POST
/
split
Split
import requests

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

payload = {
    "options": {
        "ocr_mode": "standard",
        "extraction_mode": "ocr",
        "chunking": { "chunk_mode": "variable" },
        "table_summary": { "enabled": False },
        "figure_summary": {
            "enabled": False,
            "enhanced": False,
            "override": False
        },
        "filter_blocks": [],
        "force_url_result": False
    },
    "advanced_options": {
        "ocr_system": "highres",
        "table_output_format": "html",
        "merge_tables": False,
        "include_formula_information": False,
        "include_color_information": 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,
        "exclude_hidden_sheets": False,
        "exclude_hidden_rows_cols": False,
        "enable_change_tracking": False,
        "enable_highlight_detection": False
    },
    "experimental_options": {
        "enrich": {
            "enabled": False,
            "mode": "standard"
        },
        "native_office_conversion": False,
        "enable_checkboxes": False,
        "enable_equations": False,
        "rotate_pages": True,
        "rotate_figures": False,
        "enable_scripts": False,
        "return_figure_images": False,
        "return_table_images": False,
        "layout_model": "default",
        "embed_text_metadata_pdf": False,
        "numerical_parse_confidence": False,
        "detect_signatures": False,
        "danger_filter_wide_boxes": False
    },
    "split_description": [
        {
            "name": "<string>",
            "description": "<string>",
            "partition_key": "<string>"
        }
    ],
    "split_rules": "Split the document into the applicable sections. Sections may only overlap at their first and last page if at all.",
    "priority": False,
    "document_url": "<string>",
    "split_options": { "table_cutoff": "truncate" }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
{
  "usage": {
    "num_pages": 123,
    "credits": 123
  },
  "result": {
    "section_mapping": {},
    "splits": [
      {
        "name": "<string>",
        "pages": [
          123
        ],
        "conf": "low",
        "partitions": [
          {
            "name": "<string>",
            "pages": [
              123
            ],
            "conf": "low"
          }
        ]
      }
    ]
  }
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
split_description
SplitCategory · object[]
required

The configuration options for processing the document.

document_url
required

The URL of the document to be processed. You can provide one of the following:

  1. A publicly available URL
  2. A presigned S3 URL
  3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document
  4. A job_id (jobid://) or a list of job_ids (jobid://) obtained from a previous /parse endpoint
options
object
advanced_options
object
experimental_options
object
split_rules
string
default:Split the document into the applicable sections. Sections may only overlap at their first and last page if at all.

The prompt that describes rules for splitting the document.

priority
boolean
default:false

If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs.

split_options
object

Response

Successful Response

usage
object
required
result
object
required

The split result.