Token Configuration Guide

A lot of the models available today can be found on HuggingFace. This page describes how to configure HuggingFace token settings for Cortex.

Command Line Interface (CLI)

Basic Usage

cortex config [OPTIONS] [COMMAND]

To display all current configurations

cortex config status

+-----------------------+------------------------+
| Config name           | Value                  |
+-----------------------+------------------------+
| huggingface_token     |                        |
+-----------------------+------------------------+

Options

Option	Description	Example
-h, --help	Print help message and exit
--huggingface_token <token>	Set HuggingFace token	cortex config --huggingface_token token

Token API Configuration

Endpoints

Get Current Configuration

GET /v1/configs

curl GET http://127.0.0.1:39281/v1/configs

{
  "allowed_origins": [
    "http://localhost:39281",
    "http://127.0.0.1:39281",
    "http://0.0.0.0:39281"
  ],
  "cors": true,
  "huggingface_token": "",
  "no_proxy": "example.com,::1,localhost,127.0.0.1",
  "proxy_password": "",
  "proxy_url": "",
  "proxy_username": "",
  "verify_host_ssl": true,
  "verify_peer_ssl": true,
  "verify_proxy_host_ssl": true,
  "verify_proxy_ssl": true
}

Update Configuration

PATCH /v1/configs

Updates HuggingFace token configuration settings.

Request Headers

Content-Type: application/json

Request Body

{
  "huggingface_token": "token"
}

Parameters

Field	Type	Description
huggingface_token	string	HuggingFace token to pull models

Response

{
  "config": {
    "allowed_origins": [
      "http://localhost:39281",
      "http://127.0.0.1:39281",
      "http://0.0.0.0:39281"
    ],
    "cors": true,
    "huggingface_token": "token"
  },
  "message": "Configuration updated successfully"
}