swagger: '2.0' info: title: Microsoft Azure Document Intelligence (formerly Form Recognizer) version: 2024-02-29-preview description: Extracts content, layout, and structured data from documents. x-typespec-generated: - emitter: '@azure-tools/typespec-autorest' schemes: - https x-ms-parameterized-host: hostTemplate: '{endpoint}/documentintelligence' useSchemePrefix: false parameters: - name: endpoint in: path description: The Document Intelligence service endpoint. required: true type: string produces: - application/json consumes: - application/json security: - ApiKeyAuth: [] - OAuth2Auth: - https://cognitiveservices.azure.com/.default 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 tags: - name: documentClassifiers - name: documentClassifiers:build - name: documentModels - name: documentModels:authorizeCopy - name: documentModels:build - name: documentModels:compose - name: Info - name: Operations paths: /documentClassifiers: get: operationId: microsoftAzureDocumentclassifiersListclassifiers description: List all document classifiers. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/PagedDocumentClassifierDetails' 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/ErrorResponse' x-ms-examples: Get Document Classifiers: $ref: ./examples/GetDocumentClassifiers.json x-ms-pageable: nextLinkName: nextLink summary: Microsoft Azure Get Documentclassifiers tags: - documentClassifiers /documentClassifiers/{classifierId}: get: operationId: microsoftAzureDocumentclassifiersGetclassifier description: Gets detailed document classifier information. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: classifierId in: path description: Unique document classifier name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/DocumentClassifierDetails' 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/ErrorResponse' x-ms-examples: Get Document Classifier: $ref: ./examples/GetDocumentClassifier.json summary: Microsoft Azure Get Documentclassifiers Classifierid tags: - documentClassifiers delete: operationId: microsoftAzureDocumentclassifiersDeleteclassifier description: Deletes document classifier. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: classifierId in: path description: Unique document classifier name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '204': description: >- There is no content to send for this request, but the headers may be useful. 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/ErrorResponse' x-ms-examples: Delete Document Classifier: $ref: ./examples/DeleteDocumentClassifier.json summary: Microsoft Azure Delete Documentclassifiers Classifierid tags: - documentClassifiers /documentClassifiers/{classifierId}:analyze: post: operationId: microsoftAzureDocumentclassifiersClassifydocumentfromstream description: Classifies document with document classifier. consumes: - application/octet-stream - application/pdf - image/jpeg - image/png - image/tiff - image/bmp - image/heif - text/html - >- application/vnd.openxmlformats-officedocument.wordprocessingml.document - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet - >- application/vnd.openxmlformats-officedocument.presentationml.presentation parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.classifierId' - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.stringIndexType' - $ref: '#/parameters/DocumentClassifierAnalyzeRequestParams.split' - $ref: '#/parameters/AnalyzeFromStreamRequestParams.input' 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 AnalyzeResultOperation 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/ErrorResponse' x-ms-examples: Classify Document from Url: $ref: ./examples/ClassifyDocument_Stream.json x-ms-long-running-operation: true summary: Microsoft Azure Post Documentclassifiers Classifierid:analyze tags: - documentClassifiers /documentClassifiers/{classifierId}/analyzeResults/{resultId}: get: operationId: microsoftAzureDocumentclassifiersGetclassifyresult description: Gets the result of document classifier. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: classifierId in: path description: Unique document classifier name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - name: resultId in: path description: Analyze operation result ID. required: true type: string format: uuid responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/AnalyzeResultOperation' default: description: An unexpected error response. schema: $ref: '#/definitions/ErrorResponse' x-ms-examples: Get Classify Document Result: $ref: ./examples/GetClassifyDocumentResult.json summary: Microsoft Azure Get Documentclassifiers Classifierid Analyzeresults Resultid tags: - documentClassifiers /documentClassifiers:build: post: operationId: microsoftAzureDocumentclassifiersBuildclassifier description: Builds a custom document classifier. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: buildRequest in: body description: Build request parameters. required: true schema: $ref: '#/definitions/BuildDocumentClassifierRequest' 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 DocumentClassifierBuildOperationDetails 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/ErrorResponse' x-ms-examples: Build Document Classifier: $ref: ./examples/BuildDocumentClassifier.json x-ms-long-running-operation: true summary: Microsoft Azure Post Documentclassifiers:build tags: - documentClassifiers:build /documentModels: get: operationId: microsoftAzureDocumentmodelsListmodels description: List all document models parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/PagedDocumentModelDetails' 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/ErrorResponse' x-ms-examples: Get Document Models: $ref: ./examples/GetDocumentModels.json x-ms-pageable: nextLinkName: nextLink summary: Microsoft Azure Get Documentmodels tags: - documentModels /documentModels/{modelId}:analyze: post: operationId: microsoftAzureDocumentmodelsAnalyzedocumentfromstream