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/core/config.py

@@ -0,0 +1,51 @@
+"""
+Configuration for RAG Service
+"""
+
+import os
+from typing import Literal
+from pydantic_settings import BaseSettings
+
+
+class Settings(BaseSettings):
+    """Application settings"""
+    
+    # Service
+    API_HOST: str = "0.0.0.0"
+    API_PORT: int = 9500
+    
+    # PostgreSQL + pgvector
+    PG_DSN: str = os.getenv(
+        "PG_DSN",
+        "postgresql+psycopg2://postgres:postgres@city-db:5432/daarion_city"
+    )
+    
+    # Embedding model
+    EMBED_MODEL_NAME: str = os.getenv("EMBED_MODEL_NAME", "BAAI/bge-m3")
+    EMBED_DEVICE: Literal["cuda", "cpu", "mps"] = os.getenv("EMBED_DEVICE", "cpu")
+    EMBED_DIM: int = int(os.getenv("EMBED_DIM", "1024"))  # BAAI/bge-m3 = 1024
+    
+    # Document Store
+    RAG_TABLE_NAME: str = os.getenv("RAG_TABLE_NAME", "rag_documents")
+    SEARCH_STRATEGY: Literal["approximate", "exact"] = os.getenv("SEARCH_STRATEGY", "approximate")
+    
+    # Chunking
+    CHUNK_SIZE: int = int(os.getenv("CHUNK_SIZE", "500"))
+    CHUNK_OVERLAP: int = int(os.getenv("CHUNK_OVERLAP", "50"))
+    
+    # Retrieval
+    TOP_K: int = int(os.getenv("TOP_K", "5"))
+    
+    # LLM (for query pipeline)
+    LLM_PROVIDER: str = os.getenv("LLM_PROVIDER", "router")  # router, openai, local
+    ROUTER_BASE_URL: str = os.getenv("ROUTER_BASE_URL", "http://router:9102")
+    OPENAI_API_KEY: str = os.getenv("OPENAI_API_KEY", "")
+    OPENAI_MODEL: str = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    
+    class Config:
+        env_file = ".env"
+        case_sensitive = True
+
+
+settings = Settings()
+