open-webui/backend/open_webui/retrieval/vector
PVBLIC Foundation 04b9065f08
Update pinecone.py
Now supports batched insert, upsert, and delete operations using a default batch size of 100, reducing API strain and improving throughput. All blocking calls to the Pinecone API are wrapped in asyncio.to_thread(...), ensuring async safety and preventing event loop blocking. The implementation includes zero-vector handling for efficient metadata-only queries, normalized cosine distance scores for accurate ranking, and protections against empty input operations. Logs for batch durations have been streamlined to minimize noise, while preserving key info-level success logs.
2025-05-08 15:53:30 -07:00
..
dbs Update pinecone.py 2025-05-08 15:53:30 -07:00
connector.py feat(vector-db): add support for Pinecone client 2025-04-20 11:08:51 +03:00
main.py feat: Add abstract base class for vector database integration 2025-04-21 08:27:27 +03:00