description: Analyzes document with document model. consumes: - application/octet-stream - application/pdf - image/jpeg - image/png - image/tiff - image/bmp - image/heif - text/html - >- application/vnd.openxmlformats-officedocument.wordprocessingml.document - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet - >- application/vnd.openxmlformats-officedocument.presentationml.presentation 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/AnalyzeFromStreamRequestParams.input' 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 AnalyzeResultOperation 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/ErrorResponse' x-ms-examples: Analyze Document from Url: $ref: ./examples/AnalyzeDocument_Stream.json x-ms-long-running-operation: true summary: Microsoft Azure Post Documentmodels Modelid:analyze tags: - documentModels /documentModels/{modelId}: get: operationId: microsoftAzureDocumentmodelsGetmodel description: Gets detailed document model information. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: modelId in: path description: Unique document model name. required: true type: string pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/DocumentModelDetails' 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/ErrorResponse' x-ms-examples: Get Custom Document Model: $ref: ./examples/GetDocumentModel_Custom.json Get Prebuilt Document Model: $ref: ./examples/GetDocumentModel_Prebuilt.json summary: Microsoft Azure Get Documentmodels Modelid tags: - documentModels delete: operationId: microsoftAzureDocumentmodelsDeletemodel description: Deletes document model. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: modelId in: path description: Unique document model name. required: true type: string pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '204': description: >- There is no content to send for this request, but the headers may be useful. 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/ErrorResponse' x-ms-examples: Delete Document Model: $ref: ./examples/DeleteDocumentModel.json summary: Microsoft Azure Delete Documentmodels Modelid tags: - documentModels /documentModels/{modelId}:copyTo: post: operationId: microsoftAzureDocumentmodelsCopymodelto description: Copies document model to the target resource, region, and modelId. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: modelId in: path description: Unique document model name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - name: copyToRequest in: body description: Copy to request parameters. required: true schema: $ref: '#/definitions/CopyAuthorization' 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 DocumentModelCopyToOperationDetails 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/ErrorResponse' x-ms-examples: Copy Document Model To: $ref: ./examples/CopyDocumentModelTo.json x-ms-long-running-operation: true summary: Microsoft Azure Post Documentmodels Modelid:copyto tags: - documentModels /documentModels/{modelId}/analyzeResults/{resultId}: get: operationId: microsoftAzureDocumentmodelsGetanalyzeresult description: Gets the result of document analysis. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: modelId in: path description: Unique document model name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ - name: resultId in: path description: Analyze operation result ID. required: true type: string format: uuid responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/AnalyzeResultOperation' default: description: An unexpected error response. schema: $ref: '#/definitions/ErrorResponse' x-ms-examples: Get Analyze Document Result: $ref: ./examples/GetAnalyzeDocumentResult.json summary: Microsoft Azure Get Documentmodels Modelid Analyzeresults Resultid tags: - documentModels /documentModels:authorizeCopy: post: operationId: microsoftAzureDocumentmodelsAuthorizemodelcopy description: >- Generates authorization to copy a document model to this location with
specified modelId and optional description. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: authorizeCopyRequest in: body description: Authorize copy request parameters. required: true schema: $ref: '#/definitions/AuthorizeCopyRequest' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/CopyAuthorization' default: description: An unexpected error response. schema: $ref: '#/definitions/ErrorResponse' x-ms-examples: Authorize Copy of Document Model: $ref: ./examples/AuthorizeCopyDocumentModel.json summary: Microsoft Azure Post Documentmodels:authorizecopy tags: - documentModels:authorizeCopy /documentModels:build: post: operationId: microsoftAzureDocumentmodelsBuildmodel description: Builds a custom document analysis model. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - name: buildRequest in: body description: Build request parameters. required: true schema: $ref: '#/definitions/BuildDocumentModelRequest' 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 DocumentModelBuildOperationDetails 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/ErrorResponse' x-ms-examples: Build Document Model: $ref: ./examples/BuildDocumentModel.json x-ms-long-running-operation: true summary: Microsoft Azure Post Documentmodels:build tags: - documentModels:build /documentModels:compose: post: operationId: microsoftAzureDocumentmodelsComposemodel 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/ErrorResponse' x-ms-examples: Compose Document Model: $ref: ./examples/ComposeDocumentModel.json x-ms-long-running-operation: true summary: Microsoft Azure Post Documentmodels:compose tags: - documentModels:compose /info: get: operationId: microsoftAzureMiscellaneousoperationsGetresourceinfo description: Return information about the current resource. