Classic298 7cf35bedc0 fix: editing a knowledge file on Elasticsearch keeps its old text searchable (#31530) ... With VECTOR_DB=elasticsearch, changing a file's content in a knowledge base added the new text but never removed the old chunks, so searches and chats kept returning the old text next to the new. The old chunks are now found and removed after the edit, the same as on the default store. Fixes #31523		2026-10-01 07:36:44 +04:00
..
chroma.py	fix: page Chroma get() so hybrid search works on collections over 32k chunks (#30368)	2026-09-22 14:48:45 -04:00
elasticsearch.py	fix: editing a knowledge file on Elasticsearch keeps its old text searchable (#31530)	2026-10-01 07:36:44 +04:00
mariadb_vector.py	refac	2026-07-31 17:41:14 -04:00
milvus.py	feat: Milvus hybrid search without a second text-only copy of every collection (#31660)	2026-10-01 03:07:50 +04:00
milvus_multitenancy.py	feat: Milvus hybrid search without a second text-only copy of every collection (#31660)	2026-10-01 03:07:50 +04:00
opengauss.py	fix: release the openGauss connection when a read returns no rows (#30144)	2026-09-18 19:31:01 -04:00
opensearch.py	refac	2026-08-25 16:27:17 -04:00
oracle23ai.py	fix: apply the shared metadata size cap to the last four vector DB backends (#29502)	2026-09-04 11:42:20 -04:00
pgvector.py	fix: pgvector reads leak their connection and lose most of their neighbours (#30142)	2026-09-18 19:31:49 -04:00
pinecone.py	refac	2026-08-25 16:27:17 -04:00
qdrant.py	fix: file uploads and hybrid search fail on Qdrant with strict mode enabled (#31461)	2026-09-27 22:58:42 +04:00
qdrant_multitenancy.py	fix: file uploads and hybrid search fail on Qdrant with strict mode enabled (#31461)	2026-09-27 22:58:42 +04:00
s3vector.py	refac	2026-08-25 16:27:17 -04:00
valkey.py	perf: build info log messages lazily so raising the log level actually saves work (#27837)	2026-08-02 15:39:10 -05:00
weaviate.py	fix: exact matches score as the worst result on Weaviate (#31531)	2026-09-30 19:29:59 +04:00