Extract - Reducto API

Authorizations

Authorization

string

header

required

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

Body

application/json

document_url

required

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

A publicly available URL
A presigned S3 URL
A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document
A job_id (jobid://) or a list of job_ids (jobid://)

schema

any

required

The JSON schema to use for extraction.

options

object

advanced_options

object

advanced_options.ocr_system

enum<string>

default:highres

The OCR system to use. Highres is recommended for documents with English characters.

Available options:

highres,

multilingual,

combined

advanced_options.table_output_format

enum<string>

default:html

The mode to use for table output. Dynamic returns md for simpler tables and html for more complex tables.

Available options:

html,

json,

md,

jsonbbox,

dynamic,

ai_json

advanced_options.merge_tables

boolean

default:false

A flag to indicate if consecutive tables with the same number of columns should be merged.

advanced_options.continue_hierarchy

boolean

default:true

A flag to indicate if the hierarchy of the document should be continued from chunk to chunk.

advanced_options.keep_line_breaks

boolean

default:false

If line breaks should be preserved in the text.

advanced_options.page_range

The page range to process. By default, the entire document is processed.

advanced_options.force_file_extension

string

Force the URL to be downloaded as a specific file extension (e.g. .png).

advanced_options.large_table_chunking

object

The configuration options for large table chunking (currently only supported on spreadsheet and CSV files).

advanced_options.spreadsheet_table_clustering

enum<string>

default:default

On a spreadsheet, the algorithm that is used to split up sheets into multiple tables.

Available options:

default,

disabled

advanced_options.add_page_markers

boolean

default:false

If True, add page markers to the output (e.g. [[PAGE 1 BEGINS HERE]] and [[PAGE 1 ENDS HERE]] added as blocks to the content). Defaults to False.

advanced_options.remove_text_formatting

boolean

default:false

If True, remove text formatting from the output (e.g. hyphens for list items). Defaults to False.

advanced_options.return_ocr_data

boolean

default:false

If True, return OCR data in the result. Defaults to False.

advanced_options.document_password

string

Password to decrypt password-protected documents.

experimental_options

object

system_prompt

string

default:Be precise and thorough.

A system prompt to use for the extraction. This is a general prompt that is applied to the entire document before any other prompts.

generate_citations

boolean

default:false

If citations should be generated for the extracted content.

array_extract

object

The configuration options for array extract

Response

200

application/json

Successful Response

usage

object

required

result

any[]

required

The extracted response in your provided schema. This is a list of dictionaries. If disbale_chunking is True (default), then it will be a list of length one.

citations

any[] | null

required

The citations corresponding to the extracted response.

API Reference

Authorizations

Body

Response