DeepSeek OCR
deepseek_ocrExtracts text from local PDF, Word, PowerPoint, or image files via DeepSeek's OCR API and returns per-page text for downstream processing.
Instructions
Extract text from a local PDF, Word, PowerPoint or image file with DeepSeek's OCR API. Returns per-page text.
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": {
"file_path": "<file_path>"
},
"name": "deepseek_ocr"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| purpose | No | text_recognition extracts text directly from text-only Office files and OCRs other files page by page; rich_layout_recognition OCRs every page. | text_recognition |
| file_path | Yes | Local path to a PDF, Word (doc/docx), PowerPoint (ppt/pptx), or image (png/jpeg/webp/gif/bmp/tiff). Max 100 MiB, 1000 pages. |