Regolo AI icon

Regolo AI

Use Regolo AI (OpenAI-compatible)
Join our community

Actions3

Overview

The node provides an interface to generate chat completions using Regolo AI, an OpenAI-compatible service. It allows users to send a sequence of messages with roles (system, user, assistant) as prompts and receive AI-generated responses based on those inputs.

This node is beneficial in scenarios such as:

  • Building conversational agents or chatbots.
  • Generating dynamic replies or content based on user input.
  • Automating customer support interactions.
  • Experimenting with different AI models for chat-based tasks.

For example, you can use this node to send a conversation history and get the next assistant message generated by the AI model, or to simulate dialogue flows with system instructions and user queries.

Properties

Name Meaning
Model The AI model used to generate the completion. Options include a list of available chat models or a custom model ID typed manually.
Custom Model When "Custom" model is selected, specify the custom model ID here (e.g., llama-3.1-70b-instruct).
Prompt A collection of messages forming the conversation prompt. Each message has:
- Role: one of Assistant, System, User
- Content: the text content of the message. Multiple messages can be added and sorted.
Simplify Whether to return a simplified version of the response instead of raw data. Defaults to true.
Options Additional options to customize the completion request:
- Echo Prompt: whether to echo the prompt back in the response.
- Frequency Penalty: number between -2 and 2 controlling repetition penalty.
- Maximum Number of Tokens: max tokens to generate (up to 32768).
- Number of Completions: how many completions to generate.
- Presence Penalty: number between -2 and 2 affecting new topic introduction.
- Sampling Temperature: controls randomness (0 to 1).
- Top P: nucleus sampling parameter (0 to 1).

Output

The node outputs JSON data representing the AI-generated chat completion(s). If simplification is enabled, the output contains a streamlined version of the response, typically the generated text content from the assistant role.

If multiple completions are requested, the output includes all generated results.

Binary data output is not applicable for this operation.

Dependencies

  • Requires an API key credential for Regolo AI service with a base URL configured.
  • The node sends requests to the Regolo AI endpoint specified by the user's credentials.
  • No additional external dependencies beyond the configured API access.

Troubleshooting

  • Common issues:

    • Invalid or missing API credentials will cause authentication errors.
    • Specifying an unsupported or incorrect model ID may result in errors or no response.
    • Exceeding token limits (maxTokens) might cause request failures.
    • Improperly formatted messages (missing role or content) could lead to unexpected behavior.

  • Error messages:

    • Authentication errors: Verify that the API key and base URL are correctly set in credentials.
    • Model not found or invalid model: Check the model name or use the custom model field carefully.
    • Rate limit exceeded: Wait and retry later or adjust usage patterns.
    • Request validation errors: Ensure all required fields (messages, model) are properly filled.

Links and References

Discussion