jpmschweitzerandClaude Opus 4.5
37f8e1819e
Build and Push / build (release) Successful in 28s
- Migrate volatile backend from Redis to Qdrant for semantic search
- Add natural language conversion for structured data embedding
- Simplify API: /volatile/search, /volatile/store, /{namespace}/{key}
- Integrate volatile into HybridRAG with priority boost in RRF fusion
- Add POST /maintenance/cleanup/volatile for expiry purging
- Update tests for new Qdrant-based architecture (37/37 pass)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
121 lines
4.1 KiB
Python
121 lines
4.1 KiB
Python
"""
|
|
HybridRAG router for multi-source search API.
|
|
|
|
Provides endpoint for combining vector, graph, volatile cache, and web search
|
|
with RRF fusion and LLM re-ranking.
|
|
"""
|
|
|
|
from fastapi import APIRouter, HTTPException, Depends, Query
|
|
import logging
|
|
|
|
from src.models.hybrid_rag import HybridRAGRequest, HybridRAGResponse
|
|
from src.services.hybrid_rag_service import HybridRAGService
|
|
from src.core.dependencies import (
|
|
Neo4jDep, WikiJSDep, QdrantDep, OllamaDep,
|
|
SearXNGDep, ContentExtractorDep, verify_api_key, get_settings
|
|
)
|
|
from src.config import Settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(prefix="/query", tags=["HybridRAG"])
|
|
|
|
|
|
# Dependency to get HybridRAG service
|
|
def get_hybrid_rag_service(
|
|
neo4j_client: Neo4jDep,
|
|
wiki_client: WikiJSDep,
|
|
qdrant_client: QdrantDep,
|
|
ollama_client: OllamaDep,
|
|
searxng_client: SearXNGDep,
|
|
content_extractor: ContentExtractorDep,
|
|
settings: Settings = Depends(get_settings)
|
|
) -> HybridRAGService:
|
|
"""Get HybridRAG service instance with all dependencies."""
|
|
from src.services.vector_service import VectorService
|
|
from src.services.graph_service import GraphService
|
|
from src.services.volatile_service import VolatileCacheService
|
|
|
|
# Create component services
|
|
vector_service = VectorService(qdrant_client, wiki_client, ollama_client)
|
|
graph_service = GraphService(neo4j_client, wiki_client)
|
|
volatile_service = VolatileCacheService(qdrant_client, ollama_client, settings)
|
|
|
|
# Create HybridRAG service
|
|
return HybridRAGService(
|
|
vector_service=vector_service,
|
|
graph_service=graph_service,
|
|
searxng_client=searxng_client,
|
|
ollama_client=ollama_client,
|
|
content_extractor=content_extractor,
|
|
settings=settings,
|
|
volatile_service=volatile_service
|
|
)
|
|
|
|
|
|
@router.post("/hybrid", response_model=HybridRAGResponse)
|
|
async def hybrid_search(
|
|
request: HybridRAGRequest,
|
|
user: str = Query(default="jpmschweitzer", description="User identifier for multi-tenancy"),
|
|
hybrid_rag_service: HybridRAGService = Depends(get_hybrid_rag_service),
|
|
api_key: str = Depends(verify_api_key)
|
|
):
|
|
"""
|
|
Execute HybridRAG query combining vector, graph, volatile cache, and web search.
|
|
|
|
**6-Phase Pipeline:**
|
|
1. **Query Enhancement**: Extract keywords/synonyms with LLM
|
|
2. **Parallel Retrieval**: Search vector (Qdrant), graph (Neo4j), volatile cache, web (SearXNG)
|
|
3. **RRF Fusion**: Merge results with Reciprocal Rank Fusion (volatile gets priority boost)
|
|
4. **Enrichment**: Add related documents via shared entities
|
|
5. **LLM Re-ranking**: Re-rank with configured model for relevance
|
|
6. **Context Formatting**: Format for LLM consumption
|
|
7. **Persistence**: Store for Librarian knowledge consolidation
|
|
|
|
**Example Request:**
|
|
```json
|
|
{
|
|
"query": "What's the weather in Rotterdam?",
|
|
"user": "jpmschweitzer",
|
|
"config": {
|
|
"vector_limit": 10,
|
|
"graph_limit": 10,
|
|
"web_limit": 5,
|
|
"volatile_limit": 5,
|
|
"enable_volatile": true,
|
|
"enable_reranking": true,
|
|
"final_result_count": 10
|
|
}
|
|
}
|
|
```
|
|
|
|
**Returns:**
|
|
- Ranked results from all sources (wiki, volatile, web)
|
|
- Extracted keywords/synonyms
|
|
- Related dossiers (via graph)
|
|
- Formatted context for LLM
|
|
- Performance timing breakdown
|
|
- Search ID for Librarian tracking
|
|
"""
|
|
try:
|
|
logger.info(f"HybridRAG request: '{request.query}' for user '{user}'")
|
|
|
|
response = await hybrid_rag_service.search(
|
|
query=request.query,
|
|
user=user,
|
|
config=request.config
|
|
)
|
|
|
|
logger.info(
|
|
f"HybridRAG completed: {response.total_results} results in {response.timing.total_ms:.0f}ms"
|
|
)
|
|
|
|
return response
|
|
|
|
except ValueError as e:
|
|
logger.error(f"Invalid request: {e}")
|
|
raise HTTPException(status_code=400, detail=str(e))
|
|
except Exception as e:
|
|
logger.error(f"HybridRAG search failed: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail="Search failed")
|