Reducto · Schema

ParseBlock

Reducto ParseBlock schema

Document ParsingPDFOCRData ExtractionAIMachine LearningDocument IntelligenceStructured Data

Properties

Name	Type	Description
type	string	The type of block extracted from the document.
bbox	object	The bounding box of the block extracted from the document.
content	string	The content of the block extracted from the document.
image_url	string	(Experimental) The URL of the image associated with the block.
chart_data	array	(Experimental) The URL/link to chart data JSON for figure blocks processed by chart agent.
confidence	string	The confidence for the block. It is either low or high and takes into account factors like OCR and table structure
granular_confidence	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.
extra	object	Extra metadata fields for the block. Fields like 'is_chart' will only appear when set to True.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/reducto/refs/heads/main/json-schema/reducto-parseblock.json",
  "title": "ParseBlock",
  "description": "Reducto ParseBlock schema",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "Header",
        "Footer",
        "Title",
        "Section Header",
        "Page Number",
        "List Item",
        "Figure",
        "Table",
        "Key Value",
        "Text",
        "Comment",
        "Signature"
      ],
      "title": "Type",
      "description": "The type of block extracted from the document."
    },
    "bbox": {
      "$ref": "#/components/schemas/BoundingBox",
      "description": "The bounding box of the block extracted from the document."
    },
    "content": {
      "type": "string",
      "title": "Content",
      "description": "The content of the block extracted from the document."
    },
    "image_url": {
      "type": "string",
      "nullable": true,
      "title": "Image Url",
      "description": "(Experimental) The URL of the image associated with the block."
    },
    "chart_data": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "nullable": true,
      "title": "Chart Data",
      "description": "(Experimental) The URL/link to chart data JSON for figure blocks processed by chart agent."
    },
    "confidence": {
      "type": "string",
      "nullable": true,
      "title": "Confidence",
      "description": "The confidence for the block. It is either low or high and takes into account factors like OCR and table structure",
      "default": "low"
    },
    "granular_confidence": {
      "$ref": "#/components/schemas/GranularConfidence",
      "nullable": true,
      "description": "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."
    },
    "extra": {
      "additionalProperties": true,
      "type": "object",
      "nullable": true,
      "title": "Extra",
      "description": "Extra metadata fields for the block. Fields like 'is_chart' will only appear when set to True."
    }
  },
  "type": "object",
  "required": [
    "type",
    "bbox",
    "content"
  ]
}