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/ResourceDetails' default: description: An unexpected error response. schema: $ref: '#/definitions/ErrorResponse' x-ms-examples: Get Resource Details: $ref: ./examples/GetResourceDetails.json summary: Microsoft Azure Get Info tags: - Info /operations: get: operationId: microsoftAzureMiscellaneousoperationsListoperations description: Lists all operations. parameters: - $ref: '#/parameters/Azure.Core.Foundations.ApiVersionParameter' - $ref: '#/parameters/Azure.Core.ClientRequestIdHeader' responses: '200': description: The request has succeeded. schema: $ref: '#/definitions/PagedOperationDetails' 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/ErrorResponse' x-ms-examples: Get Operations: $ref: ./examples/GetOperations.json x-ms-pageable: nextLinkName: nextLink summary: Microsoft Azure Get Operations tags: - Operations /operations/{operationId}: get: operationId: microsoftAzureMiscellaneousoperationsGetdocumentmodelbuildoperation 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/DocumentModelBuildOperationDetails' 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/ErrorResponse' x-ms-examples: Get Operation - Document Model Build: $ref: ./examples/GetOperation_DocumentModelBuild.json summary: Microsoft Azure Get Operations Operationid tags: - Operations 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' - 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 AnalyzeResultOperation 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/ErrorResponse' 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' - name: analyzeRequest in: body description: Analyze request parameters. required: false 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 AnalyzeResultOperation 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/ErrorResponse' 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=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/ErrorResponse' 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/ErrorResponse' x-ms-examples: Get Operation - Document Model Copy To: $ref: ./examples/GetOperation_DocumentModelCopyTo.json /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/ErrorResponse' x-ms-examples: Get Operation - Document Classifier Build: $ref: ./examples/GetOperation_DocumentClassifierBuild.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/OperationDetails' 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/ErrorResponse' x-ms-examples: Get Operation: $ref: ./examples/GetOperation.json definitions: AddressValue: type: object description: Address field value. properties: houseNumber: type: string description: House or building number. poBox: type: string description: Post office box number. road: type: string description: Street name. city: type: string description: Name of city, town, village, etc. state: type: string description: First-level administrative division. postalCode: type: string description: Postal code used for mail sorting. countryRegion: type: string description: Country/region. streetAddress: type: string description: >- Street-level address, excluding city, state, countryRegion, and postalCode. unit: type: string description: Apartment or office number cityDistrict: type: string description: >- Districts or boroughs within a city, such as Brooklyn in New York City or City of Westminster in London. stateDistrict: type: string description: Second-level administrative division used in certain locales. suburb: type: string description: Unofficial neighborhood name, like Chinatown. house: type: string description: Build name, such as World Trade Center. level: type: string description: Floor number, such as 3F. AnalyzeDocumentRequest: type: object description: Document analysis parameters. properties: urlSource: type: string format: uri description: >- Document URL to analyze. Either urlSource or base64Source must be specified. base64Source: type: string format: byte description: >- Base64 encoding of the document to analyze. Either urlSource or base64Source must be specified. AnalyzeResult: type: object description: Document analysis result. properties: apiVersion: type: string description: API version used to produce this result. modelId: type: string description: Document model ID used to produce this result. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ stringIndexType: $ref: '#/definitions/StringIndexType' description: Method used to compute string offset and length. contentFormat: $ref: '#/definitions/ContentFormat' description: Format of the analyze result top-level content. content: type: string description: >- Concatenate string representation of all textual and visual elements in reading order. pages: type: array description: Analyzed pages. items: $ref: '#/definitions/DocumentPage' x-ms-identifiers: [] paragraphs: type: array description: Extracted paragraphs. items: $ref: '#/definitions/DocumentParagraph' x-ms-identifiers: [] tables: type: array description: Extracted tables. items: $ref: '#/definitions/DocumentTable' x-ms-identifiers: [] figures: type: array description: Extracted figures. items: $ref: '#/definitions/DocumentFigure' x-ms-identifiers: [] lists: type: array description: Extracted lists. items: $ref: '#/definitions/DocumentList' x-ms-identifiers: [] sections: type: array description: Extracted sections. items: $ref: '#/definitions/DocumentSection' x-ms-identifiers: [] keyValuePairs: type: array description: Extracted key-value pairs. items: $ref: '#/definitions/DocumentKeyValuePair' x-ms-identifiers: [] styles: type: array description: Extracted font styles. items: $ref: '#/definitions/DocumentStyle' x-ms-identifiers: [] languages: type: array description: Detected languages. items: $ref: '#/definitions/DocumentLanguage' x-ms-identifiers: [] documents: type: array description: Extracted documents. items: $ref: '#/definitions/Document' x-ms-identifiers: [] required: - apiVersion - modelId - stringIndexType - content - pages AnalyzeResultOperation: type: object description: Status and result of the analyze operation. properties: status: $ref: '#/definitions/OperationStatus' description: Operation status. notStarted, running, succeeded, or failed createdDateTime: type: string format: date-time description: Date and time (UTC) when the analyze operation was submitted. lastUpdatedDateTime: type: string format: date-time description: Date and time (UTC) when the status was last updated. error: $ref: '#/definitions/Error' description: Encountered error during document analysis. analyzeResult: $ref: '#/definitions/AnalyzeResult' description: Document analysis result. required: - status - createdDateTime - lastUpdatedDateTime AuthorizeCopyRequest: type: object description: Request body to authorize document model copy. properties: modelId: type: string description: Unique document model name. