Dict[str, Any]] = None
|
||||
definitions: Dict[str, str] = Field(default_factory=dict)
|
||||
examples: List[str] = Field(default_factory=list)
|
||||
predictions: List[str] = Field(default_factory=list)
|
||||
|
||||
# Content-ready outputs
|
||||
executive_summary: str = ""
|
||||
key_takeaways: List[str] = Field(default_factory=list)
|
||||
suggested_outline: List[str] = Field(default_factory=list)
|
||||
|
||||
# Sources and metadata
|
||||
sources: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
confidence: float = 0.8
|
||||
gaps_identified: List[str] = Field(default_factory=list)
|
||||
follow_up_queries: List[str] = Field(default_factory=list)
|
||||
|
||||
# The inferred/confirmed intent
|
||||
intent: Optional[Dict[str, Any]] = None
|
||||
|
||||
# Error handling
|
||||
error_message: Optional[str] = None
|
||||
|
||||
|
||||
@router.post("/intent/analyze", response_model=AnalyzeIntentResponse)
|
||||
async def analyze_research_intent(
|
||||
request: AnalyzeIntentRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Analyze user input to understand research intent.
|
||||
|
||||
This endpoint uses AI to infer what the user really wants from their research:
|
||||
- What questions need answering
|
||||
- What deliverables they expect (statistics, quotes, case studies, etc.)
|
||||
- What depth and focus is appropriate
|
||||
|
||||
The response includes quick options that can be shown in the UI for user confirmation.
|
||||
"""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = str(current_user.get('id', ''))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID")
|
||||
|
||||
logger.info(f"[Intent API] Analyzing intent for: {request.user_input[:50]}...")
|
||||
|
||||
# Get research persona if requested
|
||||
research_persona = None
|
||||
competitor_data = None
|
||||
|
||||
if request.use_persona or request.use_competitor_data:
|
||||
from services.research.research_persona_service import ResearchPersonaService
|
||||
from services.onboarding_service import OnboardingService
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
# Get database session
|
||||
db = next(get_db())
|
||||
try:
|
||||
persona_service = ResearchPersonaService(db)
|
||||
onboarding_service = OnboardingService()
|
||||
|
||||
if request.use_persona:
|
||||
research_persona = persona_service.get_or_generate(user_id)
|
||||
|
||||
if request.use_competitor_data:
|
||||
competitor_data = onboarding_service.get_competitor_analysis(user_id, db)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# Infer intent
|
||||
intent_service = ResearchIntentInference()
|
||||
response = await intent_service.infer_intent(
|
||||
user_input=request.user_input,
|
||||
keywords=request.keywords,
|
||||
research_persona=research_persona,
|
||||
competitor_data=competitor_data,
|
||||
industry=research_persona.default_industry if research_persona else None,
|
||||
target_audience=research_persona.default_target_audience if research_persona else None,
|
||||
)
|
||||
|
||||
# Generate targeted queries
|
||||
query_generator = IntentQueryGenerator()
|
||||
query_result = await query_generator.generate_queries(
|
||||
intent=response.intent,
|
||||
research_persona=research_persona,
|
||||
)
|
||||
|
||||
# Update response with queries
|
||||
response.suggested_queries = [q.dict() for q in query_result.get("queries", [])]
|
||||
response.suggested_keywords = query_result.get("enhanced_keywords", [])
|
||||
response.suggested_angles = query_result.get("research_angles", [])
|
||||
|
||||
return AnalyzeIntentResponse(
|
||||
success=True,
|
||||
intent=response.intent.dict(),
|
||||
analysis_summary=response.analysis_summary,
|
||||
suggested_queries=response.suggested_queries,
|
||||
suggested_keywords=response.suggested_keywords,
|
||||
suggested_angles=response.suggested_angles,
|
||||
quick_options=response.quick_options,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Intent API] Analyze failed: {e}")
|
||||
return AnalyzeIntentResponse(
|
||||
success=False,
|
||||
intent={},
|
||||
analysis_summary="",
|
||||
suggested_queries=[],
|
||||
suggested_keywords=[],
|
||||
suggested_angles=[],
|
||||
quick_options=[],
|
||||
error_message=str(e),
|
||||
)
|
||||
|
||||
|
||||
@router.post("/intent/research", response_model=IntentDrivenResearchResponse)
|
||||
async def execute_intent_driven_research(
|
||||
request: IntentDrivenResearchRequest,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
Execute research based on user intent.
|
||||
|
||||
This is the main endpoint for intent-driven research. It:
|
||||
1. Uses the confirmed intent (or infers from user_input if not provided)
|
||||
2. Generates targeted queries for each expected deliverable
|
||||
3. Executes research using Exa/Tavily/Google
|
||||
4. Analyzes results through the lens of user intent
|
||||
5. Returns exactly what the user needs
|
||||
|
||||
The response is organized by deliverable type (statistics, quotes, case studies, etc.)
|
||||
instead of generic search results.
|
||||
"""
|
||||
try:
|
||||
if not current_user:
|
||||
raise HTTPException(status_code=401, detail="Authentication required")
|
||||
|
||||
user_id = str(current_user.get('id', ''))
|
||||
if not user_id:
|
||||
raise HTTPException(status_code=401, detail="Invalid user ID")
|
||||
|
||||
logger.info(f"[Intent API] Executing intent-driven research for: {request.user_input[:50]}...")
