Method _should_use_rag

backend/server.py:342–366

🧠 ENHANCED: Determine if a query should use RAG pipeline using document overviews. Args: message: The user's query idx_ids: List of index IDs associated with the session Returns: bool: True if should use RAG, False fo

(self, message: str, idx_ids: List[str])

                print(f"⚠️  Client disconnected during error response")
    
    def _should_use_rag(self, message: str, idx_ids: List[str]) -> bool:
        """
        🧠 ENHANCED: Determine if a query should use RAG pipeline using document overviews.
        
        Args:
            message: The user's query
            idx_ids: List of index IDs associated with the session
            
        Returns:
            bool: True if should use RAG, False for direct LLM
        """
        # No indexes = definitely no RAG needed
        if not idx_ids:
            return False

        # Load document overviews for intelligent routing
        try:
            doc_overviews = self._load_document_overviews(idx_ids)
            if doc_overviews:
                return self._route_using_overviews(message, doc_overviews)
        except Exception as e:
            print(f"⚠️ Overview-based routing failed, falling back to simple routing: {e}")
        
        # Fallback to simple pattern matching if overviews unavailable
        return self._simple_pattern_routing(message, idx_ids)

    def _load_document_overviews(self, idx_ids: List[str]) -> List[str]:
        """Load and aggregate overviews for the given index IDs.