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ description: type: string description: Document model description. maxLength: 4096 tags: type: object description: List of key-value tag attributes associated with the document model. additionalProperties: type: string required: - modelId AzureBlobContentSource: type: object description: Azure Blob Storage content. properties: containerUrl: type: string format: uri description: Azure Blob Storage container URL. prefix: type: string description: Blob name prefix. required: - containerUrl AzureBlobFileListContentSource: type: object description: File list in Azure Blob Storage. properties: containerUrl: type: string format: uri description: Azure Blob Storage container URL. fileList: type: string description: >- Path to a JSONL file within the container specifying a subset of documents. required: - containerUrl - fileList BoundingRegion: type: object description: Bounding polygon on a specific page of the input. properties: pageNumber: type: integer format: int32 description: 1-based page number of page containing the bounding region. minimum: 1 polygon: type: array description: >- Bounding polygon on the page, or the entire page if not specified. Coordinates specified relative to the top-left of the page. The numbers represent the x, y values of the polygon vertices, clockwise from the left (-180 degrees inclusive) relative to the element orientation. items: type: number format: float required: - pageNumber - polygon BuildDocumentClassifierRequest: type: object description: Request body to build a new custom document classifier. properties: classifierId: type: string description: Unique document classifier name. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ description: type: string description: Document classifier description. maxLength: 4096 baseClassifierId: type: string description: Base classifierId on top of which to train the classifier. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ docTypes: type: object description: List of document types to classify against. additionalProperties: $ref: '#/definitions/ClassifierDocumentTypeDetails' required: - classifierId - docTypes BuildDocumentModelRequest: type: object description: Request body to build a new custom document model. properties: modelId: type: string description: Unique document model name. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ description: type: string description: Document model description. maxLength: 4096 buildMode: $ref: '#/definitions/DocumentBuildMode' description: Custom document model build mode. azureBlobSource: $ref: '#/definitions/AzureBlobContentSource' description: |- Azure Blob Storage location containing the training data. Either azureBlobSource or azureBlobFileListSource must be specified. azureBlobFileListSource: $ref: '#/definitions/AzureBlobFileListContentSource' description: |- Azure Blob Storage file list specifying the training data. Either azureBlobSource or azureBlobFileListSource must be specified. tags: type: object description: List of key-value tag attributes associated with the document model. additionalProperties: type: string required: - modelId - buildMode ClassifierDocumentTypeDetails: type: object description: Classifier document type info. properties: sourceKind: $ref: '#/definitions/ContentSourceKind' description: Type of training data source. azureBlobSource: $ref: '#/definitions/AzureBlobContentSource' description: >- Azure Blob Storage location containing the training data for a classifier document type. Either azureBlobSource or azureBlobFileListSource must be specified. azureBlobFileListSource: $ref: '#/definitions/AzureBlobFileListContentSource' description: >- Azure Blob Storage file list specifying the training data for a classifier document type. Either azureBlobSource or azureBlobFileListSource must be specified. ClassifyDocumentRequest: type: object description: Document classification parameters. properties: urlSource: type: string format: uri description: >- Document URL to classify. Either urlSource or base64Source must be specified. base64Source: type: string format: byte description: >- Base64 encoding of the document to classify. Either urlSource or base64Source must be specified. ComponentDocumentModelDetails: type: object description: A component of a composed document model. properties: modelId: type: string description: Unique document model name. maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ required: - modelId 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 componentModels: type: array description: List of component document models to compose. items: $ref: '#/definitions/ComponentDocumentModelDetails' x-ms-identifiers: [] tags: type: object description: List of key-value tag attributes associated with the document model. additionalProperties: type: string required: - modelId - componentModels ContentFormat: type: string description: Format of the content in analyzed result. enum: - text - markdown x-ms-enum: name: ContentFormat modelAsString: true values: - name: text value: text description: >- Plain text representation of the document content without any formatting. - name: markdown value: markdown description: >- Markdown