Spaces:
Runtime error
Runtime error
Commit History
-
feat(tree): Add ELK port-based layout and persona-specific branching
Andrewcb5990d
-
feat(server): update message preprocessing to handle tree structure
Andrew8293c27
-
fix CI (#1884)
Eliott C.Unverified signature* fix CI * add playwright as dev dep * lint * clean up spaces-config with community tools * try to make mongo run?3b53c7a
-
Refactor token parameters to standardize naming across models and generation settings
dd2acb7
-
Omni multimodality (#1880)
Unverified signature* Add multimodal fallback support to router * fix: improve error handling for multimodal model routing * Handle multimodal messages without files9092d43
-
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
-
feat: add custom headers support to endpoint inference client
2fadb30
-
fix: only import node-llama-cpp if needed and skip for huggingchat image
72db8f3
-
fix: make sure document parser is disabled if not required
67302d2
-
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
-
Fix system message handling to preserve user-configured system prompts (#1764)
stoXe +1: nsarrazin Unverified 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
-
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
-
fix(preprocessMessages): clarify web search context in final message content
150ff48 -
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 -
feat(openai): added support for non-streaming o1 (e.g. Azure) models (#1687)
Unverified signature* feat(openai): added support for non-streaming o1 (e.g. Azure) models * feat(docs): add non streaming example * feat: moar docs --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>df0f84c
-
chores(svelte): migration to svelte 5 (#1685)
Unverified signature* chores(svelte): migration to svelte 5 * chores(svelte5): remove preventDefault & stopPropagation legacy handlers * chores(deps): version bumps * fix: closing modal works properly * fix: messagte loading reactivity * fix: loading indicator * fix: conversation list reactivity * fix: bug on tool logo rendering * fix: infinite loading circular dep * feat: hide new chat button on new chats * fix: move apply directive to main.css * fix: remove legacy syntax in `TokensCounter.svelte` * fix: replace legacy `run` with Svelte 5 `$effect` in NavMenu * fix: replace legacy `run` with Svelte 5 `$effect` in ScrollToPreviousBtn * fix: migrate `settings/[modelId]` page to Svelte 5 syntax * fix: replace legacy `run` with Svelte 5 `$effect` in ToolUpdate component * fix: migrate ToolEdit component to Svelte 5 syntax * fix: simplify login required handling in ChatInputa1a6daf -
fix: bedrock prepareMessages parameters (#1686)
Unverified signatureCo-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>415831f
-
Anthropic Tool Support (#1594)
evalstate +1: nsarrazin Unverified signature* support anthropic PDF beta * upstream merge, remove commented out console log line * Fixing type errors. the anthropic API does not yet include a "DocumentBlock" for support PDFs, so an extended type has been added to the endpoint. * changed document processor to async (matching image processor) * use the beta api types rather than custom extension * rudimentary tool testing * interim commit (tool re-passing, file handling) * remove merge error * tidy up, isolate beta classes to utils * anthropic tool calling support. * improve handling of directlyAnswer tool * fix streaming * slight tidy up to tools flow handling * fix: dont pass tools in final generation, instead deduce tools from tool results --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>69d5a1c
-
Add support for Amazon Nova (#1629)
Tarek Becker +1: nsarrazin Unverified signature* Add support for Amazon Nova * fix linting issue * fix: replace model.id check with `isNova` flag and remove debug logs --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>28c09f1
-
fix: disable caching on OpenAI-compatible endpoint type
Unverified signatured433f1d
-
fix: single step in cohere endpoint type (#1632)
Unverified signature31170da
-
fix: make single step forcing optional on cohere endpoint type
46a8e79
-
feat(openai): added support for o1 reasoning models (#1618)
Unverified signature* fix(openai): systemRoleSupported model configuration for openai endpoints * feat(openai): max_completion_tokens now used over max_tokens for chat_completeions endpoint. * fix: lint * feat(docs): add o1 example * fix: make parameter default to false and fix type checks --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>3360a5d
-
Anthropic PDF Beta Support (#1571)
evalstate +1: nsarrazin Unverified signature* support anthropic PDF beta * upstream merge, remove commented out console log line * Fixing type errors. the anthropic API does not yet include a "DocumentBlock" for support PDFs, so an extended type has been added to the endpoint. * changed document processor to async (matching image processor) * use the beta api types rather than custom extension --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>33d6f58
-
fix: remove accessToken min length for llama.cpp endpoint
8bd5344
-
Fix/oai parameters 1552 (#1557)
evalstateUnverified signature* support temperature between 0 and 2 * added parsing of presence_penalty from model parameters. OAI endpoint now correctly uses (frequency penalty=parameters.repetition penalty) and (presence penalty=parameters.presence_penalty) for both chat and completion paths. * added parsing of presence_penalty from model parameters. OAI endpoint now correctly uses (frequency penalty=parameters.repetition penalty) and (presence penalty=parameters.presence_penalty) for both chat and completion paths.9c8e5e0
