n8n OpenAI Compatible Node

This n8n node allows you to interact with any OpenAI-compatible API service like qwen etc. It supports both chat completions and text completions, making it compatible with various AI model providers that follow the OpenAI API specification.

Features

• Chat Completions: Generate responses using the chat completion endpoint (/v1/chat/completions)
• Text Completions: Generate text using the completion endpoint (/v1/completions)
• Flexible Configuration: Configure base URL, model, and API key for any OpenAI-compatible service
• Advanced Parameters: Support for temperature, max tokens, top-p, frequency penalty, presence penalty, and stop sequences
• Error Handling: Robust error handling with continue-on-fail support

Supported Services

This node works with any service that implements the OpenAI API specification, including:

• OpenAI API
• Azure OpenAI
• Anthropic Claude (via OpenAI-compatible wrapper)
• Local models (Ollama, LM Studio, etc.)
• Other OpenAI-compatible providers

Installation

Manual Installation

1. Clone or download this repository
2. Install dependencies:

   npm install
   

3. Build the node:

   npm run build
   

4. Copy the dist folder to your n8n custom nodes directory:

   cp -r dist ~/.n8n/custom/
   

5. Restart n8n

Using npm

npm install n8n-nodes-openai-compatible-node

Usage

1. Configure Credentials

1. In n8n, go to Settings → Credentials
2. Click Add Credential
3. Search for "OpenAI Compatible API"
4. Configure:
   • Base URL: The base URL of your OpenAI-compatible service (e.g., https://api.openai.com, https://your-service.com)
   • API Key: Your API key for the service

2. Add the Node

1. In your workflow, add the "OpenAI Compatible" node
2. Select the credentials you created
3. Choose the operation:
   • Chat Completion: For conversational AI responses
   • Text Completion: For text generation

3. Configure Parameters

Chat Completion

• Model: The model name (e.g., gpt-3.5-turbo, gpt-4)
• Messages: Array of messages with role (system, user, assistant) and content
• Additional Fields: Optional parameters like temperature, max tokens, etc.

Text Completion

• Model: The model name (e.g., text-davinci-003)
• Prompt: The text prompt to complete
• Additional Fields: Optional parameters like temperature, max tokens, etc.

4. Advanced Parameters

• Temperature (0-2): Controls randomness. Lower values = more deterministic
• Max Tokens: Maximum number of tokens to generate
• Top P (0-1): Controls diversity via nucleus sampling
• Frequency Penalty (-2 to 2): Penalizes new tokens based on frequency
• Presence Penalty (-2 to 2): Penalizes new tokens based on presence
• Stop: Sequences where generation stops

Examples

Chat Completion Example

{
  "operation": "chatCompletion",
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello, how are you?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1000
}

Text Completion Example

{
  "operation": "textCompletion",
  "model": "text-davinci-003",
  "prompt": "Write a short story about a robot learning to paint.",
  "temperature": 0.8,
  "max_tokens": 500
}

Configuration Examples

OpenAI API

• Base URL: https://api.openai.com
• API Key: Your OpenAI API key

Azure OpenAI

• Base URL: https://your-resource.openai.azure.com/openai/deployments/your-deployment
• API Key: Your Azure OpenAI API key

Local Ollama

• Base URL: http://localhost:11434/v1
• API Key: (leave empty or use any value)

Anthropic Claude (via OpenAI wrapper)

• Base URL: https://api.anthropic.com/v1
• API Key: Your Anthropic API key

Development

Prerequisites

• Node.js 16+
• npm or yarn
• n8n development environment

Setup

1. Clone the repository
2. Install dependencies: npm install
3. Build: npm run build
4. Link to n8n: npm link (in n8n directory)

Scripts

• npm run build: Build the node
• npm run dev: Watch mode for development
• npm run lint: Run ESLint
• npm run format: Format code with Prettier

Troubleshooting

Common Issues

1. "Base URL and API Key are required"

   • Ensure both fields are filled in the credentials

2. "At least one message is required for chat completion"

   • Add at least one message in the Messages section

3. "Prompt is required for text completion"

   • Add a prompt in the Prompt field

4. Authentication errors

   • Verify your API key is correct
   • Check if the base URL is accessible

Debug Mode

Enable debug logging in n8n to see detailed request/response information.

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

For issues and questions:

• Create an issue on GitHub
• Check the n8n documentation
• Join the n8n community