9b86f9a694
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
52 lines
1.5 KiB
Python
52 lines
1.5 KiB
Python
"""
|
|
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()
|
|
|