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
53 lines
1.4 KiB
Python
53 lines
1.4 KiB
Python
"""
|
|
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
|
|
|