Spaces:
Paused
Paused
Commit History
-
feat: add a local endpoint type for inference directly from chat-ui (#1778)
Unverified signature* feat: add a local endpoint type running llama.cpp from chat-ui * fix: build image * fix: lock file * wip: try to make it more reliable * feat: load chat template from .gguf file * feat: load gguf models from `models/` folder * fix: default config * feat: make endpoint use chatSession instead of completion * refactor: improve exit handling, exit immediately on second sinal * fix: various fixes to improve reliability when calling multiple models at once * docs: add instructions for adding .gguf files to the models directoryde36cdc
-
fix(continue): fix continue feature (#1459)
Unverified signature* fix(continue): more reliable end token stripping before we would try to strip end tokens once in order from the stop array, now we strip all end tokens from the array until we can't anymore * fix(tools): remove generation prompt in continue modec03be55
-
Community tools (#1250)
Unverified signature* wip community tools * push * fix * bugfix * pass inputs to gradio correctly * full inputs for imagegen * lint * update gradio * fix call to gradio * fix imagegen tool * fix name * fix image display * Community tools (#1297) * work on tools * wip * icon * page * use IDs for every tools * improve tools page * wip * add optimized deps * refacto 1tool=1function * Add preview page * fix active indicator * fix text alignment * fix populate script * tooledit * fixes * better inputs * fix console error & cancel button * upload new tools * edit * improve lint * working community tools * fix active featured check * Simplify outputs in user form * fix non file outputs * fix imagegen default tool * add community tools popup * redirect gradio API calls through chat-ui backend * better usecount * Better loading & output element * better redirects & auto activate * bugfixes * fix migration changes * Add feature flag for tools * fix tools menu * Keep tr…0c3e3b2
-
Function calling (#996)
Unverified signature* Initial work on function calling * wip * Add websearch as a tool * lint * smol * Move tools to their own files * directly answer check * Add text2img tool * group tool calls together * show retry even if no message * fix trailing urls * Add image popup * format * wip * clean-up * better loading indicator * text colors * extra example to summarize * switch default model * Add fetchUrl tool * wip * Add latest gradio * fix types * version bump sharp * Basic tools menu * working menu * fix menu positioning * deps fix * add deps * cleanup * more cleanup * cleanup * package cleanups * moar cleanup * ui update * Update ChatMessage.svelte * upgrade gradio dep * lint * refactor and pass results to cohere * feat: code interpreter tool * fix: add e2b dependency * feat: working TGI endpoint with tool results * feat: allow image model to expand to 90dvw * fix: dont block on title gen * bump sharp * misc cleanup * fix url fetcher, adjust tool typing *…564e576
-
filter system messages when building prompt
Unverified signaturece45571 -
Conversation trees (#223) (#807)
Unverified signature* work on branching * branching * work on input field * wip * wip * helper stuff * pass tests * add type guards and clean up type requirements * fixed shared conv type * more helpers stuff * clean up code * addChildren helper * addSibling * add test for addSibling & refacto addChildren tests * backend work pt. 1 * backend done * add children property to messages for easier frontend rendering * fix message id type rail * front-end work on simple linear conversation * fix title generation * convert conversations on post * server side retry works with branching * clean up buttons * fix retry feature backend * Send new messages in any subtree * make edit previous prompts feature work * fix padding * revert unneeded changes * bring back pending message * fix front-end streaming * fix initial message * Revert "fix initial message" This reverts commit 6257fe8789c52a20e7506aa453efda55c16e95bb. * Fix bug subtree state refresh * fix continue feature on shared co…2a808d7
-
Remove tabs in websearch prompt (#754)
Unverified signature75c6c34
-
Continue generation feature (#707)
