Spaces:
Paused
Paused
Commit History
-
update generate
3f85620 -
update generate
d2150e1
-
add logs
1c78f33
-
feat: improve export feature
- add once per hour rate limit - remove await blocks, start streaming zip right away - add stats to loggingd8a4377
-
feat: put export behind feature flag (#1862)
Unverified signature* feat: put export behind feature lfag * fix: update SHA tag configuration in deploy-prod workflow31d4584 -
fix: dont export whole websearch
aa6f1a7 -
fix: skip file if unavailable
a36bf4b -
feat: add admin only export feature
72becf3
-
fix: Improve error handling in generateFromDefaultEndpoint (#1853)
calycekr +1: nsarrazinUnverified signature- Refactor error handling in the generateFromDefaultEndpoint function to prevent the Node.js process from crashing when an AbortError occurs. - Wrapped the getEndpoint and endpoint calls within a try...catch block to ensure that exceptions are caught and the process remains stable. Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>63f4e60
-
fix: rename chat bug fix
2d7325b
-
fix: starting chat-ui with no .env.local
5b7c1e9 -
feat: add custom headers support to endpoint inference client
2fadb30
-
add headers content type
7e3696d -
feat: implement delete message functionality using API client
106688c -
refactor: move delete conv & title edit to new api
399bebf -
refactor: api cleanup (#1849)
Unverified signature5ad620b
-
fix: swagger config
62917ce -
refactor: use client API for spaces-config endpoint
93d2e4c
-
refactor: new API & universal load functions (pt. 2) (#1847)
Unverified signature* feat(API): refactor API with Elysia * feat: initial elysia setup * feat: replace conv/[id] load function with universal * fix: delete v1 catchall * wip * fix: response type * fix: add cors * feat: more routes in tools & assistants * refacto: use normal svelte fetch in `/assistant/[assistantId]` * refacto: use normal svelte fetch in `conversation/[id]` * feat: use universal load function for `tools/[toolId]` * wip: removing more server load function stuff * feat: more routes to universal load functions * feat: more routes to universal * refactor: move tools loading to API endpoint * refactor(api): implement tools search API endpoint and move load function * fix: types on tool search * refactor: update assistant route and remove redundant page load function * refactor(api): move assistants page load function to api call * refactor(settings): remove waterfall loading * refactor: main load function * fix: types * feat: improve fetchJSON to handle empty responses * …612f16b -
Revert "refactor: new API & universal load functions (#1743)"
This reverts commit 7961ae74d12cc62461929d92aca0adac48b72d9a.813f132 -
refactor: new API & universal load functions (#1743)
Unverified signature* feat(API): refactor API with Elysia * feat: initial elysia setup * feat: replace conv/[id] load function with universal * fix: delete v1 catchall * wip * fix: response type * fix: add cors * feat: more routes in tools & assistants * refacto: use normal svelte fetch in `/assistant/[assistantId]` * refacto: use normal svelte fetch in `conversation/[id]` * feat: use universal load function for `tools/[toolId]` * wip: removing more server load function stuff * feat: more routes to universal load functions * feat: more routes to universal * refactor: move tools loading to API endpoint * refactor(api): implement tools search API endpoint and move load function * fix: types on tool search * refactor: update assistant route and remove redundant page load function * refactor(api): move assistants page load function to api call * refactor(settings): remove waterfall loading * refactor: main load function * fix: types * feat: improve fetchJSON to handle empty responses * …50aea0a
-
feat(reasoning): support end token search across multiple chunks (#1838)
Unverified signature* feat(huggingchat): model update 27-05-25 * feat: update prompt examples in config * feat: revert model config changes6cd421f
-
[WIP] - Add the pop-up search (Ctrl/Command + K) to search entire conversation history (#1823)
Hong An Tran +2: krramos, nsarrazinUnverified signature* UI for crtl/command + k for conversation search * UI for ctrl/command+k * Added fetch conversations and filter conversations functions * WIP - finish with the first draft of popup-search * WIP - Finish the first version pop up search * WIP - Finish the first version pop up search * Remove unnecessary codes * Fixed formatting errors * Fixed formatting errors * refactor: search functionality * fix: revert those changes * fix: lint * chores: clean up unused comment --------- Co-authored-by: kenneth.ramos95 <kenneth.ramos95@gmail.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>c6ccfa4
-
fix: remove quotes from search query to prevent exact match search (#1834)
Unverified signaturefix: remove quotes from search query to prevent exact match search when running locally using serper Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>3f26498 -
fix: catch errors in default model
2ee0fbc
-
