document
Perform PDF document operations including table, figure, and section extraction, OCR, and knowledge graph indexing for precise asset retrieval and analysis.
Instructions
Consolidated PDF document entrypoint.
Existing document tools stay registered and keep their original contracts.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| op | Yes | ||
| ctx | No | ||
| page | No | ||
| limit | No | ||
| query | No | ||
| deskew | No | ||
| doc_id | No | ||
| refresh | No | ||
| criteria | No | ||
| doc_b_id | No | ||
| pdf_path | No | ||
| async_mode | No | ||
| file_paths | No | ||
| output_dir | No | ||
| use_marker | No | ||
| ocr_enabled | No | ||
| output_path | No | ||
| page_ranges | No | ||
| show_labels | No | ||
| ocr_language | No | eng | |
| rotate_pages | No | ||
| output_format | No | markdown | |
| extract_figures | No | ||
| include_reading_order | No | ||
| index_knowledge_graph | No | ||
| marker_max_pages_per_chunk | No |