Parse

POST /parse

Try it

Parse

Python

import requests

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

payload = {
    "input": "<string>",
    "enhance": {
        "agentic": [],
        "summarize_figures": True
    },
    "retrieval": {
        "chunking": { "chunk_mode": "disabled" },
        "filter_blocks": [],
        "embedding_optimized": False
    },
    "formatting": {
        "add_page_markers": False,
        "table_output_format": "dynamic",
        "merge_tables": False,
        "include": []
    },
    "spreadsheet": {
        "split_large_tables": {
            "enabled": True,
            "size": 50
        },
        "include": [],
        "clustering": "accurate",
        "exclude": []
    },
    "settings": {
        "ocr_system": "standard",
        "force_url_result": False,
        "return_ocr_data": False,
        "return_images": [],
        "embed_pdf_metadata": False,
        "persist_results": False
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())

200

{
  "job_id": "<string>",
  "duration": 123,
  "usage": {
    "num_pages": 123,
    "credits": 123
  },
  "result": {
    "type": "<string>",
    "chunks": [
      {
        "content": "<string>",
        "embed": "<string>",
        "enriched": "<string>",
        "blocks": [
          {
            "type": "Header",
            "bbox": {
              "left": 123,
              "top": 123,
              "width": 123,
              "height": 123,
              "page": 123,
              "original_page": 123
            },
            "content": "<string>",
            "image_url": "<string>",
            "confidence": "low",
            "granular_confidence": {
              "extract_confidence": 123,
              "parse_confidence": 123
            }
          }
        ],
        "enrichment_success": false
      }
    ],
    "ocr": {
      "words": [
        {
          "text": "<string>",
          "bbox": {
            "left": 123,
            "top": 123,
            "width": 123,
            "height": 123,
            "page": 123,
            "original_page": 123
          },
          "confidence": 123,
          "chunk_index": 123
        }
      ],
      "lines": [
        {
          "text": "<string>",
          "bbox": {
            "left": 123,
            "top": 123,
            "width": 123,
            "height": 123,
            "page": 123,
            "original_page": 123
          },
          "confidence": 123,
          "chunk_index": 123
        }
      ]
    },
    "custom": "<unknown>"
  },
  "pdf_url": "<string>",
  "studio_link": "<string>"
}

Authorizations

Authorization · string · header · required

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

Body

application/json

SyncParseConfig

input · required

For parse/split/extract pipelines, 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 jobid:// prefixed URL obtained from a previous /parse invocation

For edit pipelines, this should be a string containing the edit instructions

enhance · Enhance · object

Show child attributes

enhance. agentic · (TableAgentic · object | FigureAgentic · object | TextAgentic · object)[]

Agentic uses vision language models to enhance the accuracy of the output of different types of extraction. This will incur a cost and latency increase.

TableAgentic

Show child attributes

enhance.agentic. scope · string · required

Allowed value: "table"

enhance.agentic. prompt · string | null

Custom prompt for table agentic.

enhance. summarize_figures · boolean · default: true

If True, summarize figures using a small vision language model. Defaults to True.

retrieval · Retrieval · object

Show child attributes

retrieval. chunking · Chunking · object

Show child attributes

retrieval.chunking. chunk_mode · enum<string> · default: disabled

Choose how to partition chunks. Variable mode chunks by character length and visual context. Section mode chunks by section headers. Page mode chunks according to pages. Page sections mode chunks first by page, then by sections within each page. Disabled returns one single chunk.

Available options: variable, section, page, disabled, block, page_sections

retrieval.chunking. chunk_size · integer | null

The approximate size of chunks (in characters) that the document will be split into. Defaults to null, in which case the chunk size is variable between 250 - 1500 characters.

retrieval. filter_blocks · enum<string>[]

A list of block types to filter out from 'content' and 'embed' fields. By default, no blocks are filtered.

Available options: Header, Footer, Title, Section Header, Page Number, List Item, Figure, Table, Key Value, Text, Comment, Signature

retrieval. embedding_optimized · boolean · default: false

If True, use embedding optimized mode. Defaults to False.

formatting · Formatting · object

Show child attributes

formatting. add_page_markers · boolean · default: false

If True, add page markers to the output. Defaults to False. Useful for extracting data with page specific information.

formatting. table_output_format · enum<string> · default: dynamic

The mode to use for table output. Defaults to dynamic, which returns md for simpler tables and html for more complex tables.

Available options: html, json, md, jsonbbox, dynamic, csv

formatting. merge_tables · boolean · default: false

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

formatting. include · enum<string>[]

A list of formatting to include in the output. [insert description of each option here later]

Available options: change_tracking, highlight, comments, hyperlinks

spreadsheet · Spreadsheet · object

Show child attributes

spreadsheet. split_large_tables · SplitLargeTables · object

Show child attributes

spreadsheet.split_large_tables. enabled · boolean · default: true

If True, split large tables into smaller tables. Defaults to True.

spreadsheet.split_large_tables. size · integer · default: 50

The size of the tables to split into. Defaults to 50.

spreadsheet. include · enum<string>[]

Whether to include cell color and formula information in the output.

Available options: cell_colors, formula

spreadsheet. clustering · enum<string> · default: accurate

In a spreadsheet with different tables inside, we enable splitting up the tables by default. Accurate mode applies more powerful models for superior accuracy, at 5× the default per-cell rate. Disabling will register as one large table.

