Dolphin Mixtral icon

Dolphin Mixtral

Execute local Dolphin Mixtral models
Join our community

Overview

This node integrates with a local Dolphin Mixtral AI model to generate text completions based on user prompts. It is designed for scenarios where users want to leverage a local AI language model for tasks such as content generation, conversational agents, or any natural language processing that benefits from custom prompts and adjustable generation parameters.

Typical use cases include:

  • Generating responses in chatbots or virtual assistants.
  • Creating creative writing or brainstorming ideas.
  • Automating text-based workflows requiring AI-generated content.

For example, a user can input a prompt like "Explain the theory of relativity" and receive a detailed AI-generated explanation using the configured Dolphin Mixtral model.

Properties

Name Meaning
Model Name Choose which Dolphin Mixtral model to use. Currently supports "Dolphin Mixtral".
Prompt The text prompt to send to the AI model for generating a response.
Options Collection of optional parameters:
  System Prompt Defines the AI's system-level behavior or persona (default: "You are Dolphin, a helpful AI assistant.").
  Temperature Sampling temperature controlling randomness in output (range 0 to 2, default 0.7).
  Max Tokens Maximum number of tokens to generate in the response (default 2048).

Output

The node outputs an array of JSON objects, each containing the following fields:

  • model: The name of the model used for generation.
  • created_at: Timestamp when the response was generated.
  • response: The AI-generated text completion.
  • done: Boolean indicating if generation completed successfully.
  • done_reason: Reason why generation stopped.
  • context: Contextual information related to the generation.
  • metrics: Performance metrics including total duration, load duration, evaluation counts, and durations.

If an error occurs during generation, the output JSON will contain:

  • success: false
  • error: Error message describing the failure.
  • model: The model requested.
  • prompt: The prompt sent.
  • statusCode: HTTP status code returned by the API (if applicable).

The node does not output binary data.

Dependencies

  • Requires access to a local Dolphin Mixtral API endpoint.
  • Needs an API key credential configured in n8n to authenticate requests to the Dolphin Mixtral service.
  • The node sends HTTP POST requests to the /api/generate endpoint of the configured API URL.

Troubleshooting

  • Common issues:

    • Invalid or missing API credentials will cause authentication failures.
    • Network connectivity problems to the local Dolphin Mixtral API will result in request errors.
    • Providing an empty or invalid prompt may lead to unexpected or empty responses.
    • Setting extremely high maxTokens values might cause performance degradation or timeouts.

  • Error messages:

    • Errors returned from the API are captured and included in the output JSON under the error field.
    • HTTP status codes help diagnose issues like unauthorized access (401), bad requests (400), or server errors (500).

  • Resolutions:

    • Verify API credentials and ensure they are correctly set up in n8n.
    • Confirm the local Dolphin Mixtral API is running and accessible at the specified URL.
    • Adjust prompt and options to valid values within recommended ranges.
    • Check network settings and firewall rules if connection issues persist.

Links and References

Discussion