recognize_image
Recognize and describe the content of local images using a multimodal model. Provide an optional prompt to guide the description.
Instructions
Recognize and describe an image using a multimodal model (Kimi K2.5). Returns a text description of the image content.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | Optional instruction to guide the recognition, e.g. 'extract all text', 'describe the UI layout', 'what code is shown' | |
| image_path | Yes | Absolute path to the local image file |