|
||||
|
||||
# Get database session
|
||||
db = next(get_db())
|
||||
|
||||
try:
|
||||
# Get research persona
|
||||
from services.research.research_persona_service import ResearchPersonaService
|
||||
persona_service = ResearchPersonaService(db)
|
||||
research_persona = persona_service.get_or_generate(user_id)
|
||||
|
||||
# Determine intent
|
||||
if request.confirmed_intent:
|
||||
# Use confirmed intent from UI
|
||||
intent = ResearchIntent(**request.confirmed_intent)
|
||||
elif not request.skip_inference:
|
||||
# Infer intent from user input
|
||||
intent_service = ResearchIntentInference()
|
||||
intent_response = await intent_service.infer_intent(
|
||||
user_input=request.user_input,
|
||||
research_persona=research_persona,
|
||||
)
|
||||
intent = intent_response.intent
|
||||
else:
|
||||
# Create basic intent from input
|
||||
intent = ResearchIntent(
|
||||
primary_question=f"What are the key insights about: {request.user_input}?",
|
||||
purpose="learn",
|
||||
content_output="general",
|
||||
expected_deliverables=["key_statistics", "best_practices", "examples"],
|
||||
depth="detailed",
|
||||
original_input=request.user_input,
|
||||
confidence=0.6,
|
||||
)
|
||||
|
||||
# Generate or use provided queries
|
||||
if request.selected_queries:
|
||||
queries = [ResearchQuery(**q) for q in request.selected_queries]
|
||||
else:
|
||||
query_generator = IntentQueryGenerator()
|
||||
query_result = await query_generator.generate_queries(
|
||||
intent=intent,
|
||||
research_persona=research_persona,
|
||||
)
|
||||
queries = query_result.get("queries", [])
|
||||
|
||||
# Execute research using the Research Engine
|
||||
engine = ResearchEngine(db_session=db)
|
||||
|
||||
# Build context from intent
|
||||
personalization = ResearchPersonalizationContext(
|
||||
creator_id=user_id,
|
||||
industry=research_persona.default_industry if research_persona else None,
|
||||
target_audience=research_persona.default_target_audience if research_persona else None,
|
||||
)
|
||||
|
||||
# Use the highest priority query for the main search
|
||||
# (In a more advanced version, we could run multiple queries and merge)
|
||||
primary_query = queries[0] if queries else ResearchQuery(
|
||||
query=request.user_input,
|
||||
purpose=ExpectedDeliverable.KEY_STATISTICS,
|
||||
provider="exa",
|
||||
priority=5,
|
||||
expected_results="General research results",
|
||||
)
|
||||
|
||||
context = ResearchContext(
|
||||
query=primary_query.query,
|
||||
keywords=request.user_input.split()[:10],
|
||||
goal=_map_purpose_to_goal(intent.purpose),
|
||||
depth=_map_depth_to_engine_depth(intent.depth),
|
||||
provider_preference=_map_provider_to_preference(primary_query.provider),
|
||||
personalization=personalization,
|
||||
max_sources=request.max_sources,
|
||||
include_domains=request.include_domains,
|
||||
exclude_domains=request.exclude_domains,
|
||||
)
|
||||
|
||||
# Execute research
|
||||
raw_result = await engine.research(context)
|
||||
|
||||
# Analyze results using intent-aware analyzer
|
||||
analyzer = IntentAwareAnalyzer()
|
||||
analyzed_result = await analyzer.analyze(
|
||||
raw_results={
|
||||
"content": raw_result.raw_content or "",
|
||||
"sources": raw_result.sources,
|
||||
"grounding_metadata": raw_result.grounding_metadata,
|
||||
},
|
||||
intent=intent,
|
||||
research_persona=research_persona,
|
||||
)
|
||||
|
||||
# Build response
|
||||
return IntentDrivenResearchResponse(
|
||||
success=True,
|
||||
primary_answer=analyzed_result.primary_answer,
|
||||
secondary_answers=analyzed_result.secondary_answers,
|
||||
statistics=[s.dict() for s in analyzed_result.statistics],
|
||||
expert_quotes=[q.dict() for q in analyzed_result.expert_quotes],
|
||||
case_studies=[cs.dict() for cs in analyzed_result.case_studies],
|
||||
trends=[t.dict() for t in analyzed_result.trends],
|
||||
comparisons=[c.dict() for c in analyzed_result.comparisons],
|
||||
best_practices=analyzed_result.best_practices,
|
||||
step_by_step=analyzed_result.step_by_step,
|
||||
pros_cons=analyzed_result.pros_cons.dict() if analyzed_result.pros_cons else None,
|
||||
definitions=analyzed_result.definitions,
|
||||
examples=analyzed_result.examples,
|
||||
predictions=analyzed_result.predictions,
|
||||
executive_summary=analyzed_result.executive_summary,
|
||||
key_takeaways=analyzed_result.key_takeaways,
|
||||
suggested_outline=analyzed_result.suggested_outline,
|
||||
sources=[s.dict() for s in analyzed_result.sources],
|
||||
confidence=analyzed_result.confidence,
|
||||
gaps_identified=analyzed_result.gaps_identified,
|
||||
follow_up_queries=analyzed_result.follow_up_queries,
|
||||
intent=intent.dict(),
|
||||
)
|
||||
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[Intent API] Research failed: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return IntentDrivenResearchResponse(
|
||||
success=False,
|
||||
error_message=str(e),
|
||||
)
|
||||
|
||||
|
||||
def _map_purpose_to_goal(purpose: str) -> ResearchGoal:
|
||||
"""Map intent purpose to research goal."""
|
||||
mapping = {
|
||||
"learn": ResearchGoal.EDUCATIONAL,
|
||||
"create_content": ResearchGoal.FACTUAL,
|
||||
"make_decision": ResearchGoal.FACTUAL,
|
||||
"compare": ResearchGoal.COMPETITIVE,
|
||||
"solve_problem": ResearchGoal.EDUCATIONAL,
|
||||
"find_data": ResearchGoal.FACTUAL,
|
||||
"explore_trends": ResearchGoal.TRENDING,
|
||||
"validate": ResearchGoal.FACTUAL,
|
||||
"generate_ideas": ResearchGoal.INSPIRATIONAL,
|
||||
}
|
||||
return mapping.get(purpose, ResearchGoal.FACTUAL)
|
||||
|
||||
|
||||
def _map_depth_to_engine_depth(depth: str) -> ResearchDepth:
|
||||
"""Map intent depth to research engine depth."""
|
||||
mapping = {
|
||||
"overview": ResearchDepth.QUICK,
|
||||
"detailed": ResearchDepth.STANDARD,
|
||||
"expert": ResearchDepth.COMPREHENSIVE,
|
||||
}
|
||||
return mapping.get(depth, ResearchDepth.STANDARD)
|
||||
|
||||
|
||||
def _map_provider_to_preference(provider: str) -> ProviderPreference:
|
||||
"""Map query provider to engine preference."""