representation of the document content with section headings, tables, etc. ContentSourceKind: type: string description: Type of content source. enum: - url - base64 - azureBlob - azureBlobFileList x-ms-enum: name: ContentSourceKind modelAsString: true values: - name: url value: url description: Content at a specific URL. - name: base64 value: base64 description: Content represented via Base64 encoding. - name: azureBlob value: azureBlob description: Files in a path within an Azure Blob Storage container. - name: azureBlobFileList value: azureBlobFileList description: >- A file list specifying individual files in an Azure Blob Storage container. CopyAuthorization: type: object description: >- Authorization to copy a document model to the specified target resource and modelId. properties: targetResourceId: type: string description: >- ID of the target Azure resource where the document model should be copied to. x-ms-azure-resource: true targetResourceRegion: type: string description: >- Location of the target Azure resource where the document model should be copied to. targetModelId: type: string description: Identifier of the target document model. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ targetModelLocation: type: string format: uri description: URL of the copied document model in the target account. accessToken: type: string description: Token used to authorize the request. expirationDateTime: type: string format: date-time description: Date/time when the access token expires. required: - targetResourceId - targetResourceRegion - targetModelId - targetModelLocation - accessToken - expirationDateTime CurrencyValue: type: object description: Currency field value. properties: amount: type: number format: double description: Currency amount. currencySymbol: type: string description: Currency symbol label, if any. currencyCode: type: string description: Resolved currency code (ISO 4217), if any. required: - amount CustomDocumentModelsDetails: type: object description: Details regarding custom document models. properties: count: type: integer format: int32 description: Number of custom document models in the current resource. limit: type: integer format: int32 description: >- Maximum number of custom document models supported in the current resource. required: - count - limit Document: type: object description: An object describing the location and semantic content of a document. properties: docType: type: string description: Document type. minLength: 2 maxLength: 64 boundingRegions: type: array description: Bounding regions covering the document. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the document in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] fields: type: object description: Dictionary of named field values. additionalProperties: $ref: '#/definitions/DocumentField' confidence: type: number format: float description: Confidence of correctly extracting the document. minimum: 0 maximum: 1 required: - docType - spans - confidence DocumentBarcode: type: object description: A barcode object. properties: kind: $ref: '#/definitions/DocumentBarcodeKind' description: Barcode kind. value: type: string description: Barcode value. polygon: type: array description: >- Bounding polygon of the barcode, with coordinates specified relative to the top-left of the page. The numbers represent the x, y values of the polygon vertices, clockwise from the left (-180 degrees inclusive) relative to the element orientation. items: type: number format: float span: $ref: '#/definitions/DocumentSpan' description: Location of the barcode in the reading order concatenated content. confidence: type: number format: float description: Confidence of correctly extracting the barcode. minimum: 0 maximum: 1 required: - kind - value - span - confidence DocumentBarcodeKind: type: string description: Barcode kind. enum: - QRCode - PDF417 - UPCA - UPCE - Code39 - Code128 - EAN8 - EAN13 - DataBar - Code93 - Codabar - DataBarExpanded - ITF - MicroQRCode - Aztec - DataMatrix - MaxiCode x-ms-enum: name: DocumentBarcodeKind modelAsString: true values: - name: QRCode value: QRCode description: QR code, as defined in ISO/IEC 18004:2015. - name: PDF417 value: PDF417 description: PDF417, as defined in ISO 15438. - name: UPCA value: UPCA description: GS1 12-digit Universal Product Code. - name: UPCE value: UPCE description: GS1 6-digit Universal Product Code. - name: Code39 value: Code39 description: Code 39 barcode, as defined in ISO/IEC 16388:2007. - name: Code128 value: Code128 description: Code 128 barcode, as defined in ISO/IEC 15417:2007. - name: EAN8 value: EAN8 description: GS1 8-digit International Article Number (European Article Number). - name: EAN13 value: EAN13 description: GS1 13-digit International Article Number (European Article Number). - name: DataBar value: DataBar description: GS1 DataBar barcode. - name: Code93 value: Code93 description: Code 93 barcode, as defined in ANSI/AIM BC5-1995. - name: Codabar value: Codabar description: Codabar barcode, as defined in ANSI/AIM BC3-1995. - name: DataBarExpanded value: DataBarExpanded description: GS1 DataBar Expanded barcode. - name: ITF value: ITF description: Interleaved 2 of 5 barcode, as defined in ANSI/AIM BC2-1995. - name: MicroQRCode value: MicroQRCode description: Micro QR code, as defined in ISO/IEC 23941:2022. - name: Aztec value: Aztec description: Aztec code, as defined in ISO/IEC 24778:2008. - name: DataMatrix value: DataMatrix description: Data matrix code, as defined in ISO/IEC 16022:2006. - name: MaxiCode value: MaxiCode description: MaxiCode, as defined in ISO/IEC 16023:2000. 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. DocumentCaption: type: object description: A caption object describing a table or figure. properties: content: type: string description: Content of the caption. boundingRegions: type: array description: Bounding regions covering the caption. