Azure AI Document Intelligence DocumentModels:compose API

swagger: '2.0'
info:
  title: Document Intelligence (formerly Form Recognizer) DocumentClassifiers DocumentModels:compose API
  version: '2024-11-30'
  description: Extracts content, layout, and structured data from documents.
  x-typespec-generated:
  - emitter: '@azure-tools/typespec-autorest'
schemes:
- https
consumes:
- application/json
produces:
- application/json
security:
- ApiKeyAuth: []
- OAuth2Auth:
  - https://cognitiveservices.azure.com/.default
tags:
- name: DocumentModels:compose
paths:
  /documentModels:compose:
    post:
      operationId: DocumentModels_ComposeModel
      description: Creates a new document model from document types of existing document models.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - name: composeRequest
        in: body
        description: Compose request parameters.
        required: true
        schema:
          $ref: '#/definitions/ComposeDocumentModelRequest'
      responses:
        '202':
          description: The request has been accepted for processing, but processing has not yet completed.
          headers:
            Operation-Location:
              type: string
              format: uri
              description: The location of an instance of DocumentModelComposeOperationDetails
            Retry-After:
              type: integer
              format: int32
              description: The Retry-After header can indicate how long the client should wait before polling the operation status.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Compose Document Model:
          $ref: ./examples/ComposeDocumentModel.json
      x-ms-long-running-operation: true
      tags:
      - DocumentModels:compose
definitions:
  DocumentIntelligenceErrorResponse:
    type: object
    description: Error response object.
    properties:
      error:
        $ref: '#/definitions/DocumentIntelligenceError'
        description: Error info.
    required:
    - error
  DocumentAnalysisFeature:
    type: string
    description: Document analysis features to enable.
    enum:
    - ocrHighResolution
    - languages
    - barcodes
    - formulas
    - keyValuePairs
    - styleFont
    - queryFields
    x-ms-enum:
      name: DocumentAnalysisFeature
      modelAsString: true
      values:
      - name: ocrHighResolution
        value: ocrHighResolution
        description: Perform OCR at a higher resolution to handle documents with fine print.
      - name: languages
        value: languages
        description: Enable the detection of the text content language.
      - name: barcodes
        value: barcodes
        description: Enable the detection of barcodes in the document.
      - name: formulas
        value: formulas
        description: Enable the detection of mathematical expressions in the document.
      - name: keyValuePairs
        value: keyValuePairs
        description: Enable the detection of general key value pairs (form fields) in the document.
      - name: styleFont
        value: styleFont
        description: Enable the recognition of various font styles.
      - name: queryFields
        value: queryFields
        description: Enable the extraction of additional fields via the queryFields query parameter.
  DocumentTypeDetails:
    type: object
    description: Document type info.
    properties:
      description:
        type: string
        description: Document model description.
        maxLength: 4096
      buildMode:
        $ref: '#/definitions/DocumentBuildMode'
        description: Custom document model build mode.
      fieldSchema:
        type: object
        description: Description of the document semantic schema using a JSON Schema style syntax.
        additionalProperties:
          $ref: '#/definitions/DocumentFieldSchema'
      fieldConfidence:
        type: object
        description: Estimated confidence for each field.
        additionalProperties:
          format: float
          type: number
      modelId:
        type: string
        description: Document model to use for analyzing documents with specified type.
        maxLength: 64
        pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$
      confidenceThreshold:
        type: number
        format: float
        description: Only perform analysis if docType confidence is above threshold.
      features:
        type: array
        description: List of optional analysis features.
        items:
          $ref: '#/definitions/DocumentAnalysisFeature'
      queryFields:
        type: array
        description: List of additional fields to extract.  Ex. "NumberOfGuests,StoreNumber"
        items:
          type: string
      maxDocumentsToAnalyze:
        type: integer
        format: int32
        description: Maximum number of documents of specified type to analyze.  Default=all.
  ComposeDocumentModelRequest:
    type: object
    description: Request body to create a composed document model from component document models.
    properties:
      modelId:
        type: string
        description: Unique document model name.
        pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$
      description:
        type: string
        description: Document model description.
        maxLength: 4096
      classifierId:
        type: string
        description: Custom classifier to split and classify the input file.
      split:
        type: string
        description: File splitting behavior.
        default: none
        enum:
        - auto
        - none
        - perPage
        x-ms-enum:
          name: SplitMode
          modelAsString: true
          values:
          - name: auto
            value: auto
            description: Automatically split file into documents.
          - name: none
            value: none
            description: Treat the entire file as a single document.
