Skip to content
Monkeys

Integrate with One API

This document describes how to integrate Monkeys’ OpenAI-compatible large language model interface into One API. For installation instructions of One API, please refer to its official documentation.

1. Create a large language model workflow in the Monkeys console

For detailed steps on creating a workflow, see Built-in Tools (Large Language Models).

There are a few points to note:

  1. Select the model you need to use. Here we choose alpindale/c4ai-command-r-plus-GPTQ.

Select Model

  1. In the API Settings of the Start node, set the Model Name to the desired model name. Here we set it to command-r.

By default, the model parameter of Monkeys’ OpenAI interface corresponds to the workflow ID. You can modify this value to set the model name. (Model names must be unique within the same team)

Set Model Name

  1. (Optional) You can set a knowledge base context for this workflow, allowing the large model to automatically use the knowledge in the knowledge base to answer questions.

For details, see Built-in Tools (Private Data Search).

Here we add a customer service corpus:

Configure Knowledge Base

2. Create a channel

In the Channels page of One API, create a new channel and fill in the following information:

  • Type: Select OpenAI.
  • Name: Enter any name.
  • Group: Enter any group.
  • Model: Enter the custom model name we set above (see step 1).
  • Key: Monkeys’ API Key, which can be created or obtained on the settings page.
  • Proxy: Fill in the address of the Monkeys service, without the /v1 suffix, e.g., https://ai.infmonkeys.com.

Add Channel

Click create.

Test Channel Connectivity

Click the Test button to check if the connection is successful.

Test Channel

3. Create a token

In the Tokens page of One API, create a new token and fill in the following information:

  • Name: Enter any name.
  • Model Scope: Select the model we added above.

Create Token

Click create.

4. Call the API

Modify the API address, token, and model to your actual address, token, and model.

Terminal window
curl --location 'https://your-one-api-service.com/v1/chat/completions' \
--header 'Authorization: Bearer sk-xxxxxxxx' \
--header 'Content-Type: application/json' \
--data '{
    "model": "alpindale/c4ai-command-r-plus-GPTQ",
    "messages": [
        {"role": "user", "content": "Hello"},
        {"role": "assistant", "content": "Hello, how can i help you today?"},
        {"role": "user", "content": "What is today"}
    ],
    "stream": true
}'