OCR: make a scan searchable
ocr_pdfAdd a text layer to scanned pages, so the text can be searched, copied and read by AI. Takes a scanned PDF or an image (a photo or scan as PNG, JPEG, TIFF, GIF, WebP or HEIC), which comes back as a searchable PDF. Reads 90 languages and finds the language itself; pass language only when the person names one.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "ocr_pdf"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file | No | A file the person attached in ChatGPT (filled in by ChatGPT). | |
| file_id | No | A FynePDF file_id from upload_file, import_file_from_url or an earlier tool. | |
| file_url | No | A public link to the file. | |
| language | No | A BCP 47 code such as "en", "ne", "hi", "ar", "zh-Hans" or "ja". Left out ("auto"), the language is found from the file. | |
| library_file_id | No | A file from the person's FynePDF Library (from list_library_files). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| card | No | ||
| files | Yes | ||
| steps | Yes | ||
| job_id | Yes | ||
| status | Yes | ||
| credits | Yes | ||
| message | Yes |