|
||||
mapping = {
|
||||
"exa": ProviderPreference.EXA,
|
||||
"tavily": ProviderPreference.TAVILY,
|
||||
"google": ProviderPreference.GOOGLE,
|
||||
}
|
||||
return mapping.get(provider, ProviderPreference.AUTO)
|
||||
|
||||
@@ -33,11 +33,18 @@ class ProviderAvailability(BaseModel):
|
||||
|
||||
|
||||
class PersonaDefaults(BaseModel):
|
||||
"""Persona-aware research defaults."""
|
||||
"""Persona-aware research defaults for hyper-personalization."""
|
||||
industry: Optional[str] = None
|
||||
target_audience: Optional[str] = None
|
||||
suggested_domains: list[str] = []
|
||||
suggested_exa_category: Optional[str] = None
|
||||
has_research_persona: bool = False # Phase 2: Indicates if research persona exists
|
||||
|
||||
# Phase 2: Additional fields from research persona for pre-filling advanced options
|
||||
default_research_mode: Optional[str] = None # basic, comprehensive, targeted
|
||||
default_provider: Optional[str] = None # exa, tavily, google
|
||||
suggested_keywords: list[str] = [] # For keyword suggestions
|
||||
research_angles: list[str] = [] # Alternative research focuses
|
||||
|
||||
|
||||
class ResearchConfigResponse(BaseModel):
|
||||
@@ -106,7 +113,12 @@ async def get_persona_defaults(
|
||||
"""
|
||||
Get persona-aware research defaults for the current user.
|
||||
|
||||
Returns industry, target audience, and smart suggestions based on onboarding data.
|
||||
Phase 2: Prioritizes research persona fields (richer defaults) over core persona.
|
||||
Since onboarding is mandatory, we always have core persona data - never return "General".
|
||||
|
||||
Returns industry, target audience, and smart suggestions based on:
|
||||
1. Research persona (if exists) - has suggested domains, Exa category, etc.
|
||||
2. Core persona (fallback) - industry and target audience from onboarding
|
||||
"""
|
||||
try:
|
||||
user_id = str(current_user.get('id'))
|
||||
@@ -114,54 +126,114 @@ async def get_persona_defaults(
|
||||
# Add explicit null check for database session
|
||||
if not db:
|
||||
logger.error(f"[ResearchConfig] Database session is None for user {user_id} in get_persona_defaults")
|
||||
# Return defaults rather than error
|
||||
# Return minimal defaults - but onboarding guarantees this won't happen
|
||||
return PersonaDefaults()
|
||||
|
||||
db_service = OnboardingDatabaseService(db=db)
|
||||
|
||||
# Try to get persona data first (most reliable source for industry/target_audience)
|
||||
# Phase 2: First check if research persona exists (cached only - don't generate here)
|
||||
# Generation happens in ResearchEngine.research() on first use
|
||||
research_persona = None
|
||||
try:
|
||||
persona_service = ResearchPersonaService(db_session=db)
|
||||
research_persona = persona_service.get_cached_only(user_id)
|
||||
except Exception as e:
|
||||
logger.debug(f"[ResearchConfig] Could not get research persona for {user_id}: {e}")
|
||||
|
||||
# If research persona exists, use its richer defaults (Phase 2: hyper-personalization)
|
||||
if research_persona:
|
||||
logger.info(f"[ResearchConfig] Using research persona defaults for user {user_id}")
|
||||
|
||||
# Ensure we never return "General" - provide meaningful defaults
|
||||
industry = research_persona.default_industry
|
||||
target_audience = research_persona.default_target_audience
|
||||
|
||||
# If persona has generic defaults, provide better ones
|
||||
if industry == "General" or not industry:
|
||||
industry = "Technology" # Safe default for content creators
|
||||
logger.info(f"[ResearchConfig] Upgrading generic industry to '{industry}' for user {user_id}")
|
||||
|
||||
if target_audience == "General" or not target_audience:
|
||||
target_audience = "Professionals and content consumers" # Better than "General"
|
||||
logger.info(f"[ResearchConfig] Upgrading generic target_audience to '{target_audience}' for user {user_id}")
|
||||
|
||||
return PersonaDefaults(
|
||||
industry=industry,
|
||||
target_audience=target_audience,
|
||||
suggested_domains=research_persona.suggested_exa_domains or [],
|
||||
suggested_exa_category=research_persona.suggested_exa_category,
|
||||
has_research_persona=True, # Frontend can use this
|
||||
# Phase 2: Additional pre-fill fields
|
||||
default_research_mode=research_persona.default_research_mode,
|
||||
default_provider=research_persona.default_provider,
|
||||
suggested_keywords=research_persona.suggested_keywords or [],
|
||||
research_angles=research_persona.research_angles or [],
|
||||
# Phase 2+: Enhanced provider-specific defaults
|
||||
suggested_exa_search_type=getattr(research_persona, 'suggested_exa_search_type', None),
|
||||
suggested_tavily_topic=getattr(research_persona, 'suggested_tavily_topic', None),
|
||||
suggested_tavily_search_depth=getattr(research_persona, 'suggested_tavily_search_depth', None),
|
||||
suggested_tavily_include_answer=getattr(research_persona, 'suggested_tavily_include_answer', None),
|
||||
suggested_tavily_time_range=getattr(research_persona, 'suggested_tavily_time_range', None),
|
||||
suggested_tavily_raw_content_format=getattr(research_persona, 'suggested_tavily_raw_content_format', None),
|
||||
provider_recommendations=getattr(research_persona, 'provider_recommendations', {}),
|
||||
)
|
||||
|
||||
# Fallback to core persona from onboarding (guaranteed to exist after onboarding)
|
||||
persona_data = db_service.get_persona_data(user_id, db)
|
||||
industry = 'General'
|
||||
target_audience = 'General'
|
||||
industry = None
|
||||
target_audience = None
|
||||
|
||||
if persona_data:
