smart_ocr
Extract text from images and PDFs by automatically routing simple images to OCR and large documents to vision-language models for accurate results.
Instructions
Route simple images to OCR and PDFs/large images to PaddleOCR-VL.
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_path": "<image_path>"
},
"name": "smart_ocr"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | ch | |
| image_path | Yes | ||
| force_model | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | ||
| blocks | No | ||
| markdown | No | ||
| routed_to | Yes | ||
| source_name | Yes | ||
| elapsed_seconds | Yes |