Commit History
-
Send characters by groups of 5 (#1007)
Unverified signature* Send characters by groups of 5 * remove commentc1caa1f -
Show the assistant model name in the chat input (#1006)
Unverified signature2435b95 -
Fix unresponsive page after deleting all conversations (#1004)
Francois LancelotUnverified signatureFix #937a59f531
-
modal wording (#1000)
Unverified signature* wording * format --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>fe072ba
-
Update models and add check for assistants model on startup (#998)
Unverified signature* Remove old models from .env.template * Make sure we always have a visible model in assistant settings * Always show correct info in chat window * Add migration that runs on every server start to update assistant model * change key * fix tests * Update src/lib/migrations/migrations.ts Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> * review * Update src/lib/components/chat/ChatWindow.svelte Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> * revert duplicate Model: * simplify deprecated check --------- Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>29b7d2a
-
Move default template so it doesn't override tokenizer (#987)
Unverified signature9437108 -
Set ChatML as default chat prompt template (#985)
Unverified signature619722b
-
quick fix error message (#977)
Unverified signatured323cb0 -
Add support for cohere endpoints (#976)
Unverified signature* Add support for cohere endpoints * readme updatea99cca3 -
Use jinja template for chat formatting (#730) (#744)
Unverified signature* Use jinja template for chat formatting * Add support for transformers js chat template * update to latest transformers version * Make sure to `add_generation_prompt` * unindent0819256
-
Implement Cloudflare Workers AI endpoint (#907) (#972)
Unverified signature* Implement Cloudflare Workers AI endpoint (#907) * Renamed to Cloudflare Workers AI in docs * Add note about sampling parameters * clean up env examplecb000d3
-
Group tokens randomly (#964)
Unverified signature* Group tokens together * remove unused comment * Send final buffer at the end if neededa01ed5a -
User count update (#970)
Unverified signature* add more range * display on assitant page tooeb956bc -
Fix button placement on assistant edit/create form (#962)
Unverified signature* Fix button placement on assistant edit/create form * rm unnecessary changes * Fix alignmentdf27d77 -
Add share button for assistant intro page (#960) (#965)
Unverified signature* Add share button for assistant intro page * Fix padding on share assistant * gap --------- Co-authored-by: Victor Mustar <victor.mustar@gmail.com>55af70d -
Google Vertex API support (#950)
Unverified signature* Added Google Vertex API support Google Application credentials can be set via GOOGLE_APPLICATION_CREDENTIALS = clientid.json * Updated the readme file * Updated the package-lock file * Updated the package-lock file Fixed minor issues * Moved "@google-cloud/vertexai" to optional dependencies * Updated for lint checker3ebd3a8
-
[Trending assistants] make ui visible (#966)
MishigUnverified signature9a4b7ac
-
[Assistants] trending feature (#938)
Mishig +1: coyotte508Unverified signature* [Assistants] trending feature * cleaner sort query * create & use `AssistantStats` collection * fix grouping * rm usage of migration * ♻️ Refacto lock usage / AssistantStat * 🩹 Fix last24HoursCount.count => last24HoursCount * 🐛 Fix collection name * 🐛 Fix DB query * 🐛 Fix rate limit on assitant creation * 🐛 Fix aggregation query * ✨ Only run refreshAssistants if assistants are enabled * hide UI until we have enough stats collection --------- Co-authored-by: coyotte508 <coyotte508@gmail.com>a4c3fca
-
Expose sampling controls in assistants (#955) (#959)
Unverified signature* Expose sampling controls in assistants (#955) * Make sure all labels have the same font size * styling * Add better tooltips * better padding & wrapping * Revert "better padding & wrapping" This reverts commit 1b44086465040f2cb6bc906983cfc8d95820d6fe. * ui update * tooltip on mobile * lint * Update src/lib/components/AssistantSettings.svelte Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> --------- Co-authored-by: Victor Mustar <victor.mustar@gmail.com> Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>d4016bc
-
Limit number of fetched conversations in the API (#954)
Unverified signature* Limit number of fetched conversations in the API * Add pagination * use vare9ad67e -
Dynamic system instructions (#949)
Unverified signature* Dynamic system instructions * disable tag rendering if the feature is disabled * make time & date tags bold * fix bug enabling dynamic prompt on assistant creation * Move fetching at prompt building time * get rid of date & time tags * use `url=` for tags * add env flag check * Add more detailed errors in prompt * wording * token counter * modal update * wording * hide disabled if dynamic prompt is enabled * add template variables parsing * regex update * same regex * regex again * sys prompt max height * rm unused * Always use absolute URL in links * trying something * Revert "trying something" This reverts commit e30ab33f801fad31cbcaa7b89c47c79d4aca86a6. * wording * remove debug log * last wording tweak --------- Co-authored-by: Victor Mustar <victor.mustar@gmail.com>6887755 -
[Websearch] change context schema (#944)
MishigUnverified signature2e2f16c
-
🚸 When a user signs up they're directly logged in (#952)
Eliott C +2: coyotte508, nsarrazin Unverified signature* 🚸 When a user signs up they're directly logged in * lint --------- Co-authored-by: coyotte508 <coyotte508@protonmail.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>506e596 -
add api assistants endpoints (#951)
