Amazon Textract Document Analysis API

openapi: 3.0.0
info:
  title: Amazon Textract Async Operations Document Analysis API
  description: Amazon Textract is a machine learning service that automatically extracts text, handwriting, and data from scanned documents, going beyond simple OCR to identify and extract data from forms and tables.
  version: '2018-06-27'
  contact:
    name: Kin Lane
    email: kin@apievangelist.com
    url: https://aws.amazon.com/textract/
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://textract.amazonaws.com
  description: Amazon Textract API endpoint
tags:
- name: Document Analysis
  description: Operations for analyzing document structure and content.
paths:
  /#AnalyzeDocument:
    post:
      operationId: AnalyzeDocument
      summary: Amazon Textract Analyze Document
      description: Analyzes an input document for relationships between detected items, including tables, forms, and key-value pairs.
      requestBody:
        required: true
        content:
          application/x-amz-json-1.1:
            schema:
              type: object
              properties:
                Document:
                  type: object
                  properties:
                    Bytes:
                      type: string
                      format: byte
                    S3Object:
                      type: object
                      properties:
                        Bucket:
                          type: string
                        Name:
                          type: string
                FeatureTypes:
                  type: array
                  description: A list of the types of analysis to perform.
                  items:
                    type: string
                    enum:
                    - TABLES
                    - FORMS
                    - QUERIES
                    - SIGNATURES
                    - LAYOUT
                QueriesConfig:
                  type: object
                  properties:
                    Queries:
                      type: array
                      items:
                        type: object
                        properties:
                          Text:
                            type: string
                          Alias:
                            type: string
                          Pages:
                            type: array
                            items:
                              type: string
              required:
              - Document
              - FeatureTypes
      responses:
        '200':
          description: Successful document analysis response.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentAnalysis'
      tags:
      - Document Analysis
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    DocumentAnalysis:
      type: object
      description: Response object containing the results of document text detection or analysis, including detected blocks of text, tables, and forms.
      properties:
        DocumentMetadata:
          type: object
          description: Metadata about the document.
          properties:
            Pages:
              type: integer
              description: The number of pages detected in the document.
        Blocks:
          type: array
          description: The items detected in the document.
          items:
            type: object
            properties:
              BlockType:
                type: string
                description: The type of text item detected.
                enum:
                - KEY_VALUE_SET
                - PAGE
                - LINE
                - WORD
                - TABLE
                - CELL
                - SELECTION_ELEMENT
                - MERGED_CELL
                - TITLE
                - QUERY
                - QUERY_RESULT
                - SIGNATURE
                - TABLE_TITLE
                - TABLE_FOOTER
                - LAYOUT_TEXT
                - LAYOUT_TITLE
                - LAYOUT_HEADER
                - LAYOUT_FOOTER
                - LAYOUT_SECTION_HEADER
                - LAYOUT_PAGE_NUMBER
                - LAYOUT_LIST
                - LAYOUT_FIGURE
                - LAYOUT_TABLE
                - LAYOUT_KEY_VALUE
              Confidence:
                type: number
                format: float
                description: The confidence score for the detected block.
              Text:
                type: string
                description: The word or line of text recognized.
              Geometry:
                type: object
                properties:
                  BoundingBox:
                    type: object
                    properties:
                      Width:
                        type: number
                      Height:
                        type: number
                      Left:
                        type: number
                      Top:
                        type: number
                  Polygon:
                    type: array
                    items:
                      type: object
                      properties:
                        X:
                          type: number
                        Y:
                          type: number
              Id:
                type: string
                description: The identifier for the recognized text block.
              Relationships:
                type: array
                items:
                  type: object
                  properties:
                    Type:
                      type: string
                      enum:
                      - VALUE
                      - CHILD
                      - COMPLEX_FEATURES
                      - MERGED_CELL
                      - TITLE
                      - ANSWER
                      - TABLE
                      - TABLE_TITLE
                      - TABLE_FOOTER
                    Ids:
                      type: array
                      items:
                        type: string
              Page:
                type: integer
                description: The page on which the block was detected.
        AnalyzeDocumentModelVersion:
          type: string
          description: The version of the model used to analyze the document.