LLM providerkdeps asset
kdeps-providers-huggingface
v1.0.0kdeps provider: huggingface
set providers / shelf model
PurposeHuggingFace
LLM context: none - kdeps uses it without sending it to the model
Where it runs
Part of the providers set, used in workflow and agent mode. OpenAI-compatible LLM providers: base URL, chat path, API key setting and default model.
- a chat call names a backend
- the provider gives the URL, chat path and keyproviders/huggingface
- kdeps sends the request
- the reply comes back
Loaded by: kdeps (agent loop), kdeps run, kdeps validate, kdeps doctor, kdeps edit, kdeps env, kdeps exec, kdeps test
In the code: kdeps (agent loop)llm.AutoRouterPickconfig.CloudLLMProvidersconfig.assetProviders
Install
A kdeps asset: installed with the first-run profile that includes its set, or the first time a command needs it, and updated without a new release.
kdeps install providers/huggingface
Pin a version with kdeps install providers/huggingface@<version>.
Contents
- name
- huggingface
- label
- HuggingFace
- order
- 120
- configKey
- huggingface_api_key
- envVar
- HF_TOKEN
- url
- https://api-inference.huggingface.co
- chatPath
- /v1/chat/completions
hosts:
- huggingface.co
# OpenAI-compatible LLM provider: kdeps registers a chat backend named after
# this file and reads its key from llm.huggingface_api_key in ~/.kdeps/config.yaml.
version: 1.0.0
name: huggingface
label: HuggingFace
order: 120 # position in provider lists and the setup prompt
configKey: huggingface_api_key
envVar: HF_TOKEN
url: https://api-inference.huggingface.co
chatPath: /v1/chat/completions
hosts: [huggingface.co]
Versions
| Version | Published | Status |
|---|---|---|
| 1.0.0 | 10/13/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.0.0
- Published
- 10/13/2026
Tags
kdepsprovider