Move vars to dynamic, add metrics (#1085)

Use pino for logs (#1086)

Switch task model and add max tokens limits (#1036)

[Websearch] change context schema (#944)

Prepend domain filters in search query generation (#932)

Show error when webpage cannot be reached or parsed (#930)

Fix multi domains for assistants (#929)

Add websearch controls for assistants (#812)

Conversation trees (#223) (#807)

Added support for SearXNG as a websearch source (#805)

Web search: UI update (#749)

[Fix] small fixes in websearch generateQuery (#727)

[JS] use shorthand notation (#711)

Add embedding models configurable, from both transformers.js and TEI (#646)

Fixes "invalid url" error in websearch (#675)

Use JSON5 for parsing all config vars (#671)

Add support for SerpStack API (#669)

Add allow & blocklist for websearch (#651)

Option for running websearch locally (#563)

Enable lazy construction of pipeline (#554)

Modular backends & support for openAI & AWS endpoints (#541)

add you.com integration (#514)

[Websearch] UI fix sources (#521)

Update websearch prompting & summary prompting (#503)

remove logs for parsing

Make embedding model settings more future-proof (#454)

Backend refactor for streaming endpoints (#444)

Revert "Revert "Update embedding model for WebSearch (#437)""

Revert "Update embedding model for WebSearch (#437)"

Update embedding model for WebSearch (#437)

[Websearch] update (#427)

Make all prompt templates configurable (#400)

allow different user and assistant end-token (#375)

Add support for HF summarization endpoint in the websearch (#319)

Added Serper.dev API as an alternative web search provider (#302)

Refactor of websearch (#281)