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the caption in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] elements: type: array description: Child elements of the caption. items: $ref: '#/definitions/DocumentElement' required: - content - spans DocumentClassifierBuildOperationDetails: type: object description: Get Operation response object. properties: result: $ref: '#/definitions/DocumentClassifierDetails' description: Operation result upon success. allOf: - $ref: '#/definitions/OperationDetails' x-ms-discriminator-value: documentClassifierBuild DocumentClassifierDetails: type: object description: Document classifier info. properties: classifierId: type: string description: Unique document classifier name. maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ x-ms-mutability: - read - create description: type: string description: Document classifier description. maxLength: 4096 createdDateTime: type: string format: date-time description: Date and time (UTC) when the document classifier was created. expirationDateTime: type: string format: date-time description: Date and time (UTC) when the document classifier will expire. apiVersion: type: string description: API version used to create this document classifier. baseClassifierId: type: string description: Base classifierId on top of which the classifier was trained. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ docTypes: type: object description: List of document types to classify against. additionalProperties: $ref: '#/definitions/ClassifierDocumentTypeDetails' warnings: type: array description: List of warnings encountered while building the classifier. items: $ref: '#/definitions/Warning' x-ms-identifiers: [] required: - classifierId - createdDateTime - apiVersion - docTypes DocumentElement: type: string description: |- An JSON pointer referencing an element of the document, such as paragraph, table, section, etc. DocumentField: type: object description: An object representing the content and location of a field value. properties: type: $ref: '#/definitions/DocumentFieldType' description: Data type of the field value. valueString: type: string description: String value. valueDate: type: string format: date description: Date value in YYYY-MM-DD format (ISO 8601). valueTime: type: string format: time description: Time value in hh:mm:ss format (ISO 8601). valuePhoneNumber: type: string description: Phone number value in E.164 format (ex. +19876543210). valueNumber: type: number format: double description: Floating point value. valueInteger: type: integer format: int64 description: Integer value. valueSelectionMark: $ref: '#/definitions/DocumentSelectionMarkState' description: Selection mark value. valueSignature: $ref: '#/definitions/DocumentSignatureType' description: Presence of signature. valueCountryRegion: type: string description: 3-letter country code value (ISO 3166-1 alpha-3). valueArray: type: array description: Array of field values. items: $ref: '#/definitions/DocumentField' x-ms-identifiers: [] valueObject: type: object description: Dictionary of named field values. additionalProperties: $ref: '#/definitions/DocumentField' valueCurrency: $ref: '#/definitions/CurrencyValue' description: Currency value. valueAddress: $ref: '#/definitions/AddressValue' description: Address value. valueBoolean: type: boolean description: Boolean value. valueSelectionGroup: type: array description: Selection group value. items: type: string content: type: string description: Field content. boundingRegions: type: array description: Bounding regions covering the field. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the field in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] confidence: type: number format: float description: Confidence of correctly extracting the field. minimum: 0 maximum: 1 required: - type 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 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. DocumentFigure: type: object description: An object representing a figure in the document. properties: boundingRegions: type: array description: Bounding regions covering the figure. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the figure in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] elements: type: array description: Child elements of the figure, excluding any caption or footnotes. items: $ref: '#/definitions/DocumentElement' caption: $ref: '#/definitions/DocumentCaption' description: Caption associated with the figure. footnotes: type: array description: List of footnotes associated with the figure. items: $ref: '#/definitions/DocumentFootnote' x-ms-identifiers: [] required: - spans DocumentFootnote: type: object description: A footnote object describing a table or figure. properties: content: type: string description: Content of the footnote. boundingRegions: type: array description: Bounding regions covering the footnote. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the footnote in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] elements: type: array description: Child elements of the footnote. items: $ref: '#/definitions/DocumentElement' required: - content - spans DocumentFormula: type: object description: A formula object. properties: kind: $ref: '#/definitions/DocumentFormulaKind' description: Formula kind. value: type: string description: LaTex expression describing the formula. polygon: type: array description: >- Bounding polygon of the formula, with coordinates specified relative to the top-left of the page. The numbers represent the x, y values of the polygon vertices, clockwise from the left (-180 degrees inclusive) relative to the element orientation. items: type: number format: float span: $ref: '#/definitions/DocumentSpan' description: Location of the formula in the reading order concatenated content. confidence: type: number format: float description: Confidence of correctly extracting the formula. minimum: 0 maximum: 1 required: - kind - value - span - confidence DocumentFormulaKind: type: string description: Formula kind. enum: - inline - display x-ms-enum: name: DocumentFormulaKind modelAsString: true values: - name: inline value: inline description: A formula embedded within the content of a paragraph. - name: display value: display description: A formula in display mode that takes up an entire line. DocumentKeyValueElement: type: object description: An object representing the field key or value in a key-value pair. properties: content: type: string description: Concatenated content of the key-value element in reading order. boundingRegions: type: array description: Bounding regions covering the key-value element. