AI/ML API icon

AI/ML API

AI chat completion via AI/ML API (AIMLAPI)

Overview

This node provides AI chat completion functionality by interacting with an external AI/ML API service. It sends a user-defined prompt to a selected AI model and returns the generated response. This is useful for automating conversational tasks, generating text content, summarizing information, or building chatbots within n8n workflows.

Typical use cases include:

  • Generating natural language responses based on prompts.
  • Automating customer support replies.
  • Creating content drafts or ideas.
  • Extracting insights from textual data via AI models.

Properties

Name Meaning
Model Name or ID Select an AI model from a dynamically loaded list or specify a model ID using an expression. The chosen model will be used to generate the chat completion.
Prompt The text prompt sent to the AI model to generate a response. This is the main input that drives the AI's output.
Extract From Response Choose which part of the AI response to return:
- Text Only (First Message): Returns only the first message's text content.
- Assistant Messages: Returns all assistant messages.
- Choices Array: Returns the full array of choices.
- Full Raw JSON: Returns the complete raw JSON response from the API.
Options Additional parameters to customize the AI generation:
- Frequency Penalty: Penalizes repeated tokens (-2 to 2).
- Max Tokens: Maximum tokens to generate.
- Presence Penalty: Penalizes new topics (-2 to 2).
- Response Format: Output format, either full JSON or text only.
- Temperature: Sampling temperature controlling randomness (0-2).
- Top P: Nucleus sampling parameter (0-1).

Output

The node outputs JSON data structured according to the "Extract From Response" property:

  • Text Only (First Message): Outputs an array with one object containing the key content holding the first message's text string.
  • Assistant Messages: Outputs an array with one object containing the key result holding an array of all assistant messages.
  • Choices Array: Outputs an array with one object containing the key result holding the full array of choice objects returned by the AI.
  • Full Raw JSON: Outputs an array with one object containing the key result holding the entire raw JSON response from the API.

No binary data output is produced by this node.

Dependencies

  • Requires connection to an external AI/ML API service endpoint.
  • Needs an API key credential and base URL configured in n8n credentials for authentication.
  • The node dynamically loads available AI models from the API before execution.

Troubleshooting

  • Common Issues:

    • Invalid or missing API key or base URL can cause authentication failures.
    • Selecting a model that does not support chat completions may result in errors or empty responses.
    • Providing invalid parameter values (e.g., out-of-range penalties or token limits) might cause request rejections.
    • Network connectivity issues to the API endpoint will prevent successful requests.

  • Error Messages & Resolutions:

    • Authentication errors: Verify API key and base URL are correctly set in credentials.
    • Model not found: Ensure the selected model supports chat completions and is available in the API.
    • Invalid parameter value: Check that numeric options like temperature, penalties, and max tokens are within allowed ranges.
    • Empty or malformed response: Confirm the prompt is valid and the API service is operational.

Links and References

  • n8n Expressions Documentation
  • Refer to your AI/ML API provider’s official documentation for detailed model capabilities and parameter descriptions.

Discussion