|
||||
core_persona = persona_data.get('corePersona') or persona_data.get('core_persona')
|
||||
if core_persona:
|
||||
if core_persona.get('industry'):
|
||||
industry = core_persona['industry']
|
||||
if core_persona.get('target_audience'):
|
||||
target_audience = core_persona['target_audience']
|
||||
industry = core_persona.get('industry')
|
||||
target_audience = core_persona.get('target_audience')
|
||||
|
||||
# Fallback to website analysis if persona data doesn't have industry info
|
||||
if industry == 'General':
|
||||
# Fallback to website analysis if core persona doesn't have industry
|
||||
if not industry:
|
||||
website_analysis = db_service.get_website_analysis(user_id, db)
|
||||
if website_analysis:
|
||||
target_audience_data = website_analysis.get('target_audience', {})
|
||||
if isinstance(target_audience_data, dict):
|
||||
# Extract from target_audience JSON field
|
||||
industry_focus = target_audience_data.get('industry_focus')
|
||||
if industry_focus:
|
||||
industry = industry_focus
|
||||
industry = target_audience_data.get('industry_focus')
|
||||
demographics = target_audience_data.get('demographics')
|
||||
if demographics:
|
||||
if demographics and not target_audience:
|
||||
target_audience = demographics if isinstance(demographics, str) else str(demographics)
|
||||
|
||||
# Phase 2: Never return "General" - use sensible defaults from onboarding or fallback
|
||||
# Since onboarding is mandatory, we should always have real data
|
||||
if not industry:
|
||||
industry = "Technology" # Safe default for content creators
|
||||
logger.warning(f"[ResearchConfig] No industry found for user {user_id}, using default")
|
||||
if not target_audience:
|
||||
target_audience = "Professionals" # Safe default
|
||||
logger.warning(f"[ResearchConfig] No target_audience found for user {user_id}, using default")
|
||||
|
||||
# Suggest domains based on industry
|
||||
suggested_domains = _get_domain_suggestions(industry)
|
||||
|
||||
# Suggest Exa category based on industry
|
||||
suggested_exa_category = _get_exa_category_suggestion(industry)
|
||||
|
||||
logger.info(f"[ResearchConfig] Using core persona defaults for user {user_id}: industry={industry}")
|
||||
|
||||
return PersonaDefaults(
|
||||
industry=industry,
|
||||
target_audience=target_audience,
|
||||
suggested_domains=suggested_domains,
|
||||
suggested_exa_category=suggested_exa_category
|
||||
suggested_exa_category=suggested_exa_category,
|
||||
has_research_persona=False # Frontend knows to trigger generation
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"[ResearchConfig] Error getting persona defaults for user {user_id if 'user_id' in locals() else 'unknown'}: {e}", exc_info=True)
|
||||
# Return defaults rather than error
|
||||
return PersonaDefaults()
|
||||
# Return sensible defaults - never "General"
|
||||
return PersonaDefaults(
|
||||
industry="Technology",
|
||||
target_audience="Professionals",
|
||||
suggested_domains=[],
|
||||
suggested_exa_category=None,
|
||||
has_research_persona=False
|
||||
)
|
||||
|
||||
|
||||
@router.get("/research-persona")
|
||||
@@ -430,7 +502,7 @@ async def get_competitor_analysis(
|
||||
success=False,
|
||||
error="Onboarding step 3 (Competitor Analysis) is not completed. Please complete onboarding step 3 first."
|
||||
)
|
||||
|
||||
|
||||
print(f"[COMPETITOR_ANALYSIS] ✅ Step 3 is completed (current_step={session.current_step} or research_preferences exists)")
|
||||
|
||||
# Try Method 1: Get competitor data from CompetitorAnalysis table using OnboardingDatabaseService
|
||||
@@ -438,11 +510,11 @@ async def get_competitor_analysis(
|
||||
print(f"[COMPETITOR_ANALYSIS] 🔍 Method 1: Querying CompetitorAnalysis table using OnboardingDatabaseService...")
|
||||
try:
|
||||
competitors = db_service.get_competitor_analysis(user_id, db)
|
||||
|
||||
|
||||
if competitors:
|
||||
print(f"[COMPETITOR_ANALYSIS] ✅ Found {len(competitors)} competitor records from CompetitorAnalysis table")
|
||||
logger.info(f"[ResearchConfig] Found {len(competitors)} competitors from CompetitorAnalysis table for user {user_id}")
|
||||
|
||||
|
||||
# Map competitor fields to match frontend expectations
|
||||
mapped_competitors = []
|
||||
for comp in competitors:
|
||||
@@ -453,7 +525,7 @@ async def get_competitor_analysis(
|
||||
"similarity_score": comp.get("relevance_score") or comp.get("similarity_score", 0.5)
|
||||
}
|
||||
mapped_competitors.append(mapped_comp)
|
||||
|
||||
|
||||
print(f"[COMPETITOR_ANALYSIS] ✅ SUCCESS: Returning {len(mapped_competitors)} competitors for user_id={user_id}")
|
||||
return CompetitorAnalysisResponse(
|
||||
success=True,
|
||||
@@ -468,7 +540,7 @@ async def get_competitor_analysis(
|
||||
)
|
||||
else:
|
||||
print(f"[COMPETITOR_ANALYSIS] ⚠️ No competitor records found in CompetitorAnalysis table for user_id={user_id}")
|
||||
|
||||
|
||||
except Exception as e:
|
||||
print(f"[COMPETITOR_ANALYSIS] ❌ EXCEPTION in Method 1: {e}")
|
||||
import traceback
|
||||
@@ -487,12 +559,12 @@ async def get_competitor_analysis(
|
||||
research_data_result = await step3_service.get_research_data(str(session.id))
|
||||
|
||||
print(f"[COMPETITOR_ANALYSIS] Step3ResearchService.get_research_data() result: success={research_data_result.get('success')}")
|
||||
|
||||
|
||||
if research_data_result.get('success'):
|
||||
# Handle both 'research_data' and 'step3_research_data' keys
|
||||
# Handle both 'research_data' and 'step3_research_data' keys
|
||||
research_data = research_data_result.get('step3_research_data') or research_data_result.get('research_data', {})