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: >- Location of the key-value element in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] required: - content - spans DocumentKeyValuePair: type: object description: >- An object representing a form field with distinct field label (key) and field value (may be empty). properties: key: $ref: '#/definitions/DocumentKeyValueElement' description: Field label of the key-value pair. value: $ref: '#/definitions/DocumentKeyValueElement' description: Field value of the key-value pair. confidence: type: number format: float description: Confidence of correctly extracting the key-value pair. minimum: 0 maximum: 1 required: - key - confidence DocumentLanguage: type: object description: An object representing the detected language for a given text span. properties: locale: type: string description: >- Detected language. Value may an ISO 639-1 language code (ex. "en", "fr") or BCP 47 language tag (ex. "zh-Hans"). spans: type: array description: >- Location of the text elements in the concatenated content the language applies to. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] confidence: type: number format: float description: Confidence of correctly identifying the language. minimum: 0 maximum: 1 required: - locale - spans - confidence DocumentLine: type: object description: >- A content line object consisting of an adjacent sequence of content elements, such as words and selection marks. properties: content: type: string description: Concatenated content of the contained elements in reading order. polygon: type: array description: >- Bounding polygon of the line, with coordinates specified relative to the top-left of the page. The numbers represent the x, y values of the polygon vertices, clockwise from the left (-180 degrees inclusive) relative to the element orientation. items: type: number format: float spans: type: array description: Location of the line in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] required: - content - spans DocumentList: type: object description: An object representing a list in the document. properties: spans: type: array description: Location of the list in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] items: type: array description: Items in the list. items: $ref: '#/definitions/DocumentListItem' x-ms-identifiers: [] required: - spans - items DocumentListItem: type: object description: An object representing a list item in the document. properties: level: type: integer format: int32 description: Level of the list item (1-indexed). minimum: 1 content: type: string description: Content of the list item. boundingRegions: type: array description: Bounding regions covering the list item. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the list item in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] elements: type: array description: Child elements of the list item. items: $ref: '#/definitions/DocumentElement' required: - level - content - spans DocumentModelBuildOperationDetails: type: object description: Get Operation response object. properties: result: $ref: '#/definitions/DocumentModelDetails' description: Operation result upon success. allOf: - $ref: '#/definitions/OperationDetails' x-ms-discriminator-value: documentModelBuild DocumentModelComposeOperationDetails: type: object description: Get Operation response object. properties: result: $ref: '#/definitions/DocumentModelDetails' description: Operation result upon success. allOf: - $ref: '#/definitions/OperationDetails' x-ms-discriminator-value: documentModelCompose DocumentModelCopyToOperationDetails: type: object description: Get Operation response object. properties: result: $ref: '#/definitions/DocumentModelDetails' description: Operation result upon success. allOf: - $ref: '#/definitions/OperationDetails' x-ms-discriminator-value: documentModelCopyTo DocumentModelDetails: type: object description: Document model info. properties: modelId: type: string description: Unique document model name. pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ x-ms-mutability: - read - create description: type: string description: Document model description. maxLength: 4096 createdDateTime: type: string format: date-time description: Date and time (UTC) when the document model was created. expirationDateTime: type: string format: date-time description: Date and time (UTC) when the document model will expire. apiVersion: type: string description: API version used to create this document model. tags: type: object description: List of key-value tag attributes associated with the document model. additionalProperties: type: string buildMode: $ref: '#/definitions/DocumentBuildMode' description: Custom document model build mode. azureBlobSource: $ref: '#/definitions/AzureBlobContentSource' description: |- Azure Blob Storage location containing the training data. Either azureBlobSource or azureBlobFileListSource must be specified. azureBlobFileListSource: $ref: '#/definitions/AzureBlobFileListContentSource' description: |- Azure Blob Storage file list specifying the training data. Either azureBlobSource or azureBlobFileListSource must be specified. docTypes: