Syrus AI Multimodal (Gemma 4)

Interagir com a API Syrus AI

Actions3

Multimodal → Analyze

AI-generated

Summary

Analyze an image with a user-defined prompt by sending the image (Base64 encoded) and prompt to the Syrus AI API and receiving the analysis response.

Inputs

  • Prompt (required) — A question or description about the image to guide the analysis.
  • Image Field (required) — The name of the input field containing the image as a Base64-encoded string.

Output shape

a JSON array representing the analysis results for each input item, corresponding to the API response.

The operation processes each input item individually, extracting the Base64 image data from the specified field. If the image field is missing, it throws an error unless 'Continue On Fail' is enabled, in which case it returns an error message for that item. The output includes the API analysis results for each item.

Examples

Example 1: Send an image in Base64 format in the input item field named 'data' and ask the model to describe the image contents.

Set 'Prompt' to a descriptive question or instruction, e.g., 'Describe this image'. Set 'Image Field' to 'data'. The node outputs the AI's analysis of the image in JSON form.

Links

Discussion