|
||||
print(f"[COMPETITOR_ANALYSIS] Research data keys: {list(research_data.keys()) if isinstance(research_data, dict) else 'Not a dict'}")
|
||||
|
||||
|
||||
if isinstance(research_data, dict) and research_data.get('competitors'):
|
||||
competitors_list = research_data.get('competitors', [])
|
||||
print(f"[COMPETITOR_ANALYSIS] ✅ Found {len(competitors_list)} competitors in step_data via Step3ResearchService")
|
||||
@@ -500,8 +572,8 @@ async def get_competitor_analysis(
|
||||
if competitors_list:
|
||||
analysis_metadata = research_data.get('analysis_metadata', {})
|
||||
social_media_data = analysis_metadata.get('social_media_data', {})
|
||||
|
||||
# Map competitor fields to match frontend expectations
|
||||
|
||||
# Map competitor fields to match frontend expectations
|
||||
mapped_competitors = []
|
||||
for comp in competitors_list:
|
||||
mapped_comp = {
|
||||
@@ -511,7 +583,7 @@ async def get_competitor_analysis(
|
||||
"similarity_score": comp.get("relevance_score") or comp.get("similarity_score", 0.5)
|
||||
}
|
||||
mapped_competitors.append(mapped_comp)
|
||||
|
||||
|
||||
print(f"[COMPETITOR_ANALYSIS] ✅ SUCCESS: Returning {len(mapped_competitors)} competitors from step_data for user_id={user_id}")
|
||||
logger.info(f"[ResearchConfig] Found {len(mapped_competitors)} competitors from step_data via Step3ResearchService for user {user_id}")
|
||||
return CompetitorAnalysisResponse(
|
||||
@@ -561,6 +633,114 @@ async def get_competitor_analysis(
|
||||
print(f"[COMPETITOR_ANALYSIS] ===== END: Getting competitor analysis for user_id={user_id} =====\n")
|
||||
|
||||
|
||||
@router.post("/competitor-analysis/refresh", response_model=CompetitorAnalysisResponse)
|
||||
async def refresh_competitor_analysis(
|
||||
current_user: Dict = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
Refresh competitor analysis by re-running competitor discovery from onboarding.
|
||||
|
||||
This endpoint re-triggers the competitor discovery process and saves the results
|
||||
to the database, allowing users to update their competitor analysis data.
|
||||
"""
|
||||
user_id = None
|
||||
try:
|
||||
user_id = str(current_user.get('id'))
|
||||
logger.info(f"[ResearchConfig] Refreshing competitor analysis for user {user_id}")
|
||||
|
||||
if not db:
|
||||
raise HTTPException(status_code=500, detail="Database session not available")
|
||||
|
||||
db_service = OnboardingDatabaseService(db=db)
|
||||
|
||||
# Get onboarding session
|
||||
session = db_service.get_session_by_user(user_id, db)
|
||||
if not session:
|
||||
return CompetitorAnalysisResponse(
|
||||
success=False,
|
||||
error="No onboarding session found. Please complete onboarding first."
|
||||
)
|
||||
|
||||
# Get website URL from website analysis
|
||||
website_analysis = db_service.get_website_analysis(user_id, db)
|
||||
if not website_analysis or not website_analysis.get('website_url'):
|
||||
return CompetitorAnalysisResponse(
|
||||
success=False,
|
||||
error="No website URL found. Please complete onboarding step 2 (Website Analysis) first."
|
||||
)
|
||||
|
||||
user_url = website_analysis.get('website_url')
|
||||
if not user_url or user_url.strip() == '':
|
||||
return CompetitorAnalysisResponse(
|
||||
success=False,
|
||||
error="Website URL is empty. Please complete onboarding step 2 (Website Analysis) first."
|
||||
)
|
||||
|
||||
# Get industry context from research preferences or persona
|
||||
research_prefs = db_service.get_research_preferences(user_id, db) or {}
|
||||
persona_data = db_service.get_persona_data(user_id, db) or {}
|
||||
core_persona = persona_data.get('corePersona') or persona_data.get('core_persona') or {}
|
||||
industry_context = core_persona.get('industry') or research_prefs.get('industry') or None
|
||||
|
||||
# Import and use Step3ResearchService to re-run competitor discovery
|
||||
from api.onboarding_utils.step3_research_service import Step3ResearchService
|
||||
|
||||
step3_service = Step3ResearchService()
|
||||
result = await step3_service.discover_competitors_for_onboarding(
|
||||
user_url=user_url,
|
||||
user_id=user_id,
|
||||
industry_context=industry_context,
|
||||
num_results=25,
|
||||
website_analysis_data=website_analysis
|
||||
)
|
||||
|
||||
if result.get("success"):
|
||||
# Get the updated competitor data from database
|
||||
competitors = db_service.get_competitor_analysis(user_id, db)
|
||||
|
||||
if competitors:
|
||||
# Map competitor fields
|
||||
mapped_competitors = []
|
||||
for comp in competitors:
|
||||
mapped_comp = {
|
||||
**comp,
|
||||
"name": comp.get("title") or comp.get("name") or comp.get("domain", ""),
|
||||
"description": comp.get("summary") or comp.get("description", ""),
|
||||
"similarity_score": comp.get("relevance_score") or comp.get("similarity_score", 0.5)
|
||||
}
|
||||
mapped_competitors.append(mapped_comp)
|
||||
|
||||
logger.info(f"[ResearchConfig] Successfully refreshed competitor analysis: {len(mapped_competitors)} competitors")
|
||||
return CompetitorAnalysisResponse(
|
||||
success=True,
|
||||
competitors=mapped_competitors,
|
||||
social_media_accounts=result.get("social_media_accounts", {}),
|
||||
social_media_citations=result.get("social_media_citations", []),
|
||||
research_summary=result.get("research_summary", {}),
|
||||
analysis_timestamp=result.get("analysis_timestamp")
|
||||
)
|
||||
else:
|
||||
return CompetitorAnalysisResponse(
|
||||
success=False,
|
||||
error="Competitor discovery completed but no data was saved. Please try again."