fix: remove redundant status update in streaming
7da664f
-
fix: only import node-llama-cpp if needed and skip for huggingchat image
72db8f3
-
fix: stop button working properly
260c3b7 -
fix: make sure document parser is disabled if not required
67302d2
-
fix: rm error in retrying when tool calls are not parsed properly
a327608
-
New `InferenceClient` endpoint type (#1813)
Unverified signature* work on hf inference endpoint * working tools * fix: debug tool * feat: working tools with new endpoint type * feat: move config to HfInference * wip * fix: hf inference endpoint * refactor: rename endpoint * fix: rendering * feat: working tools on every supported model * fix: multimodal * refactor: rename endpoint type * refactor: base URL * fix: prevent simultaneous provider and baseURL usage * fix: disable tools on qwen 2.5 vl * feat: make sure json is correctly formatted4906f37
-
fix: build local llama (#1805)
Unverified signature* fix: build local llama * fix: node build local * fix: docker build * feat: use group for CI? * fix: github actionsf8f7cda
-
feat: allow storing env variable in DB (#1802)
Unverified signature* feat(config): wip, make config controllable from DB, public side for now * fix: build * feat(config): add config manager env var toggle * wip: make backend config use config manager * fix: typechecks * fix: circular import * refactor: init hook sveltekit * fix: disable config manager during tests * refactor: use enum for semaphore, move delete from auto after 60s to separate `deleteAt` field * feat: config manager checks for updates on requests * fix: config script exit * fix: remove top-level awaits * fix: script await * feat: filter config keys based on public environment variables for more security * fix: change import to type for public environment variables48059af
-
feat: allow strings in `MODELS` env var (#1791)
Unverified signature* feat: allow strings in `MODELS` env var This feature lets you simplify your `MODELS` env var by just specifying a bunch of model names on the hub and letting chat-ui deal with the rest. For example ``` MODELS=['hf:HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF'] ``` would automatically download the relevant file and serve it locally with `node-llama-cpp` * fix: make it simpler to usef887995 -
refactor: make env imports match the rest of the app in `adminToken.ts`
4f27ac2 -
Enable/Disable reasoning summary using .env (#1760)
Unverified signature* enable/disable reasoning summary using .env * refactor: rename env variable and move readme section to reasoning part. --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>09dfa5f -
Fix system message handling to preserve user-configured system prompts (#1764)
stoXe +1: nsarrazinUnverified signaturePreviously, when a preprompt was provided, it would completely replace any user-configured system message instead of being prepended to it. Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>bdb443a
-
feat: improve port detection on admin cli login
f6a70cc
-
feat: admin CLI login (#1789)
Unverified signature* feat: implement admin token management and CLI login functionality - Added `ADMIN_CLI_LOGIN` and `ADMIN_TOKEN` to the environment configuration. - Introduced `AdminTokenManager` for handling admin sessions and token validation. - Updated user session handling to include admin status. - Enhanced API routes to utilize admin checks based on the new token management. - Modified frontend components to reflect admin status correctly. - Added a new endpoint for validating admin tokens. * fix: remove token after validationafbe0de
-
fix: lint
64682dd -
fix: docker image llama.cpp error catching
65e6be3 -
Add `toolId` to ToolCall and use it in tool results (#1787)
Kelig +1: Kelig LEFEUVREUnverified signature* Add `toolId` to ToolCall and use it in tool results * Make `toolId` optional in ToolCall interface --------- Co-authored-by: Kelig LEFEUVRE <klefeuvre@alpes-controles.fr>82b61d0 -
fix: build llama.cpp locally in dockerfile (#1788)
Unverified signature* fix: build llama.cpp locally in dockerfile * fix: build for good * refactor: move model folder to /data/modelsffc89fe
-
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
-
feat(db): use in memory db when MONGODB_URL not set (#1773)
Unverified signature* feat(db): allow use of in memory db when MONGODB_URL not set * fix(db): enhance database disconnection handling with server stop * feat(db): persist db to disk * fix: use proper root folder in both build & devd4471e3
-
fix: trigger redeploy
73268d4 -
fix: give more buffer to reasoning
8ce2fb0
-
fix(preprocessMessages): clarify web search context in final message content
150ff48 -
feat: improve task model tool calling (#1755)
Unverified signature* feat: improve task model tool calling * feat(prod): add tokenizer for Hermes-3-Llama-3.1-8B to task configurationd37f9ca -
fix(endpoints): fix for tool calling on hf inference with openai endpoint type (#1754)
Unverified signature* fix(endpoints): fix for tool calling on hf inference with openai endpoint type * moar fix * fix: typechecks185c2ff