Spaces:
Runtime error
Runtime error
Commit History
-
Clean up Dockerfile and prod environment config
efb37e7
-
HuggingChat 2026 (#1875)
Unverified signature* refactor: remove tokenizer-related functionality and dependencies - Removed tokenizer dependencies from package.json. - Deleted TokensCounter component and its usages across the application. - Updated model configurations to exclude tokenizer properties. - Refactored model processing logic to support only OpenAI-compatible endpoints. - Adjusted API responses to omit tokenizer information. - Cleaned up related utility functions and imports. * Remove web search functionality and related components - Deleted endpoints for various web search APIs (serpApi, serpStack, serper, webLocal, youApi). - Removed generateQuery function and its usage in search. - Eliminated web search related types and interfaces from the codebase. - Updated Assistant and Conversation types to remove references to web search and embedding models. - Cleaned up related utility functions and message updates for web search. - Adjusted API routes and components to reflect the removal of web search features. - Updated…7bf1507
-
fix: reduce min pods following closure (#1865)
Unverified signaturede0d97b
-
fix(infra): remove group order
Unverified signatureSigned-off-by: Adrien <adrien@huggingface.co>7469079 -
chore: add internal (#1828)
AdrienUnverified signatureSigned-off-by: Adrien <adrien@huggingface.co>244889b
-
fix(hchat): `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` endpoint url
8d11e8e
-
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(cohere): 404 due to org rename (#1815)
oOraph +2: Raphael Glon, nsarrazin Unverified signature* fix(cohere): 404 due to org rename Signed-off-by: Raphael Glon <oOraph@users.noreply.github.com> * fix: old models `transferTo` --------- Signed-off-by: Raphael Glon <oOraph@users.noreply.github.com> Co-authored-by: Raphael Glon <oOraph@users.noreply.github.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>51b7de0 -
fix(huggingchat): sed api-inference (#1814)
oOraph +1: Raphael GlonUnverified signatureSigned-off-by: Raphael Glon <oOraph@users.noreply.github.com> Co-authored-by: Raphael Glon <oOraph@users.noreply.github.com>72dbfaf
-
fix: correct typo in prompt example in prod.yaml
ee5dfa3
-
feat: update banner
28954fa -
feat: new model 29-04-25 (#1808)
Unverified signaturee390fd0 -
fix: config bits
7fbafc9 -
feat(huggingchat): update available models
- remove llama 3.2 - remove qwen coder - add qwen 2.5 VL 32Bbb8ac6e
-
feat: add Mistral-Small-3.1-24B-Instruct-2503 model and Phi-4 (#1806)
Unverified signature9111ea7 -
fix: prod config
29851bb -
feat: rework example layout to work better on mobile
2335377
-
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: 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(hchat): update endpoint for qwq
c44d626 -
fix: add missing examples in prod config
8326cc3
-
fix: duplicate endpoints in task model
49c41c7 -
Revert "Revert "feat(config): add gemma 3 to prod config (#1753)""
This reverts commit 4b7b51e0efcd4978517e75ac123a56b31bd488f3.9308560
-
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 -
Revert "feat(config): add gemma 3 to prod config (#1753)"
This reverts commit 002c21bb4567fbfb9911eca804d532e36b5a3f4b.c7c1fe9 -
feat(config): add gemma 3 to prod config (#1753)
Unverified signature* feat(prod): add gemma 3 to prod config * feat: add multimodal mode to gemma 3 * docs: update Gemma 3 model description to highlight multimodal support9828685
-
fix: improve tasks performance
28b6d44
-
feat(model): configure Llama-3.1-8B-Instruct with OpenAI-compatible endpoint
55ff303 -
feat(tasks): use tools for tasks if available (#1749)
Unverified signature* feat(tasks): use tools for web search query if available * feat(websearch): improve query generation with error handling and logging * feat(tools): implement generic tool output extraction utility This commit adds a new `getToolOutput` utility to standardize tool interaction across different tasks like title generation, reasoning summary, and web search query generation. The utility supports extracting tool outputs using a consistent approach, with fallback mechanisms and error handling.6655689
-
feat(hchat): add QwQ-32B to prod HuggingChat config (#1746)
Unverified signature7139d72
-
fix(prod): model config
2b6c120 -
fix(huggingchat): add additional stop token for model configuration
a6bb678
-
fix(hchat): update internal endpoint (#1716)
Unverified signature54a5aad -
refactor: remove deprecated EXPOSE_API environment variable
a06cb0c
-
fix: handle no beginToken for token based reasoning models (#1713)
Unverified signature* refactor: remove debug console log in updateLocalEnv script * fix: handle no beginToken for token-based reasoning modelsa68038a
-
feat(hchat): move Llama 3.3 70B as the default model
eccf709
-
feat(chart): use inference proxy (#1688)
Unverified signature* feat(chart): use inference proxy * fix: also use `HF_API_ROOT` for embedding endpointscf63293
-
Update prod.yaml
AdrienUnverified signaturea11228d -
feat(hchat): Add additional network policy allowed blocks (#1679)
Unverified signatureef4a8e3
-
fix(chart): use dedicated nodes (#1675)
Unverified signatureac50b0e
-
feat(hchat): update banners
Unverified signaturedec1307 -
feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config (#1660)
Unverified signature* feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config * feat: hide reasoning modal when its empty * fix: put r1 model higher in lista38e9de
-
fix: update name of task model
Unverified signature47f2b57
-
feat: show login modal if login is required for creating assistants & tools (#1640)
Unverified signature14ef8d0
-
feat: new tool UI (#1630)
Unverified signature* feat: new tool UI * wip community tools support * fix: community tools support * fix: line heights * fix: MIME types * fix: remove debug logs * fix: make sure file upload is always last * fix: always enable document parser when a pdf is present in the conversation * fix: use correct icon for document upload * fix: make sure community tools use their custom icons correctly * feat: add button to browse community tools * tweak buttons * add some tooltips * fix: bug in file upload tooltips * fix: lint --------- Co-authored-by: Victor Mustar <victor.mustar@gmail.com>b104edb
-
fix: add banner for 3.3
Unverified signature9831629 -
config(hchat): model update 06-12-24 (#1617)
Unverified signature* fix(hchat): add new model * fix: description21ed304 -
feat: improve tool calling & add tools to qwen 2.5 72b (#1615)
Unverified signature* fix: clean up tool calling more inline with latest changes in transformers lib and adds tool calling to qwen 2.5 72b * fix: add more field name options * fix: make tool calls a bit more robust642ce40
-
Revert "Remove unneeded QwQ System prompt (#1610)"
This reverts commit 7579437d39b0c8aa9fb8874777d28755e4a5f783.8a59b35
-
Remove unneeded QwQ System prompt (#1610)
Unverified signature* Remove unneeded QwQ System prompt * Update chart/env/prod.yaml --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>b717e16
