Actions2
Overview
This node integrates with an external AI service to perform two main operations: generating text responses from a prompt or processing videos via a provided URL. The "Process Video" operation sends a video URL along with a user prompt to the AI service, which presumably analyzes or processes the video content and returns a response.
Common scenarios for this node include:
- Automatically analyzing video content for insights, summaries, or metadata extraction.
- Enhancing video workflows by integrating AI-driven video understanding.
- Generating textual output based on video content combined with user prompts.
For example, a user might provide a URL of a lecture video and a prompt asking for a summary of key points. The node would send this data to the AI service and return the processed result.
Properties
| Name | Meaning |
|---|---|
| Video URL | URL of the video to be processed (used only when Operation is "Process Video") |
| Model Type | Selects the AI model to use for text generation. Options include various Gemini, Llama, Mistral, Mixtral, and WizardLM models. (hidden when Operation is "Process Video") |
| Prompt | A prompt that you want the AI model to respond to. |
Note: The bundled source code shows additional properties related to text generation (temperature, max tokens, topP, topK, safety settings), but these are not relevant for the "Process Video" operation and thus omitted here per your request.
Output
The node outputs JSON data returned from the AI service API:
- For the "Process Video" operation, the output JSON contains the response from the
/process-videoendpoint of the AI service. This likely includes analysis results or processed information about the video based on the prompt. - The output is wrapped in an array of items as per n8n conventions, with each item containing a
jsonproperty holding the API response. - If an error occurs during the API call, the output JSON will contain an
errorfield with the error message.
No binary data output is indicated for this operation.
Dependencies
- Requires an API key credential for authenticating with the external AI service.
- The node makes HTTP POST requests to the AI service domain specified in the credentials.
- The
/process-videoendpoint is used for the video processing operation. - The node expects the AI service to accept JSON requests and return JSON responses.
Troubleshooting
- Missing Credentials: The node throws an error if no API credentials are provided. Ensure the API key credential is configured correctly.
- API Request Failures: Network issues, invalid URLs, or service downtime can cause request failures. The node either throws an error or continues on fail depending on configuration.
- Timeouts: The video processing request has a timeout of 120 seconds. Large or slow-processing videos may cause timeouts.
- Invalid Video URL: Providing an incorrect or inaccessible video URL may lead to errors from the AI service.
- Error Responses: If the AI service returns an error, it will appear in the output JSON under the
errorkey. Review the error message for troubleshooting.
Links and References
- No direct links are available from the source code. Users should refer to the documentation of the external AI service used for video processing at the domain specified in their credentials.