ocr_image
Extract all text blocks from an image, returning their text and bounding boxes in pixel and normalized coordinates.
Instructions
OCR 提取图片中所有文字块,返回 text + bbox(像素与归一化坐标)。
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"image": "<image>"
},
"name": "ocr_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | ||
| language | No | 语言提示,默认 auto |