The node allows you to configure certain parameters as dynamic inputs. You can enable these in the “Configure Inputs” section:
Use Link: Boolean
true/false to use video URL instead of file upload
When enabled, allows direct input of video URLs
Prompt: String
The specific question or instruction for analyzing the video
Example: “Describe the main events in this video”
video_model_preference: String
Name of the AI model to use for video analysis
Accepted values: “Gemini 1.5 Flash” or “Gemini 1.5 Pro”
Cache Response: Boolean
true/false to enable/disable response caching
Helps reduce API calls for identical inputs
Temperature: Number
Value between 0 and 1
Controls analysis consistency and creativity
When enabled as inputs, these parameters can be dynamically set by previous nodes in your workflow. If not enabled, the values set in the node configuration will be used.
Analysis quality depends on video resolution and clarity
When using the Use Link option make sure the link has the appropriate file extension
In summary, the Analyze Video node provides powerful video analysis capabilities using state-of-the-art AI vision models, suitable for a wide range of applications from content description to detailed motion analysis.