n8n-nodes-reilabs

This is an n8n community node that provides integration with ReiLabs Unit for chat completions. It allows you to use ReiLabs' OpenAI-compatible API within your n8n workflows, including with the AI Agent node.

Features

• OpenAI-Compatible: Works with ReiLabs Unit's OpenAI-compatible chat completion API
• AI Agent Integration: Can be used as a chat model within n8n's AI Agent node
• Secure Credentials: API keys are stored securely using n8n's credential system
• Function Calling: Supports tools/function calling for advanced use cases
• Configurable Parameters: Full control over temperature, max tokens, penalties, and more

Installation

Community Node Installation (Recommended)

1. Go to Settings > Community Nodes in your n8n instance
2. Click Install a community node
3. Enter n8n-nodes-reilabs
4. Click Install

Manual Installation

Navigate to your n8n installation directory and run:

npm install n8n-nodes-reilabs

For Docker installations, add this to your Dockerfile or docker-compose.yml:

npm install -g n8n-nodes-reilabs

Local Development

1. Clone this repository
2. Install dependencies:

   npm install
   

3. Build the node:

   npm run build
   

4. Link to your n8n installation:

   npm link
   cd ~/.n8n/custom
   npm link n8n-nodes-reilabs
   

Configuration

Setting Up Credentials

1. In n8n, go to Credentials and click Add Credential
2. Search for ReiLabs API
3. Enter your ReiLabs Unit Secret Key
4. Click Save
5. Test the connection to verify it works

Using the Node

1. Add the ReiLabs Unit Chat Node to your workflow
2. Select your ReiLabs API credentials
3. Configure the required parameters:
   • Agent Model: Currently supports google/gemini-2.5-flash
   • Behaviour Prompt: System-level instructions for the model
   • Messages: Array of message objects in OpenAI format

Example Messages Format

[
  {
    "role": "user",
    "content": "Hello, can you help me?"
  }
]

Optional Parameters

• Temperature (0-2): Controls randomness (default: 0.7)
• Max Tokens: Maximum tokens to generate (default: 1024)
• Top P (0-1): Nucleus sampling parameter (default: 1)
• Frequency Penalty (-2 to 2): Reduces repetition (default: 0)
• Presence Penalty (-2 to 2): Encourages new topics (default: 0)
• Tools: JSON array of function definitions for function calling
• Stop Sequences: Comma-separated list of stop sequences

Function Calling Example

In the Tools field, provide a JSON array:

[
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get current temperature of given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "City and country (e.g. Paris, France)"
          }
        },
        "required": ["location"],
        "additionalProperties": false
      },
      "strict": true
    }
  }
]

Using with AI Agent Node

This node is designed to work seamlessly with n8n's AI Agent node:

1. Add an AI Agent node to your workflow
2. In the AI Agent configuration, select ReiLabs Unit Chat Node as the chat model
3. Configure your agent's tools, memory, and other settings
4. The agent will use ReiLabs Unit for its language model capabilities

API Reference

Endpoint

• Base URL: https://api.reilabs.org
• Chat Completions: /v1/chat/completions

Authentication

Uses Bearer token authentication:

Authorization: Bearer YOUR_REIGENT_UNIT_SECRET_KEY

Request Format

{
  "agentModel": "google/gemini-2.5-flash",
  "behaviourPrompt": "You are a helpful assistant",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "top_p": 1,
  "frequency_penalty": 0,
  "presence_penalty": 0
}

Response Format

{
  "choices": [
    {
      "index": 0,
      "message": {
        "content": "Hello! How can I assist you today?",
        "role": "assistant"
      }
    }
  ]
}

Troubleshooting

Connection Issues

• Verify your API key is correct
• Check that you have access to the ReiLabs API
• Ensure your n8n instance can reach https://api.reilabs.org

Invalid JSON Errors

• Ensure Messages and Tools fields contain valid JSON
• Use the JSON validator in your editor before pasting

Model Not Available

• Currently only google/gemini-2.5-flash is supported
• Contact ReiLabs if you need access to additional models

Development

Project Structure

n8n-nodes-reilabs/
├── credentials/
│   └── ReiLabsApi.credentials.ts
├── nodes/
│   └── ReiLabsUnitChatNode/
│       ├── ReiLabsUnitChatNode.node.ts
│       └── reilabs.svg
├── package.json
├── tsconfig.json
└── README.md

Building

npm run build

Linting

npm run lint
npm run lintfix

Formatting

npm run format

Support

For issues related to:

• This n8n node: Open an issue on GitHub
• ReiLabs API: Contact ReiLabs support
• n8n platform: Visit n8n community forum

License

MIT

Resources

• n8n Documentation
• ReiLabs API Documentation
• Creating n8n Nodes