feat: Roadmap K — RAG corpus management with score-based eviction (v0.13.0)

- Config: RAG_MAX_VECTORS, high/low water marks, grace period, weights
- rag.py: get_collection_count, evict_batch, maybe_evict (asyncio.Lock),
  get_rag_operational_stats, EVICTION_LOG, retrieval_count tracking
- routers/rag_admin.py: GET /api/rag/stats, POST /api/rag/flush (admin)
- Wire maybe_evict() into upload.py and ingest.py after Qdrant upsert
- 16 tests: collection stats, eviction scoring, pinned/grace/batch guards,
  endpoint auth, race lock, flush, operational stats shape
- Bump to v0.13.0
This commit is contained in:
gramps
2026-07-06 07:56:09 -07:00
parent 133cca2551
commit 8072fb3dd0
7 changed files with 665 additions and 6 deletions
+5 -1
View File
@@ -10,7 +10,7 @@ from fastapi.responses import JSONResponse
from config import UPLOAD_DIR, MAX_UPLOAD_BYTES, SUPPORTED_UPLOAD_TYPES, UPLOAD_CONTEXT_EXPIRY_HOURS
from db import get_db, insert_upload_context, list_upload_context_by_conversation, delete_upload_context_by_id
from rag import chunk_text, QDRANT_URL, EMBED_URL, EMBED_MODEL, RAG_COLLECTION
from rag import chunk_text, maybe_evict, QDRANT_URL, EMBED_URL, EMBED_MODEL, RAG_COLLECTION
log = logging.getLogger("jarvischat")
router = APIRouter()
@@ -87,6 +87,10 @@ async def upload_file(
else:
log.warning(f"Qdrant upsert failed for chunk {i}: {upsert_resp.status_code}")
result["chunks_ingested"] = ingested
if ingested > 0:
evicted = await maybe_evict()
if evicted:
log.info(f"Evicted {evicted} vectors after upload")
if mode in ("context", "both"):
expires = (datetime.now(timezone.utc) + timedelta(hours=UPLOAD_CONTEXT_EXPIRY_HOURS)).isoformat()