mineru_parse
Parse documents from URLs to extract text, tables, and formulas. Supports PDF, DOC, PPT, and image formats with OCR and multiple export options.
Instructions
Parse a document URL. Returns task_id to check status.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Document URL (PDF, DOC, PPT, images) | |
| model | No | pipeline=fast, vlm=90% accuracy | |
| pages | No | Page range: 1-10,15 or 2--2 | |
| ocr | No | Enable OCR (pipeline only) | |
| formula | No | Formula recognition | |
| table | No | Table recognition | |
| language | No | Language code: ch, en, etc | |
| formats | No | Extra export formats |