SL LLMs icon

SL LLMs

StrangeLogic LLM Node

Actions2

Overview

This node integrates with StrangeLogic's Large Language Models (LLMs) to generate text or process videos based on user input. The primary use case is generating natural language responses from prompts using various AI models, which can be customized by parameters like temperature and token limits. It also supports video processing by sending a video URL along with a prompt.

Typical scenarios include:

  • Generating creative or informative text completions for chatbots, content creation, or summarization.
  • Processing video content with AI-driven analysis or transformation based on a prompt.

For example, you could provide a prompt asking the model to write a product description or summarize a video’s content by supplying its URL.

Properties

Name Meaning
Operation Choose between "Generate Text" or "Process Video".
Model Name or ID Select an AI model from a dynamically loaded list or specify a model ID via expression.
Prompt The text prompt that the LLM will respond to or use as context for video processing.
Temperature Controls randomness in text generation; higher values produce more diverse outputs (default 0.7).
Max Tokens Maximum length of the generated text response (default 2048 tokens).
Top P Nucleus sampling parameter controlling token selection breadth (default 1).
Top K Limits token selection to top K candidates (default 2).
Saftey Settings : Hate Block Level of filtering for hate speech content: None, Low, Medium, High (only for certain Gemini models).
Saftey Settings : Harrasment Block Level of filtering for harassment content: None, Low, Medium, High (only for certain Gemini models).
Saftey Settings : Sexual Block Level of filtering for sexual content: None, Low, Medium, High (only for certain Gemini models).
Saftey Settings : Dangerous Content Block Level of filtering for dangerous content: None, Low, Medium, High (only for certain Gemini models).
JSON Response Whether to request the response in JSON format instead of plain text (available for specific models).
Video URL URL of the video to be processed (only shown when Operation is "Process Video").

Output

The node outputs an array of items where each item contains a json field holding the API response:

  • For text generation, the json field contains the generated text or structured JSON response depending on the JSON Response setting.
  • For video processing, the json field contains the result returned by the video processing endpoint, typically including analysis or transformed data related to the video.

No binary data output is produced by this node.

Dependencies

  • Requires an API key credential for authentication with the StrangeLogic AI service.
  • The node makes HTTP requests to the StrangeLogic API endpoints:
    • https://ai.system.sl/llm-models to load available models.
    • ${domain}/llms for text generation.
    • ${domain}/process-video for video processing.
  • The domain and API key are provided via credentials configured in n8n.

Troubleshooting

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

  • Invalid response from API: Expected an array of models.
    Happens during model loading if the API returns unexpected data. Check network connectivity and API availability.

  • API request errors (e.g., network issues, invalid parameters)
    The node throws errors with messages from the API. Use the "Continue On Fail" option to handle errors gracefully in workflows.

  • Model or operation mismatch
    Some safety settings and options only apply to specific models or operations. Selecting incompatible combinations may cause unexpected behavior.

Links and References

  • n8n Expressions Documentation — for specifying dynamic model IDs.
  • StrangeLogic AI API documentation (not publicly linked here) for details on model capabilities and parameters.

Discussion