|
||||
)
|
||||
else:
|
||||
return CompetitorAnalysisResponse(
|
||||
success=False,
|
||||
error=result.get("error", "Failed to refresh competitor analysis")
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"[ResearchConfig] Error refreshing competitor analysis for user {user_id if user_id else 'unknown'}: {e}", exc_info=True)
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail=f"Failed to refresh competitor analysis: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
# Helper functions from RESEARCH_AI_HYPERPERSONALIZATION.md
|
||||
|
||||
def _get_domain_suggestions(industry: str) -> list[str]:
|
||||
|
||||
@@ -56,7 +56,9 @@ class TaskManager:
|
||||
self.cleanup_old_tasks()
|
||||
|
||||
if task_id not in self.task_storage:
|
||||
logger.warning(f"[StoryWriter] Task not found: {task_id}")
|
||||
# Log at DEBUG level - task not found is expected when tasks expire or are cleaned up
|
||||
# This prevents log spam from frontend polling for expired/completed tasks
|
||||
logger.debug(f"[StoryWriter] Task not found: {task_id} (may have expired or been cleaned up)")
|
||||
return None
|
||||
|
||||
task = self.task_storage[task_id]
|
||||
|
||||
@@ -31,17 +31,21 @@ def generate_hd_video_payload(request: Any, user_id: str) -> Dict[str, Any]:
|
||||
kwargs["seed"] = request.seed
|
||||
|
||||
logger.info(f"[StoryWriter] Generating HD video via {getattr(request, 'provider', 'huggingface')} for user {user_id}")
|
||||
raw_bytes = ai_video_generate(
|
||||
result = ai_video_generate(
|
||||
prompt=request.prompt,
|
||||
operation_type="text-to-video",
|
||||
provider=getattr(request, "provider", None) or "huggingface",
|
||||
user_id=user_id,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
# Extract video bytes from result dict
|
||||
video_bytes = result["video_bytes"]
|
||||
|
||||
filename = f"hd_{uuid4().hex}.mp4"
|
||||
file_path = output_dir / filename
|
||||
with open(file_path, "wb") as fh:
|
||||
fh.write(raw_bytes)
|
||||
fh.write(video_bytes)
|
||||
|
||||
logger.info(f"[StoryWriter] HD video saved to {file_path}")
|
||||
return {
|
||||
@@ -111,16 +115,20 @@ def generate_hd_video_scene_payload(request: Any, user_id: str) -> Dict[str, Any
|
||||
if getattr(request, "seed", None) is not None:
|
||||
kwargs["seed"] = request.seed
|
||||
|
||||
raw_bytes = ai_video_generate(
|
||||
result = ai_video_generate(
|
||||
prompt=enhanced_prompt,
|
||||
operation_type="text-to-video",
|
||||
provider=getattr(request, "provider", None) or "huggingface",
|
||||
user_id=user_id,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
# Extract video bytes from result dict
|
||||
video_bytes = result["video_bytes"]
|
||||
|
||||
video_service = StoryVideoGenerationService()
|
||||
save_result = video_service.save_scene_video(
|
||||
video_bytes=raw_bytes,
|
||||
video_bytes=video_bytes,
|
||||
scene_number=scene_number,
|
||||
user_id=user_id,
|
||||
)
|
||||
|
||||
@@ -26,6 +26,76 @@ YOUTUBE_AUDIO_DIR.mkdir(parents=True, exist_ok=True)
|
||||
# Initialize audio service
|
||||
audio_service = StoryAudioGenerationService(output_dir=str(YOUTUBE_AUDIO_DIR))
|
||||
|
||||
# WaveSpeed Minimax Speech voice ids include language-specific voices
|
||||
# Ref: https://wavespeed.ai/docs/docs-api/minimax/minimax_speech_voice_id
|
||||
LANGUAGE_CODE_TO_LANGUAGE_BOOST = {
|
||||
"en": "English",
|
||||
"es": "Spanish",
|
||||
"fr": "French",
|
||||
"de": "German",
|
||||
"pt": "Portuguese",
|
||||
"it": "Italian",
|
||||
"hi": "Hindi",
|
||||
"ar": "Arabic",
|
||||
"ru": "Russian",
|
||||
"ja": "Japanese",
|
||||
"ko": "Korean",
|
||||
"zh": "Chinese",
|
||||
"vi": "Vietnamese",
|
||||
"id": "Indonesian",
|
||||
"tr": "Turkish",
|
||||
"nl": "Dutch",
|
||||
"pl": "Polish",
|
||||
"th": "Thai",
|
||||
"uk": "Ukrainian",
|
||||
"el": "Greek",
|
||||
"cs": "Czech",
|
||||
"fi": "Finnish",
|
||||
"ro": "Romanian",
|
||||
}
|
||||
|
||||
# Default language-specific Minimax voices (first-choice). We keep English on the existing "persona" voices.
|
||||
LANGUAGE_BOOST_TO_DEFAULT_VOICE_ID = {
|
||||
"Spanish": "Spanish_male_1_v1",
|
||||
"French": "French_male_1_v1",
|
||||
"German": "German_male_1_v1",
|
||||
"Portuguese": "Portuguese_male_1_v1",
|
||||
"Italian": "Italian_male_1_v1",
|
||||
"Hindi": "Hindi_male_1_v1",
|
||||
"Arabic": "Arabic_male_1_v1",
|
||||
"Russian": "Russian_male_1_v1",
|
||||
"Japanese": "Japanese_male_1_v1",
|
||||
"Korean": "Korean_male_1_v1",
|
||||
"Chinese": "Chinese_male_1_v1",
|
||||
"Vietnamese": "Vietnamese_male_1_v1",
|
||||
"Indonesian": "Indonesian_male_1_v1",
|
||||
"Turkish": "Turkish_male_1_v1",
|
||||
"Dutch": "Dutch_male_1_v1",
|
||||
"Polish": "Polish_male_1_v1",
|
||||
"Thai": "Thai_male_1_v1",
|
||||
"Ukrainian": "Ukrainian_male_1_v1",
|
||||
"Greek": "Greek_male_1_v1",
|
||||
"Czech": "Czech_male_1_v1",
|
||||
"Finnish": "Finnish_male_1_v1",
|
||||
"Romanian": "Romanian_male_1_v1",
|
||||
}
|
||||
|
||||
|
||||
def _resolve_language_boost(language: Optional[str], explicit_language_boost: Optional[str]) -> str:
|
||||
"""
|
||||
Determine the effective WaveSpeed `language_boost`.
