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/document_store.py

@@ -0,0 +1,57 @@
+"""
+Document Store for RAG Service
+Uses PostgreSQL + pgvector via Haystack
+"""
+
+import logging
+from typing import Optional
+
+from haystack.document_stores import PGVectorDocumentStore
+
+from app.core.config import settings
+
+logger = logging.getLogger(__name__)
+
+# Global document store instance
+_document_store: Optional[PGVectorDocumentStore] = None
+
+
+def get_document_store() -> PGVectorDocumentStore:
+    """
+    Get or create PGVectorDocumentStore instance
+    
+    Returns:
+        PGVectorDocumentStore configured with pgvector
+    """
+    global _document_store
+    
+    if _document_store is not None:
+        return _document_store
+    
+    logger.info(f"Initializing PGVectorDocumentStore: table={settings.RAG_TABLE_NAME}")
+    logger.info(f"Connection: {settings.PG_DSN.split('@')[1] if '@' in settings.PG_DSN else 'hidden'}")
+    
+    try:
+        _document_store = PGVectorDocumentStore(
+            connection_string=settings.PG_DSN,
+            embedding_dim=settings.EMBED_DIM,
+            table_name=settings.RAG_TABLE_NAME,
+            search_strategy=settings.SEARCH_STRATEGY,
+            # Additional options
+            recreate_table=False,  # Don't drop existing table
+            similarity="cosine",  # Cosine similarity for embeddings
+        )
+        
+        logger.info("PGVectorDocumentStore initialized successfully")
+        return _document_store
+        
+    except Exception as e:
+        logger.error(f"Failed to initialize DocumentStore: {e}", exc_info=True)
+        raise RuntimeError(f"DocumentStore initialization failed: {e}") from e
+
+
+def reset_document_store():
+    """Reset global document store instance (for testing)"""
+    global _document_store
+    _document_store = None
+