document
Consolidate, analyze, and query PDF documents to extract tables, figures, and text, with optional OCR and knowledge graph integration.
Instructions
Consolidated PDF document entrypoint.
Existing document tools stay registered and keep their original contracts.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| op | Yes | ||
| file_paths | No | ||
| pdf_path | No | ||
| doc_id | No | ||
| output_dir | No | ||
| output_path | No | ||
| async_mode | No | ||
| use_marker | No | ||
| ocr_enabled | No | ||
| ocr_language | No | eng | |
| rotate_pages | No | ||
| deskew | No | ||
| page | No | ||
| limit | No | ||
| show_labels | No | ||
| include_reading_order | No | ||
| marker_max_pages_per_chunk | No | ||
| extract_figures | No | ||
| index_knowledge_graph | No | ||
| page_ranges | No | ||
| output_format | No | markdown | |
| refresh | No | ||
| query | No | ||
| criteria | No | ||
| doc_b_id | No | ||
| ctx | No |