feat: implement RAG Service MVP with PARSER + Memory integration

RAG Service Implementation:
- Create rag-service/ with full structure (config, document_store, embedding, pipelines)
- Document Store: PostgreSQL + pgvector via Haystack
- Embedding: BAAI/bge-m3 (multilingual, 1024 dim)
- Ingest Pipeline: Convert ParsedDocument to Haystack Documents, embed, index
- Query Pipeline: Retrieve documents, generate answers via DAGI Router
- FastAPI endpoints: /ingest, /query, /health

Tests:
- Unit tests for ingest and query pipelines
- E2E test with example parsed JSON
- Test fixtures with real PARSER output example

Router Integration:
- Add mode='rag_query' routing rule in router-config.yml
- Priority 7, uses local_qwen3_8b for RAG queries

Docker:
- Add rag-service to docker-compose.yml
- Configure dependencies (router, city-db)
- Add model cache volume

Documentation:
- Complete README with API examples
- Integration guides for PARSER and Router

services/rag-service/app/main.py

@@ -0,0 +1,105 @@
+"""
+RAG Service - FastAPI application
+Retrieval-Augmented Generation for MicroDAO
+"""
+
+import logging
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+
+from app.models import IngestRequest, IngestResponse, QueryRequest, QueryResponse
+from app.ingest_pipeline import ingest_parsed_document
+from app.query_pipeline import answer_query
+
+logger = logging.getLogger(__name__)
+
+# FastAPI app
+app = FastAPI(
+    title="RAG Service",
+    description="Retrieval-Augmented Generation service for MicroDAO",
+    version="1.0.0"
+)
+
+# CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.get("/health")
+async def health():
+    """Health check endpoint"""
+    return {
+        "status": "healthy",
+        "service": "rag-service",
+        "version": "1.0.0"
+    }
+
+
+@app.post("/ingest", response_model=IngestResponse)
+async def ingest_endpoint(request: IngestRequest):
+    """
+    Ingest parsed document from PARSER service into RAG
+    
+    Body:
+    - dao_id: DAO identifier
+    - doc_id: Document identifier
+    - parsed_json: ParsedDocument JSON from PARSER service
+    - user_id: Optional user identifier
+    """
+    try:
+        result = ingest_parsed_document(
+            dao_id=request.dao_id,
+            doc_id=request.doc_id,
+            parsed_json=request.parsed_json,
+            user_id=request.user_id
+        )
+        
+        return IngestResponse(**result)
+        
+    except Exception as e:
+        logger.error(f"Ingest endpoint error: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@app.post("/query", response_model=QueryResponse)
+async def query_endpoint(request: QueryRequest):
+    """
+    Answer query using RAG pipeline
+    
+    Body:
+    - dao_id: DAO identifier
+    - question: User question
+    - top_k: Optional number of documents to retrieve
+    - user_id: Optional user identifier
+    """
+    try:
+        result = await answer_query(
+            dao_id=request.dao_id,
+            question=request.question,
+            top_k=request.top_k,
+            user_id=request.user_id
+        )
+        
+        return QueryResponse(**result)
+        
+    except Exception as e:
+        logger.error(f"Query endpoint error: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+if __name__ == "__main__":
+    import uvicorn
+    from app.core.config import settings
+    
+    uvicorn.run(
+        "app.main:app",
+        host=settings.API_HOST,
+        port=settings.API_PORT,
+        reload=True
+    )
+