Use JSON5 for embeddings (#719)

[JS] use shorthand notation (#711)

Revert "[Small model] Explicitly close AsyncGenerator" (#709)

[Small model] Explicitly close AsyncGenerator (#704)

Mv embeddingEndpoints.ts (#688)

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)

Add feature to unlist a model (#625)

Standardize HF_ACCESS_TOKEN -> HF_TOKEN (#610)

Get rid of the unused websearch collection, and the unused endpoint (#607)

Support websearch for openAI chat completion mode (#608)

Add support for passing an API key or any other custom token in the authorization header (#579)

Session management improvements: Multi sessions, renew on login/logout (#603)

Add ollama endpoint support (#569)

disable cache on tgi endpoint (#567)

Option for running websearch locally (#563)

Add support for tgi multimodal models (#531)

remove min string size on accessToken

Enable lazy construction of pipeline (#554)

fix: typecheck

fix: Rename sagemaker endpoint to aws endpoint

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

add you.com integration (#514)

[Websearch] UI fix sources (#521)

Switch chat model back to mistral, use zephyr for small tasks (#515)

Feature/add OIDC optional tolerance and resource (#496)

Update websearch prompting & summary prompting (#503)

Added optional llm summerization (#498)

Pass stop sequences properly to TGI (#499)

delete unused file

move some tasks to small model (#479)

remove logs for parsing

fix JSON.parse for summerize (#445)

fix types

error console instead of crashing

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

Refactor summarization so it gets called from backend (#456)

Backend refactor for streaming endpoints (#444)

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

Revert "Improve error message when the .env MODELS is not well formatted (#451)"

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

Update embedding model for WebSearch (#437)

Improve error message when the .env MODELS is not well formatted (#451)

[Websearch] update (#427)

🐛 Fix - Remove the min length validation on preprompt

Support custom system prompts from the user (#399)

Make all prompt templates configurable (#400)