|
||||
- If user explicitly provided language_boost, use it (including "auto").
|
||||
- Else if language code provided, map to the WaveSpeed boost label.
|
||||
- Else default to English (backwards compatible).
|
||||
"""
|
||||
if explicit_language_boost is not None and str(explicit_language_boost).strip() != "":
|
||||
return str(explicit_language_boost).strip()
|
||||
|
||||
if language is not None and str(language).strip() != "":
|
||||
lang_code = str(language).strip().lower()
|
||||
return LANGUAGE_CODE_TO_LANGUAGE_BOOST.get(lang_code, "auto")
|
||||
|
||||
return "English"
|
||||
|
||||
def select_optimal_emotion(scene_title: str, narration: str, video_plan_context: Optional[Dict[str, Any]] = None) -> str:
|
||||
"""
|
||||
@@ -153,6 +223,7 @@ class YouTubeAudioRequest(BaseModel):
|
||||
scene_title: str
|
||||
text: str
|
||||
voice_id: Optional[str] = None # Will auto-select based on content if not provided
|
||||
language: Optional[str] = None # Language code for multilingual audio (e.g., "en", "es", "fr")
|
||||
speed: float = 1.0
|
||||
volume: float = 1.0
|
||||
pitch: float = 0.0
|
||||
@@ -164,7 +235,7 @@ class YouTubeAudioRequest(BaseModel):
|
||||
bitrate: int = 256000 # Highest quality: 256kbps (valid values: 32000, 64000, 128000, 256000)
|
||||
channel: Optional[str] = "2" # Stereo for richer audio (valid values: "1" or "2")
|
||||
format: Optional[str] = "mp3" # Universal format for web
|
||||
language_boost: Optional[str] = "English" # Optimize for English content
|
||||
language_boost: Optional[str] = None # If not provided, inferred from `language` (or defaults to English)
|
||||
enable_sync_mode: bool = True
|
||||
# Context for intelligent voice/emotion selection
|
||||
video_plan_context: Optional[Dict[str, Any]] = None # Optional video plan for context-aware voice selection
|
||||
@@ -224,13 +295,24 @@ async def generate_youtube_scene_audio(
|
||||
|
||||
logger.info(f"[YouTubeAudio] Text preprocessing: {len(request.text)} -> {len(processed_text)} characters")
|
||||
|
||||
effective_language_boost = _resolve_language_boost(request.language, request.language_boost)
|
||||
|
||||
# Intelligent voice and emotion selection based on content analysis
|
||||
if not request.voice_id:
|
||||
selected_voice = select_optimal_voice(
|
||||
request.scene_title,
|
||||
processed_text,
|
||||
request.video_plan_context
|
||||
)
|
||||
# If non-English language is selected, default to the language-specific Minimax voice_id.
|
||||
# Otherwise keep the existing English persona voice selection logic.
|
||||
if effective_language_boost in LANGUAGE_BOOST_TO_DEFAULT_VOICE_ID and effective_language_boost not in ["English", "auto"]:
|
||||
selected_voice = LANGUAGE_BOOST_TO_DEFAULT_VOICE_ID[effective_language_boost]
|
||||
logger.info(
|
||||
f"[VoiceSelection] Using language-specific default voice '{selected_voice}' "
|
||||
f"(language_boost={effective_language_boost}, language={request.language})"
|
||||
)
|
||||
else:
|
||||
selected_voice = select_optimal_voice(
|
||||
request.scene_title,
|
||||
processed_text,
|
||||
request.video_plan_context
|
||||
)
|
||||
else:
|
||||
selected_voice = request.voice_id
|
||||
|
||||
@@ -244,7 +326,10 @@ async def generate_youtube_scene_audio(
|
||||
else:
|
||||
selected_emotion = request.emotion
|
||||
|
||||
logger.info(f"[YouTubeAudio] Voice selection: {selected_voice}, Emotion: {selected_emotion}")
|
||||
logger.info(
|
||||
f"[YouTubeAudio] Voice selection: {selected_voice}, Emotion: {selected_emotion}, "
|
||||
f"language={request.language}, language_boost={effective_language_boost}"
|
||||
)
|
||||
|
||||
# Build kwargs for optional parameters - use defaults if None
|
||||
# WaveSpeed API requires specific values, so we provide sensible defaults
|
||||
@@ -252,7 +337,11 @@ async def generate_youtube_scene_audio(
|
||||
optional_kwargs = {}
|
||||
|
||||
# DEBUG: Log what values we received
|
||||
logger.info(f"[YouTubeAudio] Request parameters: sample_rate={request.sample_rate}, bitrate={request.bitrate}, channel={request.channel}, format={request.format}, language_boost={request.language_boost}")
|
||||
logger.info(
|
||||
f"[YouTubeAudio] Request parameters: sample_rate={request.sample_rate}, bitrate={request.bitrate}, "
|
||||
f"channel={request.channel}, format={request.format}, language_boost={request.language_boost}, "
|
||||
f"effective_language_boost={effective_language_boost}, language={request.language}"
|
||||
)
|
||||
|
||||
# sample_rate: Use provided value or omit (WaveSpeed will use default)
|
||||
if request.sample_rate is not None:
|
||||
@@ -276,9 +365,9 @@ async def generate_youtube_scene_audio(
|
||||
if request.format is not None:
|
||||
optional_kwargs["format"] = request.format
|
||||
|
||||
# language_boost: Use provided value or omit (WaveSpeed will use default)
|
||||
if request.language_boost is not None:
|
||||
optional_kwargs["language_boost"] = request.language_boost
|
||||
# language_boost: always send resolved value (improves pronunciation and helps multilingual voices)
|
||||
if effective_language_boost is not None and str(effective_language_boost).strip() != "":
|
||||
optional_kwargs["language_boost"] = effective_language_boost
|
||||
|
||||
logger.info(f"[YouTubeAudio] Final optional_kwargs: {optional_kwargs}")
|
||||
|
||||
|
||||
@@ -287,7 +287,7 @@ async def create_video_plan(
|
||||
|
||||
# Check for existing YouTube creator avatar in asset library
|
||||
asset_service = ContentAssetService(db)
|
||||
existing_avatars = asset_service.get_assets(
|
||||
existing_avatars, _ = asset_service.get_user_assets(
|
||||
user_id=user_id,
|
||||
asset_type=AssetType.IMAGE,
|
||||
source_module=AssetSource.YOUTUBE_CREATOR,
|
||||
@@ -685,11 +685,12 @@ async def render_single_scene_video(
|
||||
async def get_render_status(
|
||||
task_id: str,
|
||||
current_user: Dict[str, Any] = Depends(get_current_user),
|
||||
) -> Dict[str, Any]:
|
||||
) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Get the status of a video rendering task.
