302.AI icon

302.AI

Interact with 302.ai AI services
Join our community

Overview

This node integrates with the 302.ai API to send chat messages to an AI language model. It allows users to specify a model, provide a system prompt to set the assistant's behavior, and send a user message optionally accompanied by an image URL. The node then returns the AI-generated chat response.

Common scenarios include:

  • Building conversational AI assistants that respond based on custom prompts.
  • Enhancing chatbots with image context by sending images alongside text.
  • Experimenting with different AI models and tuning generation parameters like temperature and penalties.

Practical example:

  • A customer support chatbot sends a user query and receives a helpful answer.
  • An educational app sends a system prompt defining a tutor persona and asks questions.
  • A creative writing tool sends a story prompt and gets AI-generated continuation.

Properties

Name Meaning
Model Name or ID Select the AI model to use from a list or specify an ID via expression.
System Prompt Optional system message to define the assistant's behavior or context.
Message The main user message to send to the chat model (required).
Image URL Optional URL or base64 string of an image to provide additional context along with the message.
Temperature Sampling temperature controlling randomness in output (e.g., 0.9).
Additional Fields Collection of optional parameters:
- Frequency Penalty: Penalizes repeated tokens (-2.0 to 2.0).
- Max Tokens: Maximum tokens to generate.
- Presence Penalty: Penalizes tokens based on presence (-2.0 to 2.0).
- Top P: Nucleus sampling parameter (0 to 1).

Output

The node outputs JSON data with the following structure:

{
  "response": "AI-generated chat message text"
}
  • The response field contains the trimmed text generated by the AI model in reply to the input message.
  • If an error occurs and "Continue On Fail" is enabled, the output will contain an error field with the error message.
  • No binary data output is produced by this node.

Dependencies

  • Requires an API key credential for authenticating with the 302.ai service.
  • Makes HTTP requests to the 302.ai API endpoints:
    • GET https://api.302.ai/v1/models?llm=1 to load available models.
    • POST https://api.302.ai/v1/chat/completions to send chat messages.
  • The node expects the API key to be configured in n8n credentials for 302.ai.

Troubleshooting

  • No valid API key provided: Ensure the API key credential is correctly set up and linked to the node.
  • Failed to load models: Check network connectivity and validity of the API key; the node fetches models dynamically.
  • Invalid response format from 302.ai API: This indicates unexpected API response structure; verify API status or version compatibility.
  • Error during chat request: Could be due to invalid parameters or API limits; review input properties and API usage quotas.
  • Enable "Continue On Fail" to handle errors gracefully and receive error details in output.

Links and References

  • 302.ai API Documentation (assumed official docs)
  • n8n Expressions Documentation
  • General info on AI chat models and parameters:
    • Temperature: Controls randomness in output.
    • Frequency and Presence Penalties: Influence token repetition and novelty.
    • Top P (Nucleus Sampling): Alternative sampling method focusing on top probability mass.

Discussion