Commit History
-
Show the assistant model name in the chat input (#1006)
Unverified signature2435b95
-
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
-
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
-
[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
-
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
-
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 -
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
-
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 -
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
-
Automated migration setup (#897)
Unverified signature* Initial migration setup for chat-ui * refresh the lock regularly while the migrations are running * add index for migrationResults * clean up code a bit * Don't try to run migrations when sveltekit is building * simplified lock code * Add early check for migrations being done Reduce timer for lock * migration use `generateSearchTokens` * Update src/lib/migrations/migrations.spec.ts Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> --------- Co-authored-by: Mishig Davaadorj <dmishig@gmail.com> Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>4dbcbb6 -
[Assistants] Filter on names (#841)
Mishig +3: Eliott C., nsarrazin, victor Unverified signature* [Assistants] Filter on names * Add `$text` index on `assistant.name` (#844) * add maxlength * better experience * use `$meta: "textScore"` * Update src/routes/assistants/+page.server.ts Co-authored-by: Eliott C. <coyotte508@gmail.com> * null, not undefined * [Assistants] Filter on names (using searchTokens) (#873) Filter with `searchTokens` * input * rm extra whitespace * hide UI before migration * rm ad-hoc migration --------- Co-authored-by: Eliott C. <coyotte508@gmail.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com> Co-authored-by: Victor Mustar <victor.mustar@gmail.com>10dbbd6 -
Fix issue with "continue" feature on llama.cpp endpoints (#898)
Unverified signature714ff2c -
Bug Fix: Json Decoder aggessively pulls json (#867)
Matthew Current +1: nsarrazin Unverified signature* wait for newline char b4 decoding json * remove noisy console log * linters --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>9c5a826
-
Navigation collapse (#893)
Unverified signature* add collapse behaviour * add collapsedNavigation setting * Revert "add collapsedNavigation setting" This reverts commit 6c9baf480834ba5bf2b5bdd3cbf93232afce02a7. * last tweaks * rm unused * Update src/lib/components/ExpandNavigation.svelte Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> --------- Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>3abaf81
-
fix retry button showing while loading (#894)
Unverified signaturee283983 -
Improve error handling when posting new messages (#892)
Unverified signature* send an error or if no text was written * fix loading indicator * fix lastIsError code0f7a55d
-
Use `uuid` for message ID generation instead of crypto method (#882)
Unverified signatureBecause `crypto.randomUUID()` is not available on non-secure contexts (for example `http` versions of chat-ui), this would break on non-https deployments of chat-ui. This should fix #870 and fix #868d8e839e
-
Pass websearch to `preprocessMessages` (#876)
Unverified signatureThere was a bug where the websearch was fetching relevant chunks for context correctly but it wasn't getting injected into the prompt, this PR fixes that.00443e1
-
Small UX updates assistants (#872)
Unverified signature482a094
-
/models tweaks (#864)
Unverified signature* direct link to new chat * mobile spacing * show model logo on new chat * temp: hide "new chat" * exemples tweak8ffc49e
-
Allow retry on shared conversations (#839)
Unverified signaturea4e40b1 -
Add gemma model to prod config (#854)
Unverified signature* Add `google/gemma-7b-it` to production config * Add gemma prompt format to PROMPTS.md * Make sampling parameters optional5f78b90