|
||||
|
||||
Returns current progress, status, and result when complete.
|
||||
Returns None if task not found (matches podcast pattern for graceful handling).
|
||||
"""
|
||||
try:
|
||||
require_authenticated_user(current_user)
|
||||
@@ -697,24 +698,17 @@ async def get_render_status(
|
||||
logger.debug(f"[YouTubeAPI] Getting render status for task: {task_id}")
|
||||
task_status = task_manager.get_task_status(task_id)
|
||||
if not task_status:
|
||||
logger.warning(
|
||||
f"[YouTubeAPI] Task {task_id} not found. "
|
||||
f"Available tasks: {list(task_manager.task_storage.keys())[:5]}..."
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail={
|
||||
"error": "Task not found",
|
||||
"message": "The render task was not found. It may have expired, been cleaned up, or the server may have restarted.",
|
||||
"task_id": task_id,
|
||||
"user_action": "Please try rendering again."
|
||||
}
|
||||
# Log at DEBUG level - null is expected when tasks expire or server restarts
|
||||
# This prevents log spam from frontend polling for expired/completed tasks
|
||||
# Return None instead of raising 404 to match podcast pattern for graceful frontend handling
|
||||
logger.debug(
|
||||
f"[YouTubeAPI] Task {task_id} not found (may have expired or been cleaned up). "
|
||||
f"Available tasks: {len(task_manager.task_storage)}"
|
||||
)
|
||||
return None
|
||||
|
||||
return task_status
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"[YouTubeAPI] Error getting render status: {e}", exc_info=True)
|
||||
raise HTTPException(
|
||||
@@ -1201,6 +1195,12 @@ def _execute_scene_video_render_task(
|
||||
result=result,
|
||||
)
|
||||
|
||||
# Verify the task status was updated correctly (matches podcast pattern)
|
||||
updated_status = task_manager.get_task_status(task_id)
|
||||
logger.info(
|
||||
f"[YouTubeRenderer] Task status after update: task_id={task_id}, status={updated_status.get('status') if updated_status else 'None'}, has_result={bool(updated_status.get('result') if updated_status else False)}, video_url={updated_status.get('result', {}).get('video_url') if updated_status else 'N/A'}"
|
||||
)
|
||||
|
||||
logger.info(
|
||||
f"[YouTubeRenderer] ✅ Single-scene render {task_id} completed (scene {scene_num}), cost=${total_cost:.2f}"
|
||||
)
|
||||
@@ -1348,27 +1348,37 @@ async def list_videos(
|
||||
List videos for the current user from the asset library (source: youtube_creator).
|
||||
Used to rescue/persist scene videos after reloads.
|
||||
"""
|
||||
user_id = require_authenticated_user(current_user)
|
||||
asset_service = ContentAssetService(db)
|
||||
try:
|
||||
user_id = require_authenticated_user(current_user)
|
||||
asset_service = ContentAssetService(db)
|
||||
|
||||
assets = asset_service.get_assets(
|
||||
user_id=user_id,
|
||||
asset_type=AssetType.VIDEO,
|
||||
source_module=AssetSource.YOUTUBE_CREATOR,
|
||||
limit=100,
|
||||
)
|
||||
assets, _ = asset_service.get_user_assets(
|
||||
user_id=user_id,
|
||||
asset_type=AssetType.VIDEO,
|
||||
source_module=AssetSource.YOUTUBE_CREATOR,
|
||||
limit=100,
|
||||
)
|
||||
|
||||
videos = []
|
||||
for asset in assets:
|
||||
videos.append({
|
||||
"scene_number": asset.asset_metadata.get("scene_number") if asset.asset_metadata else None,
|
||||
"video_url": asset.file_url,
|
||||
"filename": asset.filename,
|
||||
"created_at": asset.created_at,
|
||||
"resolution": asset.asset_metadata.get("resolution") if asset.asset_metadata else None,
|
||||
})
|
||||
videos = []
|
||||
for asset in assets:
|
||||
try:
|
||||
videos.append({
|
||||
"scene_number": asset.asset_metadata.get("scene_number") if asset.asset_metadata else None,
|
||||
"video_url": asset.file_url,
|
||||
"filename": asset.filename,
|
||||
"created_at": asset.created_at.isoformat() if asset.created_at else None,
|
||||
"resolution": asset.asset_metadata.get("resolution") if asset.asset_metadata else None,
|
||||
})
|
||||
except Exception as asset_error:
|
||||
logger.warning(f"[YouTubeAPI] Error processing asset {asset.id if hasattr(asset, 'id') else 'unknown'}: {asset_error}")
|
||||
continue # Skip this asset and continue with others
|
||||
|
||||
return VideoListResponse(videos=videos)
|
||||
logger.info(f"[YouTubeAPI] Listed {len(videos)} videos for user {user_id}")
|
||||
return VideoListResponse(videos=videos)
|
||||
except Exception as e:
|
||||
logger.error(f"[YouTubeAPI] Error listing videos: {e}", exc_info=True)
|
||||
# Return empty list on error rather than failing completely
|
||||
return VideoListResponse(videos=[], success=False, message=f"Failed to list videos: {str(e)}")
|
||||
|
||||
|
||||
def _execute_combine_video_task(
|
||||
|
||||
Reference in New Issue
Block a user