SL LLMs

Overview

This node integrates with StrangeLogic's Large Language Models (LLMs) API to generate text completions or process videos based on user input. It supports multiple advanced LLM models, allowing users to send prompts and receive generated text responses tailored by parameters such as temperature and token limits.

Common scenarios:

• Generating creative or informative text content from a prompt.
• Processing video URLs for analysis or extraction of information (though this operation is hidden in the provided properties).
• Experimenting with different LLM models to find the best fit for specific natural language tasks.

Practical examples:

• Creating chatbot responses or automated email drafts.
• Summarizing or extracting insights from video content via URL.
• Adjusting generation randomness and length to produce concise or elaborate outputs.

Properties

Note: The following properties exist but are not part of the "Default" Resource-Operation combination requested:

• Temperature: Controls randomness in response generation (number).
• Max Tokens: Maximum length of the generated response (number).
• Top P: Nucleus sampling parameter controlling token selection breadth (number).
• Top K: Limits token selection to top K tokens (number).
• Safety Settings (Hate Block, Harassment Block, Sexual Block, Dangerous Content Block): Levels to block unsafe content (None, Low, Medium, High).
• JSON Response: Whether to request the response in JSON format (boolean).

Output

The node outputs JSON data containing the response from the StrangeLogic LLM API.

• For text generation, the output JSON contains the generated text or an error message if the request failed.
• For video processing (not applicable here), it would return processed video data.
• No binary data output is indicated.

Example output structure:

{
  "json": {
    // API response object, typically including generated text or error details
  }
}

Dependencies

• Requires an API key credential for StrangeLogic's AI API service.
• The node makes HTTP POST requests to the configured API domain endpoints:
  • /llms for text generation.
  • /process-video for video processing (not used in Default operation).
• Proper configuration of the API domain and authentication credentials in n8n is necessary.

Troubleshooting

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

• API request failures:
  Network issues, invalid API keys, or incorrect parameters can cause errors. The node throws errors with messages from the API. Use "Continue On Fail" option to handle errors gracefully.

• Empty or unexpected responses:
  Verify that the prompt is correctly set and the selected model supports the requested operation.

Links and References

• StrangeLogic AI API Documentation (Replace with actual URL if available)
• n8n documentation on Creating Custom Nodes
• General info on Large Language Models