Commit History
-
Move vars to dynamic, add metrics (#1085)
Unverified signature* Add healthcheck route * Add prom client with basic metrics * wip: serve metrics on a different port * exclude server from tsconfig * latest * refacto(all): use class & singleton * refacto(all): use class & singleton * refacto(all): add request logs * Make all the env vars dynamic (#1092) * Add truncate to task model (#1090) * retry text area height (#1091) * Make all the env vars dynamic * only check for db at runtime * remove secret from build step * improve dockerfile * Wrap db in singleton * add .env.local to dockerignore * changes to dockerfile * lint * aborted generations * move collections build check * Use a single dockerfile * lint * fixes * lint * don't return db during building * remove dev --------- Co-authored-by: Victor Muštar <victor.mustar@gmail.com> * refacto(all): update default metrics port * fix recursion error * add version check * revert vite preview * Move request …98b1c51
-
return only valid models in the API (#1064)
Kevin CATHALYUnverified signaturec265074 -
add default value for description and examples in the API route for models (#1063)
Kevin CATHALYUnverified signature815e76f
-
Final fix to assistants display logic (#1056)
Unverified signature84d0edd -
Only require featured assistants for other users' assistants (#1054)
Unverified signature7ede405 -
fix: See all your assistants regardless of usercount (#1053)
Unverified signature95b3715 -
Move featured assistant check behind `REQUIRE_FEATURED_ASSISTANTS` (#1043)
Unverified signatureMove featured assistant check behind `REQUIRE_FEATURED_ASSISTANTS` env var (#997)7d34920
-
add an endpoint to api to get an assistant by id (#1020)
Kevin CATHALYUnverified signaturec2f5b76
-
Limit number of fetched conversations in the API (#954)
Unverified signature* Limit number of fetched conversations in the API * Add pagination * use vare9ad67e
-
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
-
Models page (#849)
Unverified signature* add models page * add logo * models discussion * add default hint * Update +page.svelte * mishig review * fix typecheck --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>25c844d
-
add an api endpoint to get current user's informations (#763)
Kevin CATHALYUnverified signatureb954b26
-
Add conversation API endpoint to get conversation (#698)
Kevin CATHALY +2: Kevin CATHALY, Eliott C.Unverified signature* Sorting conversation list in api response * Add new conversation endpoint in the api * only expose needed param in the API * Update src/routes/api/conversations/+server.ts Co-authored-by: Eliott C. <coyotte508@gmail.com> * linter * fix type --------- Co-authored-by: Kevin CATHALY <alakme@kevins-mbp.home> Co-authored-by: Eliott C. <coyotte508@gmail.com>ee47ff3
-
Add an endpoints to expose models and conversations (#694)
Kevin CATHALY +3: Kevin CATHALY, nsarrazin, Eliott C. Unverified signature* Add an endpoint to expose available models * Add a route to list conversations history * use authCondition to filter current user's conversations * map models object to only keep needed params and also change the route path to /api/models * Put API feature behind feature flag (#695) * Puts the API behind a feature flag * Update src/hooks.server.ts Co-authored-by: Eliott C. <coyotte508@gmail.com> --------- Co-authored-by: Eliott C. <coyotte508@gmail.com> * add a better error when session's cookie is missing * rename error to message to be consistent --------- Co-authored-by: Kevin CATHALY <alakme@kevins-mbp.home> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com> Co-authored-by: Eliott C. <coyotte508@gmail.com>c30d191
-
✨ Save messages in backend (#31)
Eliott CUnverified signaturead02fa3 -
🩹 Fix proxified headers + remove guard in hook (#27)
Eliott CUnverified signature3ddb8c6
-
Split app structure & create convos (#20)
Eliott CUnverified signature1b66f8d -
🔧 Standardize environment config (#13)
Eliott CUnverified signature3ebd805 -
Migrate to new model + proxy from server (#5)
Adrien Denat +1: julien-c Unverified signature* use fork of hf.js to support fully custom endpoints for testing purpose * proxy textGenerationStream call to the backend to hide token from client * migrate to patch-package instead of pnpm * fix issue after merge conflict * use env var instead of hardcoded value for endpoint * fix messages not being split between assistant/user * fix stream response sometimes not split by token * remove PUBLIC_ from private env variables + rename ENDPOINT to MODEL_ENDPOINT * only set hf token as private, model can stay public * move HF_TOKEN to a dynamic env * fix env var import typo * remove @microsoft/fetch-event-source * update parameters to be identical to Python demo * small refactor to avoid typing issue * cleanup while loop Co-authored-by: Julien Chaumond <julien@huggingface.co> * make comment clearer on what is happening on stream chunks split * fix chunk spliting not being handled properly * cleanup model tokens sometimes containing "<|e…c8d90f4