Unverified signature* Initial work on continue feature * Move continue button * Fix websearch with continue * Make it work with every model * Update src/routes/conversation/[id]/+server.ts Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> * fixes * async all the things * add reduce comment * remove log * Only show loading indicator if not continuing --------- Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>c51ecfb
-
Add support for tgi multimodal models (#531)
Unverified signature* wip: add support for tgi multimodal models * wip work on passing images to prompt * working idefics config! * rm allowed conv feature * lint * Add image resizing * fix ssr * add upload button * add delete button * misc formatting * lint * server file size check * optimistic update of images * retry with images * fix websearch button * lint * better error handling & max one image at a time * replace test image by blank one * disable loading on page change * Fix sharing of images * fix comments * Update filedropzone (#544) * Update src/lib/buildPrompt.ts Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> * small tweaks * Fix merge conflicts * lint * wildcard image mime type * fix lint and comment * added comments * added comment about file size * Readme update --------- Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> Co-authored-by: Victor Mustar <victor.mustar@gmail.com>241ba68
-
Update websearch prompting & summary prompting (#503)
Unverified signature* Use the task model for websearch query generation * summary with examples in chat format * Update to websearch prompting - Removed web search template - Added examples in `generateQuery` - Passed previous questions when generating the web search query - Added previous questions to the bottom of the context window in `buildPrompt` when using websearch * wait for model if needed * rm console.log * get rid of regex * added a few time related examples * Update src/lib/server/websearch/generateQuery.ts Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu> * reformat yesterday * test * fix whitespace * remove extra whitespace for mistral * removed mistral extra whitespace * Update src/lib/server/summarize.ts Co-authored-by: Victor Muštar <victor.mustar@gmail.com> * Update src/lib/server/summarize.ts Co-authored-by: Victor Muštar <victor.mustar@gmail.com> * add an emoji if none is found in the first three characters --------- Co-authored-by: Mishig <mishig.davaa…43606a3
-
Backend refactor for streaming endpoints (#444)
Unverified signature* wip: complete refactor of streaming backend * working refactoring * fix missing first token & perf regression in output quality * lint * Fix websearch loading from db * fix loading * fix invalidate * remove logs * fix SSR error * typo: paragraphs * fixed save on abort * lint * lint * remove debug log in console * lint for reale5f4e9a
-
[Websearch] update (#427)
Mishig +2: julien-c, victorUnverified signature* Fix reuqest body * update webSearchQueryPromptTemplate * update generate google query parser * Add today's date to google search query creator * crawl top stories if exts; remove answer_box & knowledgeGraph * Create paragraph chunks from top articles * flattened paragprah chunks * update status texts * add gradio client * call gradio app for RAG * Web scrape only "p, li, span" els * add MAX_N_CHUNKS * gradio result typing * parse only <p> elements * rm dev change * update typing WebSearch * buld RAG prompt * Rm dev change * change websearch context msg from user to assisntat type * use hosted gradio app * fix lint * prompt engineering * more prompt engineering * MAX_N_PAGES_SCRAPE = 10 * better error msg * more prompt engineering * revert websearch prompt to previous * rm `top_stories` from websearch as the results are not good * Stop using gradio client, use regular fetch * chore * Rm websearchsummary references as it is no longer used * update readme …0fc59f9
-
fix auth on websearch (#410)
Unverified signaturea7f2fe0
-
Support custom system prompts from the user (#399)
Unverified signature* Support custom system prompts from the user * linter * types & lint11983d2 -
Make all prompt templates configurable (#400)
