Files
odysseus/src/rag_singleton.py

62 lines
1.9 KiB
Python
Raw Normal View History

2026-05-31 23:58:26 +09:00
"""
RAG singleton instance for the application.
"""
import os
import logging
import time
from pathlib import Path
logger = logging.getLogger(__name__)
rag_instance = None
_last_attempt = 0.0
_RETRY_INTERVAL = 30 # seconds between re-init attempts
Re-enable VectorRAG init with lazy retry Personal Docs (POST /api/personal/add_directory and friends) currently returns HTTP 503 'RAG system is not available' for every request, because get_rag_manager() and rag_manager are both hardcoded off. The disablement was added when chromadb 1.4.1 / pydantic 2.12 were mutually incompatible at the client init layer. That compat issue is fixed in the current pins (chromadb 1.5.x + pydantic 2.13.x). Verified by calling the original lazy initializer against a running chroma server — VectorRAG instantiates, reports healthy=True, and indexes successfully. This change: 1. src/rag_singleton.py — replace the hardcoded `return None` in get_rag_manager() with the original lazy init body. Keeps the 30s retry-throttle so a missing chroma server doesn't busy-retry on every request. 2. app.py — replace the parallel `rag_manager = None` / `rag_available = False` hardcoding with a get_rag_manager() call. Logs the resolved state at startup. If chroma isn't reachable yet, rag_manager stays None and personal-doc routes still return 503, but the *next* request will hit the retry-throttle path in get_rag_manager() and try to init again. Doesn't touch requirements.txt. Repos using docker-compose get chroma automatically; manual installs that want Personal Docs to work still need to either pip install chromadb (full package) and run `chroma run` or point at an external chroma instance via env. That can be a follow-up README / requirements-optional note.
2026-05-31 22:32:13 -07:00
def get_rag_manager():
"""Lazy ChromaDB-backed VectorRAG initializer.
Returns the VectorRAG instance on first successful init, None if ChromaDB
isn't reachable / available. Failed init attempts are throttled to once
per _RETRY_INTERVAL seconds so a missing ChromaDB doesn't busy-retry on
every request — callers (personal-doc routes etc.) get None back and
return a clean 503 to the user instead.
Historical note: this used to be hardcoded to ``return None`` with a
comment about chromadb 1.4.1 / pydantic 2.12 being mutually incompatible.
That compat issue is resolved in current pinned versions
(chromadb 1.5.x + pydantic 2.13.x), so the real initializer is back.
"""
2026-05-31 23:58:26 +09:00
global rag_instance, _last_attempt
if rag_instance is not None:
return rag_instance
now = time.monotonic()
if now - _last_attempt < _RETRY_INTERVAL:
Re-enable VectorRAG init with lazy retry Personal Docs (POST /api/personal/add_directory and friends) currently returns HTTP 503 'RAG system is not available' for every request, because get_rag_manager() and rag_manager are both hardcoded off. The disablement was added when chromadb 1.4.1 / pydantic 2.12 were mutually incompatible at the client init layer. That compat issue is fixed in the current pins (chromadb 1.5.x + pydantic 2.13.x). Verified by calling the original lazy initializer against a running chroma server — VectorRAG instantiates, reports healthy=True, and indexes successfully. This change: 1. src/rag_singleton.py — replace the hardcoded `return None` in get_rag_manager() with the original lazy init body. Keeps the 30s retry-throttle so a missing chroma server doesn't busy-retry on every request. 2. app.py — replace the parallel `rag_manager = None` / `rag_available = False` hardcoding with a get_rag_manager() call. Logs the resolved state at startup. If chroma isn't reachable yet, rag_manager stays None and personal-doc routes still return 503, but the *next* request will hit the retry-throttle path in get_rag_manager() and try to init again. Doesn't touch requirements.txt. Repos using docker-compose get chroma automatically; manual installs that want Personal Docs to work still need to either pip install chromadb (full package) and run `chroma run` or point at an external chroma instance via env. That can be a follow-up README / requirements-optional note.
2026-05-31 22:32:13 -07:00
return None # too soon to retry — last attempt failed
2026-05-31 23:58:26 +09:00
_last_attempt = now
try:
from src.rag_vector import VectorRAG
base_dir = Path(__file__).parent.parent
persist_dir = os.path.join(base_dir, "data", "rag")
rag_instance = VectorRAG(persist_directory=persist_dir)
if not rag_instance.healthy:
logger.warning("VectorRAG created but not healthy, will retry later")
rag_instance = None
else:
logger.info("Initialized VectorRAG with ChromaDB")
except ImportError as e:
logger.warning(f"VectorRAG not available: {e}")
rag_instance = None
except Exception as e:
logger.error(f"Failed to initialize RAG: {e}")
rag_instance = None
return rag_instance