Run OCR
transkribus_recog_run_ocrRun OCR on a document or specific pages in a Transkribus collection to extract text from scanned images.
Instructions
Run OCR on a document or specific pages in a collection.
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": {
"collId": "<collId>",
"docId": "<docId>"
},
"name": "transkribus_recog_run_ocr"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Deprecated document-ID alias; if supplied, must match docId. OCR does not accept a model ID. | |
| docId | Yes | Document ID | |
| pages | No | Page range (e.g. "1-5") | |
| collId | Yes | Collection ID | |
| ocrType | No | OCR type (default "Legacy") | |
| language | No | Language for OCR | |
| typeFace | No | Type face for OCR | |
| doBlockSegOnly | No | Only do block segmentation (default false) |