Document Processing Request

Schema for a Google Cloud Document AI processing request.

Data ExtractionDocument ProcessingFormsGoogle CloudMachine LearningOCR

Properties

Name	Type	Description
inlineDocument	object	An inline document for processing.
rawDocument	object	A raw document provided as bytes.
skipHumanReview	boolean	Whether to skip the human review stage.
fieldMask	string	Specifies which fields to include in the output document.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/google-cloud-document-ai/refs/heads/main/json-schema/document-processing.json",
  "title": "Document Processing Request",
  "description": "Schema for a Google Cloud Document AI processing request.",
  "type": "object",
  "properties": {
    "inlineDocument": {
      "type": "object",
      "description": "An inline document for processing.",
      "properties": {
        "mimeType": {
          "type": "string",
          "description": "MIME type of the document."
        },
        "text": {
          "type": "string",
          "description": "UTF-8 encoded text of the document."
        },
        "content": {
          "type": "string",
          "description": "Base64-encoded document content."
        }
      }
    },
    "rawDocument": {
      "type": "object",
      "description": "A raw document provided as bytes.",
      "properties": {
        "content": {
          "type": "string",
          "description": "Base64-encoded document content."
        },
        "mimeType": {
          "type": "string",
          "description": "MIME type of the raw document."
        }
      }
    },
    "skipHumanReview": {
      "type": "boolean",
      "description": "Whether to skip the human review stage."
    },
    "fieldMask": {
      "type": "string",
      "description": "Specifies which fields to include in the output document."
    }
  }
}