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/embedding.py

@@ -0,0 +1,52 @@
+"""
+Embedding service for RAG
+Uses SentenceTransformers via Haystack
+"""
+
+import logging
+from typing import Optional
+
+from haystack.components.embedders import SentenceTransformersTextEmbedder
+
+from app.core.config import settings
+
+logger = logging.getLogger(__name__)
+
+# Global embedder instance
+_text_embedder: Optional[SentenceTransformersTextEmbedder] = None
+
+
+def get_text_embedder() -> SentenceTransformersTextEmbedder:
+    """
+    Get or create SentenceTransformersTextEmbedder instance
+    
+    Returns:
+        SentenceTransformersTextEmbedder configured with embedding model
+    """
+    global _text_embedder
+    
+    if _text_embedder is not None:
+        return _text_embedder
+    
+    logger.info(f"Loading embedding model: {settings.EMBED_MODEL_NAME}")
+    logger.info(f"Device: {settings.EMBED_DEVICE}")
+    
+    try:
+        _text_embedder = SentenceTransformersTextEmbedder(
+            model=settings.EMBED_MODEL_NAME,
+            device=settings.EMBED_DEVICE,
+        )
+        
+        logger.info("Text embedder initialized successfully")
+        return _text_embedder
+        
+    except Exception as e:
+        logger.error(f"Failed to initialize TextEmbedder: {e}", exc_info=True)
+        raise RuntimeError(f"TextEmbedder initialization failed: {e}") from e
+
+
+def reset_embedder():
+    """Reset global embedder instance (for testing)"""
+    global _text_embedder
+    _text_embedder = None
+