Available options: accurate, fast, disabled

spreadsheet. exclude · enum<string>[]

Whether to exclude hidden sheets, rows, or columns in the output.

Available options: hidden_sheets, hidden_rows, hidden_cols

settings · Settings · object

Show child attributes

settings. ocr_system · enum<string> · default: standard

Standard is our best multilingual OCR system. Legacy only supports germanic languages and is available for backwards compatibility.

Available options: standard, legacy

settings. force_url_result · boolean · default: false

Force the result to be returned in URL form.

settings. force_file_extension · string | null

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

settings. return_ocr_data · boolean · default: false

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

settings. return_images · enum<string>[]

Whether to return images for the specified block types. By default, no images are returned.

Available options: figure, table

settings. embed_pdf_metadata · boolean · default: false

If True, embed OCR metadata into the returned PDF. Defaults to False.

settings. persist_results · boolean · default: false

If True, persist the results indefinitely. Defaults to False.

settings. timeout · number | null

The timeout for the job in seconds.

settings. page_range

The page range to process (1-indexed). By default, the entire document is processed.

Show child attributes

settings.page_range. start · integer | null

The page number to start processing from (1-indexed).

settings.page_range. end · integer | null

The page number to stop processing at (1-indexed).

settings. document_password · string | null

Password to decrypt password-protected documents.

Response

200

application/json

Successful Response

ParseResponse

job_id · string · required

duration · number · required

The duration of the parse request in seconds.

usage · ParseUsage · object · required

Show child attributes

usage. num_pages · integer · required

usage. credits · number | null

result · FullResult · object · required

The response from the document processing service. Note that there can be two types of responses, Full Result and URL Result. This is due to limitations on the max return size on HTTPS. If the response is too large, it will be returned as a presigned URL in the URL response. You should handle this in your application.

FullResult

Show child attributes

result. type · string · required

type = 'full'

Allowed value: "full"

result. chunks · ParseChunk · object[] · required

Show child attributes

result.chunks. content · string · required

The content of the chunk extracted from the document.

result.chunks. embed · string · required

Chunk content optimized for embedding and retrieval.

result.chunks. enriched · string | null · required

The enriched content of the chunk extracted from the document.

result.chunks. blocks · ParseBlock · object[] · required

Show child attributes

result.chunks.blocks. type · enum<string> · required

The type of block extracted from the document.

Available options: Header, Footer, Title, Section Header, Page Number, List Item, Figure, Table, Key Value, Text, Comment, Signature

result.chunks.blocks. bbox · BoundingBox · object · required

The bounding box of the block extracted from the document.

Show child attributes

result.chunks.blocks.bbox. left · number · required

result.chunks.blocks.bbox. top · number · required

result.chunks.blocks.bbox. width · number · required

result.chunks.blocks.bbox. height · number · required

result.chunks.blocks.bbox. page · integer · required

The page number of the bounding box (1-indexed).

result.chunks.blocks.bbox. original_page · integer

The page number in the original document of the bounding box (1-indexed).

result.chunks.blocks. content · string · required

The content of the block extracted from the document.

result.chunks.blocks. image_url · string | null

(Experimental) The URL of the image associated with the block.

result.chunks.blocks. confidence · string | null · default: low

The confidence for the block. It is either low or high and takes into account factors like OCR and table structure

result.chunks.blocks. granular_confidence · GranularConfidence · object

Granular confidence scores for the block. It is a dictionary of confidence scores for the block. The confidence scores will not be None if the user has enabled numeric confidence scores.

Show child attributes

result.chunks.blocks.granular_confidence. extract_confidence · number | null

result.chunks.blocks.granular_confidence. parse_confidence · number | null

result.chunks. enrichment_success · boolean · default: false

Whether the enrichment was successful.

result. ocr · OCRResult · object

Show child attributes

result.ocr. words · OCRWord · object[] · required

Show child attributes

result.ocr.words. text · string · required

result.ocr.words. bbox · BoundingBox · object · required

Show child attributes

result.ocr.words.bbox. left · number · required

result.ocr.words.bbox. top · number · required

result.ocr.words.bbox. width · number · required

result.ocr.words.bbox. height · number · required

result.ocr.words.bbox. page · integer · required

The page number of the bounding box (1-indexed).

result.ocr.words.bbox. original_page · integer

The page number in the original document of the bounding box (1-indexed).

result.ocr.words. confidence · number | null

OCR confidence score between 0 and 1, where 1 indicates highest confidence

result.ocr.words. chunk_index · integer | null

The index of the chunk that the word belongs to.

result.ocr. lines · OCRLine · object[] · required

Show child attributes

result.ocr.lines. text · string · required

result.ocr.lines. bbox · BoundingBox · object · required

Show child attributes

result.ocr.lines.bbox. left · number · required

result.ocr.lines.bbox. top · number · required

result.ocr.lines.bbox. width · number · required

result.ocr.lines.bbox. height · number · required

result.ocr.lines.bbox. page · integer · required

The page number of the bounding box (1-indexed).

result.ocr.lines.bbox. original_page · integer

The page number in the original document of the bounding box (1-indexed).

result.ocr.lines. confidence · number | null

OCR confidence score between 0 and 1, where 1 indicates highest confidence

result.ocr.lines. chunk_index · integer | null

The index of the chunk that the line belongs to.

result. custom · unknown

pdf_url · string | null

The storage URL of the converted PDF file.

studio_link · string | null

The link to the studio pipeline for the document.