Kevin CATHALY +2: Kevin CATHALY, nsarrazin Unverified signature* add api assistants endpoints * lint --------- Co-authored-by: Kevin CATHALY <alakme@kevins-macbook-pro.home> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>5f64024 -
Count system prompt tokens (#850)
Mishig +1: nsarrazin Unverified signature* Count sysmte prompt tokens * show error only once * fix * fix css * simplify * fix * simplify * Revert "simplify" This reverts commit 61c0a2281f9795c4a4351d9ad473993a3c01c59f. * `model.tokenizer` config & fix reactivity issues * rm gated tokenizer * use `truncate` --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>50d8483 -
Enhance Dynamic User Attribute Handling in OIDC Integration (#885)
Chang Chi, Meng +2: nsarrazin, ‘XGungo’ Unverified signature* Refactor `updateUser` to Support Dynamic `nameClaim` Configuration * style: run Prettier to fix lint errors * Validate NAME_CLAIM in OIDConfig schema * Refactor userData parsing --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com> Co-authored-by: ‘XGungo’ <‘daniel2000890311g@gmail.com’>c6129c3 -
feat: smooth and combine token output (#936)
Liam DyerUnverified signature* feat: smooth and combine token output * fix: stop generating button not triggering message updates abort8583cf1
-
Modals: dont close if text is selected (#943)
Unverified signaturedont close if text is selected999407a
-
Update AssistantSettings.svelte (#941)
Unverified signature2ce726f -
Store user agent in conversation (#940)
Unverified signature* Store user agent on conversation creation * casing headerd196c64
-
Prepend domain filters in search query generation (#932)
Unverified signature233d2a9 -
Fix model identification when creating conversations (#820)
Unverified signaturePR #181 introduced a model ID field so that models could be switched out without breaking existing conversations. However, the new conversation endpoint incorrectly uses the model name instead of ID, so without this fix it was not possible to have a model with a different ID and name. Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>7849c30 -
Show error when webpage cannot be reached or parsed (#930)
Unverified signaturee04d4e8 -
Fix multi domains for assistants (#929)
Unverified signaturecbf4205 -
Remove extra > in URLs (#931)
Unverified signature89f9b29 -
Anthropic Endpoint Support (#923)
Liam DyerUnverified signaturefeat: anthropic endpoint5a31018
-
Add websearch controls for assistants (#812)
Unverified signature* remove query modifiers from generateQuery * Add backend for assistant RAG * Add front-end for updating RAG assistant * enable web parser to return plaintext directly for matching headers * Update websearch flow for handling assistant rag preferences * Add our old blocklist to .env.template * Enable websearch to run on messages depending on assistant requirements * reorganized imports * Rename vars * use projection * Add environment variable for assistant rag * fix assistant rag on runwebsearch * fix styling if rag is disabled * make sure we always omit credentials when fetching web pages * Add new checks for SSRF, with a new env var `ENABLE_LOCAL_FETCH` * Use DNS to check if the links are local or not * Add a websearch indicator * Add more tags to parser * Add indicators * Display RAG options in settings view * ui * fix rag detection * bit more spacing * fix button position in assistant form * wording (mainly) …3f5871c
-
Fix prompt caching on llama.cpp endpoints (#920)
Unverified signatureExplicitly enable prompt caching on llama.cpp endpoints Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>eb071be -
fix: Prompt bypasses login (#921)
Kartik ShettyUnverified signatureFixes#879 checking login requirement in chat window2edb278
-
Add openai embeddings (#915)
Martok88 +1: nsarrazin Unverified signature* Add OpenAI embedding compatibility * Use OPENAI_API_KEY by default * lint * Add default OpenAI URL replace `authorization` by `apiKey` * Add a note in readme --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>f7db219 -
Remove double meta tags on models page (#918)
Unverified signature* Remove double meta tags * Remove unknown property0081568 -
Direct model page (#858)
Unverified signature* Direct model page * Remove auto redirect * fix thumbnail * css warning * change url for models * instantSet from settings * Get rid of redirect * thumbnail * also link from /models * use public app color --------- Co-authored-by: Victor Mustar <victor.mustar@gmail.com>64b910e -
Return an error on unknown model in new conversation (#916)
Unverified signature403d4bd
-
Make assistant settings form fill the modal (#900)
Unverified signature* Make assistant settings form fill the modal * tweaks * Use layout groups instead of parsing the url * fix console error & overflows * scroll on dialog instead --------- Co-authored-by: Victor Mustar <victor.mustar@gmail.com>315e56b -
Include last chunk in websearch context (#912)
Unverified signatureFix bug where last chunk was dropped in websearch8e839b8 -
Make sure preprompt is set on open ai endpoint type (#913)
Unverified signature* Make sure preprompt is set on open ai endpoint type * fix preprompt passing to conversationbcfa394
-
[Assisntans filter] More UX fixes (#908)
MishigUnverified signature* [Assisntans filter] More UX fixes * rm unused09eb258 -
[Assistants filter] Make UI more responsive (#906)
MishigUnverified signature7f7375d -
Add limits on API endpoints (#886)
Unverified signature* Add limits on messages, conversations, assistants and messages/minute * Add max message length limit * remove rate limits from public config * add `RATE_LIMITS` to secrets * Add `MESSAGES_BEFORE_LOGIN` to secrets * replace `RATE_LIMITS` by `USAGE_LIMITS` * replace `RateLimits` by `usageLimits` and only get nEvents if needed * rename schema too * replace \r\n by \n537b6f5
-
[Assistants filter] Fix bug (#902)
MishigUnverified signature21c9b41