Actions2
Overview
This node, named "SL LLMs," integrates with an external AI service to perform two main operations: generating text responses from prompts and processing videos via a provided URL. The "Process Video" operation sends a video URL along with a prompt to the AI service, which presumably analyzes or processes the video content in some way and returns a response.
Common scenarios for this node include:
- Automatically analyzing video content based on user prompts, such as summarizing, extracting insights, or generating metadata.
- Enhancing workflows that require AI-driven video understanding without manual intervention.
- Combining video processing with natural language prompts to get contextual or descriptive outputs.
Example use case:
- A marketing team uploads a video URL and asks the AI to generate a summary or key points from the video content automatically.
Properties
| Name | Meaning |
|---|---|
| Video URL | URL of the video to be processed (used only in the "Process Video" operation) |
| Model Type | Selects the AI model to use for text generation (not applicable for video operation). Options include various Gemini, Gemma, Llama, Mistral, Mixtral, and WizardLM models. |
| Prompt | Text prompt to send to the AI model for generating a response or guiding video processing |
| Temperature | Controls randomness in the generated response; higher values produce more diverse outputs |
| Max Tokens | Maximum length of the generated response |
| Top P | Nucleus sampling parameter controlling token selection breadth |
| Top K | Limits token selection to top K choices |
| Safety Settings : Hate Block | Level of filtering for hate speech content (None, Low, Medium, High); applies only to certain Gemini models |
| Safety Settings : Harrasment Block | Level of filtering for harassment content (None, Low, Medium, High); applies only to certain Gemini models |
| Safety Settings : Sexual Block | Level of filtering for sexual content (None, Low, Medium, High); applies only to certain Gemini models |
| Safety Settings : Dangerous Content Block | Level of filtering for dangerous content (None, Low, Medium, High); applies only to certain Gemini models |
Output
The node outputs a JSON object containing the response from the external AI service. For the "Process Video" operation, the output JSON includes the AI's analysis or processing result related to the provided video URL and prompt.
If an error occurs during the request, the output JSON will contain an error field with the error message.
No binary data output is produced by this node.
Dependencies
- Requires an API key credential for authenticating requests to the external AI service.
- The node makes HTTP POST requests to the AI service endpoint at
{domain}/llms, where{domain}and the API key are obtained from the configured credentials. - Proper network access to the AI service domain is necessary.
Troubleshooting
No credentials returned!
This error indicates missing or misconfigured API authentication credentials. Ensure that the required API key credential is properly set up in n8n.Request errors (e.g., network issues, invalid parameters)
Errors during the HTTP request to the AI service will throw exceptions. If "Continue On Fail" is enabled, the node will output the error message in the JSON output instead of stopping execution.Invalid or unsupported video URL
Providing an incorrect or inaccessible video URL may cause the AI service to fail processing. Verify the URL is correct and publicly accessible.Model type restrictions on safety settings
Safety filter options apply only to specific Gemini models. Selecting these filters with unsupported models will have no effect.
Links and References
- No direct links available from the source code. Users should refer to the documentation of the external AI service used by this node for detailed API usage and model descriptions.