Classic298 6e5e5fe6e9 feat: add a Tavily search depth setting (#31308) ... Tavily web search always ran at Tavily's default depth (basic), because the search request never sent `search_depth`. The only Tavily depth control in Admin > Settings > Web Search, "Tavily Extract Depth", applies to the Extract API used by the web loader, never to search. This adds `TAVILY_SEARCH_DEPTH` (env var and persisted setting, default `basic`) and a "Tavily Search Depth" select (ultra-fast, fast, basic, advanced) under the Tavily search engine settings. The value is sent as `search_depth` on every Tavily search request, so admins can set search and extract depth independently, for example fast search with advanced extraction. The default matches Tavily's own default, so existing setups keep the same behaviour until the setting is changed. Fixes #29891		2026-09-27 23:15:09 +04:00
..
loaders	fix: backslashes in uploaded HTML files turn into line breaks or break the upload (#31450)	2026-09-27 23:08:14 +04:00
models	fix: repair two broken logging calls, one of which makes VECTOR_DB=opengauss unusable (#27838)	2026-08-10 22:19:41 -06:00
vector	fix: file uploads and hybrid search fail on Qdrant with strict mode enabled (#31461)	2026-09-27 22:58:42 +04:00
web	feat: add a Tavily search depth setting (#31308)	2026-09-27 23:15:09 +04:00
external.py	refac	2026-07-27 01:59:17 -04:00
utils.py	fix: hybrid search finds nothing when a collection cannot be read (#31460)	2026-09-27 22:59:02 +04:00