mirror of
https://github.com/open-webui/open-webui.git
synced 2026-09-16 23:43:03 +00:00
ea1b58eb6a
Chunk metadata inserted into the vector DB carries arbitrary client- supplied fields (e.g. custom metadata from file uploads), so it needs the same size cap, type coercion and null-byte sanitization every other backend already applies through process_metadata(). Four backends never called it: Qdrant, Qdrant multitenancy, Milvus multitenancy and Oracle23ai, so an oversized or malformed metadata blob went into those unfiltered. Wire process_metadata() in at each backend's single insert/upsert chokepoint, matching the pattern already used by the other eleven backends. |
||
|---|---|---|
| .. | ||
| chroma.py | ||
| elasticsearch.py | ||
| mariadb_vector.py | ||
| milvus.py | ||
| milvus_multitenancy.py | ||
| opengauss.py | ||
| opensearch.py | ||
| oracle23ai.py | ||
| pgvector.py | ||
| pinecone.py | ||
| qdrant.py | ||
| qdrant_multitenancy.py | ||
| s3vector.py | ||
| valkey.py | ||
| weaviate.py | ||