          - name: perPage
            value: perPage
            description: Treat each page in the file as a separate document.
      docTypes:
        type: object
        description: Dictionary mapping supported docTypes to the corresponding document models.
        additionalProperties:
          $ref: '#/definitions/DocumentTypeDetails'
      tags:
        type: object
        description: List of key-value tag attributes associated with the document model.
        additionalProperties:
          type: string
    required:
    - modelId
    - classifierId
    - docTypes
  DocumentFieldSchema:
    type: object
    description: Description of the field semantic schema using a JSON Schema style syntax.
    properties:
      type:
        $ref: '#/definitions/DocumentFieldType'
        description: Semantic data type of the field value.
      description:
        type: string
        description: Field description.
        maxLength: 4096
      example:
        type: string
        description: Example field content.
      items:
        $ref: '#/definitions/DocumentFieldSchema'
        description: Field type schema of each array element.
      properties:
        type: object
        description: Named sub-fields of the object field.
        additionalProperties:
          $ref: '#/definitions/DocumentFieldSchema'
    required:
    - type
  DocumentIntelligenceInnerError:
    type: object
    description: An object containing more specific information about the error.
    properties:
      code:
        type: string
        description: One of a server-defined set of error codes.
      message:
        type: string
        description: A human-readable representation of the error.
      innererror:
        $ref: '#/definitions/DocumentIntelligenceInnerError'
        description: Inner error.
  DocumentBuildMode:
    type: string
    description: Custom document model build mode.
    enum:
    - template
    - neural
    x-ms-enum:
      name: DocumentBuildMode
      modelAsString: true
      values:
      - name: template
        value: template
        description: Target documents with similar visual templates.
      - name: neural
        value: neural
        description: Support documents with diverse visual templates.
  DocumentFieldType:
    type: string
    description: Semantic data type of the field value.
    enum:
    - string
    - date
    - time
    - phoneNumber
    - number
    - integer
    - selectionMark
    - countryRegion
    - signature
    - array
    - object
    - currency
    - address
    - boolean
    - selectionGroup
    x-ms-enum:
      name: DocumentFieldType
      modelAsString: true
      values:
      - name: string
        value: string
        description: Plain text.
      - name: date
        value: date
        description: Date, normalized to ISO 8601 (YYYY-MM-DD) format.
      - name: time
        value: time
        description: Time, normalized to ISO 8601 (hh:mm:ss) format.
      - name: phoneNumber
        value: phoneNumber
        description: Phone number, normalized to E.164 (+{CountryCode}{SubscriberNumber}) format.
      - name: number
        value: number
        description: Floating point number, normalized to double precision floating point.
      - name: integer
        value: integer
        description: Integer number, normalized to 64-bit signed integer.
      - name: selectionMark
        value: selectionMark
        description: Is field selected?
      - name: countryRegion
        value: countryRegion
        description: Country/region, normalized to ISO 3166-1 alpha-3 format (ex. USA).
      - name: signature
        value: signature
        description: Is signature present?
      - name: array
        value: array
        description: List of subfields of the same type.
      - name: object
        value: object
        description: Named list of subfields of potentially different types.
      - name: currency
        value: currency
        description: Currency amount with optional currency symbol and unit.
      - name: address
        value: address
        description: Parsed address.
      - name: boolean
        value: boolean
        description: Boolean value, normalized to true or false.
      - name: selectionGroup
        value: selectionGroup
        description: Array of selected string values.
  DocumentIntelligenceError:
    type: object
    description: The error object.
    properties:
      code:
        type: string
        description: One of a server-defined set of error codes.
      message:
        type: string
        description: A human-readable representation of the error.
      target:
        type: string
        description: The target of the error.
      details:
        type: array
        description: An array of details about specific errors that led to this reported error.
        items:
          $ref: '#/definitions/DocumentIntelligenceError'
      innererror:
        $ref: '#/definitions/DocumentIntelligenceInnerError'
        description: An object containing more specific information than the current object about the error.
    required:
    - code
    - message
parameters:
  Azure.Core.Foundations.ApiVersionParameter:
    name: api-version
    in: query
    description: The API version to use for this operation.
    required: true
    type: string
    minLength: 1
    x-ms-parameter-location: method
    x-ms-client-name: apiVersion
securityDefinitions:
  ApiKeyAuth:
    type: apiKey
    name: Ocp-Apim-Subscription-Key
    in: header
  OAuth2Auth:
    type: oauth2
    flow: accessCode
    authorizationUrl: https://login.microsoftonline.com/common/oauth2/authorize
    scopes:
      https://cognitiveservices.azure.com/.default: ''
    tokenUrl: https://login.microsoftonline.com/common/oauth2/token
x-ms-parameterized-host:
  hostTemplate: '{endpoint}/documentintelligence'
  useSchemePrefix: false
  parameters:
  - name: endpoint
    in: path
    description: The Document Intelligence service endpoint.
    required: true
    type: string
    format: uri
    x-ms-skip-url-encoding: true
x-ms-paths:
  /documentClassifiers/{classifierId}:analyze?_overload=classifyDocument:
    post:
      operationId: DocumentClassifiers_ClassifyDocument
      description: Classifies document with document classifier.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.classifierId'
      - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.stringIndexType'
      - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.split'
      - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.pages'
      - name: classifyRequest
        in: body
        description: Classify request parameters.
        required: true
        schema:
          $ref: '#/definitions/ClassifyDocumentRequest'
      responses:
        '202':
          description: The request has been accepted for processing, but processing has not yet completed.
