Extract Async

import requests

url = "https://platform.reducto.ai/extract_async"

payload = {
    "options": {
        "ocr_mode": "standard",
        "extraction_mode": "ocr",
        "chunking": {"chunk_mode": "variable"},
        "table_summary": {"enabled": False},
        "figure_summary": {
            "enabled": False,
            "override": False
        },
        "filter_blocks": [],
        "force_url_result": False
    },
    "advanced_options": {
        "ocr_system": "highres",
        "table_output_format": "html",
        "merge_tables": False,
        "continue_hierarchy": True,
        "keep_line_breaks": False,
        "page_range": {},
        "large_table_chunking": {
            "enabled": True,
            "size": 50
        },
        "spreadsheet_table_clustering": "default",
        "add_page_markers": False,
        "remove_text_formatting": False,
        "return_ocr_data": False,
        "filter_line_numbers": False,
        "read_comments": False,
        "persist_results": False
    },
    "experimental_options": {
        "enrich": {
            "enabled": False,
            "mode": "standard"
        },
        "native_office_conversion": False,
        "enable_checkboxes": False,
        "enable_equations": False,
        "rotate_pages": True,
        "enable_scripts": False,
        "return_figure_images": False,
        "return_table_images": False,
        "layout_model": "default",
        "danger_filter_wide_boxes": False
    },
    "document_url": "<string>",
    "schema": "<any>",
    "system_prompt": "Be precise and thorough.",
    "generate_citations": False,
    "array_extract": {
        "enabled": False,
        "mode": "legacy",
        "pages_per_segment": 10,
        "streaming_extract_item_density": 50
    },
    "use_chunking": False,
    "priority": False,
    "webhook": {
        "mode": "disabled",
        "channels": []
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)

{
  "job_id": "<string>"
}