LLM Node

Custom LLM node with dynamic model options
Join our community

Actions2

Overview

This node integrates with a large language model (LLM) API to perform two main operations: generating chat completions and processing videos based on prompts. It is useful for automating content generation, natural language understanding, or video analysis tasks that require AI-powered responses.

  • Chat operation: Sends a text prompt to an LLM and receives a generated response. This can be used for conversational agents, content creation, summarization, or any scenario where you want the AI to generate or complete text.
  • Video operation: Sends a prompt along with a video URL to the API for processing. This could be used for video captioning, analysis, or extracting insights from video content.

Practical examples:

  • Automatically generate customer support replies based on user queries.
  • Create video summaries or extract metadata by providing a video URL and a descriptive prompt.

Properties

Name Meaning
Model Name or ID Choose the LLM model to use from a dynamically loaded list or specify an ID via expression. Only shown for the Chat operation.
Prompt The input text prompt you want the LLM to respond to or use as context for video processing.
Operation Select between "Chat" (text generation) and "Video" (video processing).

Note: For the Video operation, only "Prompt" and "Operation" are relevant inputs according to the provided properties.

Output

The node outputs an array of JSON objects, each corresponding to one input item processed:

  • For Chat operation: The output JSON contains the LLM's generated response. The exact structure depends on the API but generally includes the generated text or JSON response if requested.
  • For Video operation: The output JSON contains the result of the video processing request, which may include analyzed data, captions, or other metadata returned by the API.

No binary data output is indicated in the code.

Dependencies

  • Requires an API key credential for authentication with the external LLM service.
  • Makes HTTP requests to the API endpoints:
    • https://ai.system.sl/llm-models to load available models.
    • ${domain}/llms for chat completions.
    • ${domain}/process-video for video processing.
  • The domain and API key are obtained from the configured credentials.
  • The node expects the API to accept and return JSON-formatted data.

Troubleshooting

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

  • Error loading models
    If the model list cannot be fetched, the node will show an error option. Check network connectivity and API key validity.

  • API request failures
    Errors during the HTTP requests (e.g., invalid parameters, server errors) will cause the node to throw exceptions unless "Continue On Fail" is enabled. Review the error message for details and verify the prompt, model selection, and video URL.

  • Invalid operation or missing parameters
    Make sure to select the correct operation ("Chat" or "Video") and provide all required inputs like prompt and video URL (for video).

Links and References

  • n8n Expressions Documentation — for using expressions in property fields.
  • External API documentation (not provided) would be needed for detailed usage of the LLM and video processing endpoints.

Discussion