          headers:
            Operation-Location:
              type: string
              format: uri
              description: The location of an instance of AnalyzeOperation
            Retry-After:
              type: integer
              format: int32
              description: The Retry-After header can indicate how long the client should wait before polling the operation status.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Classify Document from Url:
          $ref: ./examples/ClassifyDocument_Url.json
      x-ms-long-running-operation: true
  /documentModels/{modelId}:analyze?_overload=analyzeDocument:
    post:
      operationId: DocumentModels_AnalyzeDocument
      description: Analyzes document with document model.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.modelId'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.pages'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.locale'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.stringIndexType'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.features'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.queryFields'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.outputContentFormat'
      - $ref: '#/parameters/DocumentModelAnalyzeRequestParams.output'
      - name: analyzeRequest
        in: body
        description: Analyze request parameters.
        required: true
        schema:
          $ref: '#/definitions/AnalyzeDocumentRequest'
      responses:
        '202':
          description: The request has been accepted for processing, but processing has not yet completed.
          headers:
            Operation-Location:
              type: string
              format: uri
              description: The location of an instance of AnalyzeOperation
            Retry-After:
              type: integer
              format: int32
              description: The Retry-After header can indicate how long the client should wait before polling the operation status.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Analyze Document from Base64:
          $ref: ./examples/AnalyzeDocument_Base64.json
        Analyze Document from Url:
          $ref: ./examples/AnalyzeDocument_Url.json
      x-ms-long-running-operation: true
  /operations/{operationId}?_overload=getDocumentClassifierBuildOperation:
    get:
      operationId: MiscellaneousOperations_GetDocumentClassifierBuildOperation
      description: Gets operation info.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - name: operationId
        in: path
        description: Operation ID
        required: true
        type: string
      - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader'
      responses:
        '200':
          description: The request has succeeded.
          schema:
            $ref: '#/definitions/DocumentClassifierBuildOperationDetails'
          headers:
            x-ms-client-request-id:
              type: string
              format: uuid
              description: An opaque, globally-unique, client-generated string identifier for the request.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Get Operation - Document Classifier Build:
          $ref: ./examples/GetOperation_DocumentClassifierBuild.json
  /operations/{operationId}?_overload=getDocumentClassifierCopyToOperation:
    get:
      operationId: MiscellaneousOperations_GetDocumentClassifierCopyToOperation
      description: Gets operation info.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - name: operationId
        in: path
        description: Operation ID
        required: true
        type: string
      - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader'
      responses:
        '200':
          description: The request has succeeded.
          schema:
            $ref: '#/definitions/DocumentClassifierCopyToOperationDetails'
          headers:
            x-ms-client-request-id:
              type: string
              format: uuid
              description: An opaque, globally-unique, client-generated string identifier for the request.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Get Operation - Document Classifier Copy To:
          $ref: ./examples/GetOperation_DocumentClassifierCopyTo.json
  /operations/{operationId}?_overload=getDocumentModelComposeOperation:
    get:
      operationId: MiscellaneousOperations_GetDocumentModelComposeOperation
      description: Gets operation info.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - name: operationId
        in: path
        description: Operation ID
        required: true
        type: string
      - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader'
      responses:
        '200':
          description: The request has succeeded.
          schema:
            $ref: '#/definitions/DocumentModelComposeOperationDetails'
          headers:
            x-ms-client-request-id:
              type: string
              format: uuid
              description: An opaque, globally-unique, client-generated string identifier for the request.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Get Operation - Document Model Compose:
          $ref: ./examples/GetOperation_DocumentModelCompose.json
  /operations/{operationId}?_overload=getDocumentModelCopyToOperation:
    get:
      operationId: MiscellaneousOperations_GetDocumentModelCopyToOperation
      description: Gets operation info.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - name: operationId
        in: path
        description: Operation ID
        required: true
        type: string
      - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader'
      responses:
        '200':
          description: The request has succeeded.
          schema:
            $ref: '#/definitions/DocumentModelCopyToOperationDetails'
          headers:
            x-ms-client-request-id:
              type: string
              format: uuid
              description: An opaque, globally-unique, client-generated string identifier for the request.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Get Operation - Document Model Copy To:
          $ref: ./examples/GetOperation_DocumentModelCopyTo.json
  /operations/{operationId}?_overload=getOperation:
    get:
      operationId: MiscellaneousOperations_GetOperation
      description: Gets operation info.
      parameters:
      - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter'
      - name: operationId
        in: path
        description: Operation ID
        required: true
        type: string
      - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader'
      responses:
        '200':
          description: The request has succeeded.
          schema:
            $ref: '#/definitions/DocumentIntelligenceOperationDetails'
          headers:
            x-ms-client-request-id:
              type: string
              format: uuid
              description: An opaque, globally-unique, client-generated string identifier for the request.
        default:
          description: An unexpected error response.
          schema:
            $ref: '#/definitions/DocumentIntelligenceErrorResponse'
      x-ms-examples:
        Get Operation:
          $ref: ./examples/GetOperation.json