Craig ce4dca47cb fix: apply RAG_EMBEDDING_QUERY_PREFIX to memory search queries (#24921) ... The query_memory endpoint embeds the search query without the configured RAG_EMBEDDING_QUERY_PREFIX, while every RAG retrieval path in retrieval/utils.py correctly passes it. Instruction-tuned embedding models (e.g. Qwen3-Embedding) produce poor results without the prefix, causing memory search to return semantically unrelated results.		2026-06-01 13:23:15 -07:00
..
data	refac: mv backend files to /open_webui dir	2024-09-04 16:54:48 +02:00
open_webui	fix: apply RAG_EMBEDDING_QUERY_PREFIX to memory search queries (#24921)	2026-06-01 13:23:15 -07:00
.dockerignore	fix: litellm config issue	2024-02-24 22:35:11 -08:00
.gitignore	refac	2024-09-06 04:59:20 +02:00
dev.sh	refac	2026-03-24 19:43:30 -05:00
requirements-min.txt	refac	2026-04-24 18:20:10 +09:00
requirements.txt	refac	2026-06-01 12:24:45 -07:00
start.sh	fix: default optional env vars used with bash ,, in start.sh (#24683)	2026-05-15 09:29:25 +09:00
start_windows.bat	refac	2026-04-24 15:40:02 +09:00