Unverified signature* Make all prompt templates configurable This PR enables all prompts to be configurable using handlebar templates as described in #382. For backward compatibility the old hardcoded templates are reimplemented as the default templates. The old template parameters such as `preprompt`, `userMessageToken`, `userMessageEndToken`, `assistantMessageToken`, `assistantMessageEndToken` are now considered legacy. They still work as they are exposed as variables to the default template. However, new prompt configurations should not use these. And it is recommended that the legacy support is eventually removed. As an example, this is how the default chat prompt template is implemented: ``` {{preprompt}} {{#each messages}} {{#ifUser}}{{@root.userMessageToken}}{{content}}{{@root.userMessageEndToken}}{{/ifUser}} {{#ifAssistant}}{{@root.assistantMessageToken}}{{content}}{{@root.assistantMessageEndToken}}{{/ifAssistant}} {{/each}} {{assistantMessageToken}} ``` In addition, this PR fixes an issue wh…f58e466
-
allow different user and assistant end-token (#375)
Unverified signature* allow different user and assistant end-token For models like Llama2, the EndToken is not the same for a userMessage and an assistantMessage. This implements `userMessageEndToken` and `assistantMessageEndToken` which overwrites the messageEndToken behavior. This PR also allows empty strings as userMessageToken and assistantMessageToken and makes this the default. This adds additional flexibility, which is required in the case of Llama2 where the first userMessage is effectively different because of the system message. Note that because `userMessageEndToken` and `assistantMessageToken` are nearly always concatenated, it is almost redundant to have both. The exception is `generateQuery` for websearch which have several consecutive user messages. * Make model branding customizable based on env var (#345) * rm open assistant branding * Update SettingsModal.svelte * make settings work with a dynamic list of models * fixed types --------- Co-authored-by: Nathan Sarrazin <sarrazin…5ebe152
-
Add initial support for web browsing (#237)
Unverified signature* basic poc for web search * * Hide feature when serpapi_key is not defined * handle error case where serpapi failed * only use user queries for generating the query * Update src/lib/buildPrompt.ts Co-authored-by: Eliott C. <coyotte508@gmail.com> * Update src/routes/+layout.server.ts Co-authored-by: Eliott C. <coyotte508@gmail.com> * refactored getQueryFromPrompt * add jsdom to package.json * begin work on fetching webpage content * Update .env Co-authored-by: Eliott C. <coyotte508@gmail.com> * prettier fix * Add feature for scraping webpages * refactored search functionality - now gets triggered from a separate endpoint - results are stored in db - results can be displayed in their own endpoint * Added a stream to send updates from backend on web-search endpoint * made stream more reliable * Add front-end to web search feature * made sure the web results button appears on newly posted messages * close modal when message is done generating * removed log statements *…0c6af63
-
Disable models (#187)
Adrien Denat +1: Eliott C.Unverified signature* add ability for a model to be disabled * fallback to default model if user has invalid/disabled model in settings * set conversations to read-only if conv model is disabled * add better disabled state on chat input * fix inverted if statement * remove bigcode from .env * fix not updating settings Co-authored-by: Eliott C. <coyotte508@gmail.com> * refactor solution to use an OLD_MODELS env var instead * OLD_MODELS needs to be in .env but can be empty * fix typing issue + typo * refactor models validation * old models displayName is optional * set read only prop on user message not assistant messages * remove console.log * ♻️ Refacto isReadOnly * 🩹 Fluff: use 410 http code --------- Co-authored-by: Eliott C. <coyotte508@gmail.com>c202241
-
🐛 Stop bigcode prompts (#170)
Eliott CUnverified signaturef16c630 -
Models selector (#164)
Adrien Denat +3: victor, julien-c, coyotte508Unverified signatureCo-authored-by: Victor Mustar <victor.mustar@gmail.com> Co-authored-by: Julien Chaumond <julien@huggingface.co> Co-authored-by: coyotte508 <coyotte508@gmail.com>01b06a3
-
👷 Add CI to check types (#161)
Eliott CUnverified signature59de250
-
✨ Add preprompt (#124)
Eliott C +1: olivierdehaeneUnverified signatureCo-authored-by: OlivierDehaene <Olivier.dehaene@gmail.com>f504988
-
⚡️ Limit the number of tokens sent to the backend (#93)
Eliott CUnverified signatured4bec8b
-
Prettier update (#54)
Unverified signature* Update .prettierrc * prettify everthing prettify everything98051f8
-
✨ Save messages in backend (#31)
Eliott CUnverified signature92a7501