-
fix: better websearch quotes
e7c09f7 -
feat: add sources for websearch (#1551)
Unverified signature* feat: playwright, spatial parsing, markdown for web search Co-authored-by: Aaditya Sahay <aadityasahay1@gmail.com> * feat: choose multiple clusters if necessary (#2) * chore: resolve linting failures * feat: improve paring performance and error messages * feat: inline citations * feat: adjust inline citation prompt, less intrusive tokens * feat: add sources to message when using websearch * fix: clean up packages * fix: packages * fix: packages lol * fix: make websearch citation work better wiht tools * fix: use single brackets for sources, only render source element if a matching source is available * fix: bad import --------- Co-authored-by: Liam Dyer <liamcdyer@gmail.com> Co-authored-by: Aaditya Sahay <aadityasahay1@gmail.com> Co-authored-by: Aaditya Sahay <56438732+Aaditya-Sahay@users.noreply.github.com>69dee14
-
feat: paste long context as plaintext files (#1549)
Unverified signature* feat: paste long context as a file * fix: anim sources * fix: animations * feat: actually inject plaintext files in the prompt * filter out files that are plain text * feat: use custom MIME type for clipboard content * feat: add better UI affordance for pasting * fix: cleanup animationsc99779e
-
[feat] Add support for endpoint web sources (#1544)
goupilew +1: nsarrazin Unverified signature* [feat] Add support for endpoint web sources * chores: lint --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>eabf2bf
-
fix(endpoint): fallback to hf token for openai endpoint type
Unverified signature8a9d27a
-
[fix] Fix typo in Vertex (#1531)
goupilewUnverified signatureaf3d972
-
[vertex] Add PDF/plein texts support (#1520)
goupilewUnverified signature* [vertex] Add PDF support * [vertex] Fix lint * [vertex] Add support for text/plainaa59751
-
feat(endpoints): Add conv ID to headers passed to TGI (#1511)
Unverified signature791e118
-
feat(tools): Basic tool support for OpenAI models (#1447)
Unverified signature* feat(tools): Basic tool support for OpenAI models * feat(tools): Basic tool support for OpenAI models * fix: tools with document input (not image) * fix: double yield of streaming tokens * fix: boolean parameter processing error took me a while to find this one lol * feat: throw error if using tools in `completions` mode * feat: fix image processing in tools mode * fix: remove correlationKey and clean up types --------- Co-authored-by: Jacob Gladish <jacob_gladish@comcast.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>7dbac68
-
Add support for model version in Vertex AI (#1496)
Unverified signature* Add support for model version in Vertex AI * Update src/lib/server/endpoints/google/endpointVertex.ts Co-authored-by: goupilew <arthurgoupil@gmail.com> * fix: optional chaining on extraBody --------- Co-authored-by: goupilew <arthurgoupil@gmail.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>5559ab7
-
Fix: Cohere Endpoint - Add Support for Tools (#1490)
dvirmorUnverified signature* fix(endpointCohere): Added force_single_step param to chatStream call * refactor(endpointCohere): change force_single_step parameter to forceSingleStep for lintingb642b29
-
fix: multimodal on TGI endpoint type (#1491)
Unverified signaturebd01335
-
fix(endpoints): make bedrock import optional (#1468)
Unverified signaturef13ecff
-
Move Google GenAI API key to env file instead (#1448)
Unverified signature- Updated the documentation with the latest links from Google AI Studio - Fixed the incorrect documentation on `safetyThreshold` - Fixed the `safetySettings` to exclude unspecified category, as it is not considered as a valid input category in Google's API Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>dffaafd -
feat: add support for multimodal in Vertex (#1338)
goupilewUnverified signature* feat: add support for multimodal in Vertex * Nit changes and remove tools if multimodal * revert model name change * Fix tools/multimodal condition * chores(lint): fix formatting --------- Co-authored-by: Thomas <thomas.poc@gmail.com> Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>96070f4
-
Add support for Anthropic models via AWS Bedrock (#1413)
ABarLT +1: nsarrazin Unverified signature* Add support for Anthropic models via AWS Bedrock * deps * Fixed type errors * Temporary fix for continue button showing up on Claude * Fix continue button issue by setting the last message token's special to true --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>bf78ac3
-
Dynamic credential resolution for AWS endpoints (#1419)
Mike Nason +1: nsarrazin Unverified signature* Dynamic credential resolution for AWS endpoints If AWS credentials are provided, they will continue to be used. With this change, they become optional parameters and the AWS SDK will attempt to use the default resolution chain if they are not provided. * cleanup deps * restore optional aws region in endpointAwsParametersSchema --------- Co-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>cc0d6c5 -
fix(openai): do not throw "Generation failed" when finish_reason="length" (#1429)
L +1: nsarrazin Unverified signatureCo-authored-by: Nathan Sarrazin <sarrazin.nathan@gmail.com>1f8ab3d