SL LLMs icon

SL LLMs

StrangeLogic LLM Node
Join our community

Overview

This node integrates with StrangeLogic's Large Language Models (LLMs) to generate text completions based on user-provided prompts. It is designed for scenarios where users want to leverage advanced AI language models for tasks such as content generation, summarization, question answering, or conversational agents.

Typical use cases include:

  • Generating creative writing or marketing copy.
  • Automating responses in chatbots.
  • Summarizing documents or extracting information.
  • Experimenting with different LLM models and parameters to optimize output quality.

Users provide a prompt and configure model parameters; the node sends this data to the StrangeLogic API and returns the generated response.

Properties

Name Meaning
Model Type Selects the LLM model to use. Options include Gemini variants, Gemma, Llama 3.1 versions, Mistral, Mixtral, and WizardLM models.
Prompt The input text prompt that the LLM will respond to.
Temperature Controls randomness in the output; higher values produce more diverse results.
Max Tokens Maximum length of the generated response in tokens.
Top P Nucleus sampling parameter controlling token selection breadth (probability mass).
Top K Limits token selection to the top K most likely tokens at each step.
Saftey Settings : Hate Block (Only for certain Gemini models) Level of filtering for hate speech: None, Low, Medium, High.
Saftey Settings : Harrasment Block (Only for certain Gemini models) Level of filtering for harassment content: None, Low, Medium, High.
Saftey Settings : Sexual Block (Only for certain Gemini models) Level of filtering for sexual content: None, Low, Medium, High.
Saftey Settings : Dangerous Content Block (Only for certain Gemini models) Level of filtering for dangerous content: None, Low, Medium, High.

Output

The node outputs a JSON object containing the response from the StrangeLogic LLM API. The main field is:

  • json: An object representing the API response, which includes the generated text completion based on the prompt and parameters.

No binary data output is produced by this node.

Dependencies

  • Requires an active connection to the StrangeLogic LLM API service.
  • Needs an API key credential configured in n8n to authenticate requests.
  • The node makes HTTP POST requests to the API endpoint ${domain}/llms where domain and apiKeyApi are provided via credentials.

Troubleshooting

  • No credentials returned!
    This error occurs if the required API authentication credentials are not set up or accessible. Ensure the API key credential is properly configured in n8n.

  • API request failures
    Network issues, invalid API keys, or incorrect domain URLs can cause request errors. Verify credentials and network connectivity.

  • Invalid model or parameter values
    Using unsupported model types or out-of-range parameter values may result in API errors. Use only the provided options and valid numeric ranges.

  • Continue On Fail behavior
    If enabled, the node will return error messages within the output JSON instead of stopping execution, allowing workflows to handle errors gracefully.

Links and References

Discussion