detect_elements
Detect objects in an image and return labels, bounding boxes, and confidence scores. Uses conservative detection to reduce false claims, prioritizing accuracy in image analysis.
Instructions
Detect objects in an image with mandatory bounding boxes.
Conservative by design: prefers false negatives over false positives.
Args:
image_source: Local file path or http(s) URL of the image.
prompt: Optional extra instructions (e.g. "only people and vehicles").
temperature: Sampling temperature, default 0.2.
Returns:
JSON: {"objects":[{"label","bbox","confidence"}], "overall_confidence"}.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | ||
| temperature | No | ||
| image_source | Yes |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |