add manifest.json (#469)

fix title summarization

remove logs for parsing

Add a message wide copy button (#453)

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)

Add latex support with marked-katex-extension (#450)

fix lint on main

Mobile: fix model selection (#448)

[Websearch] update (#427)

Add rate limiting to websearch and title summary (#433)

move rate limit event to top

ip rate limit

Revert "IP based rate limit"

IP based rate limit

Store IP in messageEvents

🐛 Fix - preprompt not being passed correctly

🐛 Fix - Remove the min length validation on preprompt

fix auth on websearch (#410)

🐛 Fix - Model switching no longer enables data sharing

types fix in SettingsModal.svelte

fix issue with settings modal

Support custom system prompts from the user (#399)

Make all prompt templates configurable (#400)

Add Sagemaker support (#401)

feat: add support for endpoints requiring client authentication using PKI (#393)

Leverage model link to modelUrl when informed (#385)

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

add a login button when users are logged out (#381)

trim and remove stop-suffixes from summary (#369)

Make model branding customizable based on env var (#345)

Update /privacy and other content following Llama v2 release (#374)

Revert "support rate limiting based on user IP (#342)"

Reopen: Feature/disable login for n messages (#356)

support rate limiting based on user IP (#342)

Revert "Option to disable login on first N messages (#352)"

Option to disable login on first N messages (#352)

Add ability to define custom model/dataset URLs (#347)

Add optional timestamps to messages (#294)

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

feat: factor out HF_API_ROOT to allow different inference endpoints (#332)