type: object description: Supported document types. additionalProperties: $ref: '#/definitions/DocumentTypeDetails' warnings: type: array description: List of warnings encountered while building the model. items: $ref: '#/definitions/Warning' x-ms-identifiers: [] required: - modelId - createdDateTime DocumentPage: type: object description: Content and layout elements extracted from a page from the input. properties: pageNumber: type: integer format: int32 description: 1-based page number in the input document. minimum: 1 angle: type: number format: float description: >- The general orientation of the content in clockwise direction, measured in degrees between (-180, 180]. maximum: 180 width: type: number format: float description: The width of the image/PDF in pixels/inches, respectively. minimum: 0 height: type: number format: float description: The height of the image/PDF in pixels/inches, respectively. minimum: 0 unit: $ref: '#/definitions/LengthUnit' description: >- The unit used by the width, height, and polygon properties. For images, the unit is "pixel". For PDF, the unit is "inch". spans: type: array description: Location of the page in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] words: type: array description: Extracted words from the page. items: $ref: '#/definitions/DocumentWord' x-ms-identifiers: [] selectionMarks: type: array description: Extracted selection marks from the page. items: $ref: '#/definitions/DocumentSelectionMark' x-ms-identifiers: [] lines: type: array description: >- Extracted lines from the page, potentially containing both textual and visual elements. items: $ref: '#/definitions/DocumentLine' x-ms-identifiers: [] barcodes: type: array description: Extracted barcodes from the page. items: $ref: '#/definitions/DocumentBarcode' x-ms-identifiers: [] formulas: type: array description: Extracted formulas from the page. items: $ref: '#/definitions/DocumentFormula' x-ms-identifiers: [] required: - pageNumber - spans DocumentParagraph: type: object description: |- A paragraph object consisting with contiguous lines generally with common alignment and spacing. properties: role: $ref: '#/definitions/ParagraphRole' description: Semantic role of the paragraph. content: type: string description: Concatenated content of the paragraph in reading order. boundingRegions: type: array description: Bounding regions covering the paragraph. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the paragraph in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] required: - content - spans DocumentSection: type: object description: An object representing a section in the document. properties: spans: type: array description: Location of the section in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] elements: type: array description: Child elements of the section. items: $ref: '#/definitions/DocumentElement' required: - spans DocumentSelectionMark: type: object description: |- A selection mark object representing check boxes, radio buttons, and other elements indicating a selection. properties: state: $ref: '#/definitions/DocumentSelectionMarkState' description: State of the selection mark. polygon: type: array description: >- Bounding polygon of the selection mark, with coordinates specified relative to the top-left of the page. The numbers represent the x, y values of the polygon vertices, clockwise from the left (-180 degrees inclusive) relative to the element orientation. items: type: number format: float span: $ref: '#/definitions/DocumentSpan' description: >- Location of the selection mark in the reading order concatenated content. confidence: type: number format: float description: Confidence of correctly extracting the selection mark. minimum: 0 maximum: 1 required: - state - span - confidence DocumentSelectionMarkState: type: string description: State of the selection mark. enum: - selected - unselected x-ms-enum: name: DocumentSelectionMarkState modelAsString: true values: - name: selected value: selected description: >- The selection mark is selected, often indicated by a check ✓ or cross X inside the selection mark. - name: unselected value: unselected description: The selection mark is not selected. DocumentSignatureType: type: string description: Presence of signature. enum: - signed - unsigned x-ms-enum: name: DocumentSignatureType modelAsString: true values: - name: signed value: signed description: A signature is detected. - name: unsigned value: unsigned description: No signatures are detected. DocumentSpan: type: object description: >- Contiguous region of the concatenated content property, specified as an offset and length. properties: offset: type: integer format: int32 description: Zero-based index of the content represented by the span. minimum: 0 length: type: integer format: int32 description: Number of characters in the content represented by the span. minimum: 0 required: - offset - length DocumentStyle: type: object description: An object representing observed text styles. properties: isHandwritten: type: boolean description: Is content handwritten? similarFontFamily: type: string description: >- Visually most similar font from among the set of supported font families, with fallback fonts following CSS convention (ex. 'Arial, sans-serif'). fontStyle: $ref: '#/definitions/FontStyle' description: Font style. fontWeight: $ref: '#/definitions/FontWeight' description: Font weight. color: type: string description: 'Foreground color in #rrggbb hexadecimal format.' pattern: ^#[0-9a-f]{6}$ backgroundColor: type: string description: 'Background color in #rrggbb hexadecimal format..' pattern: ^#[0-9a-f]{6}$ spans: type: array description: >- Location of the text elements in the concatenated content the style applies to. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] confidence: type: number format: float description: Confidence of correctly identifying the style. minimum: 0 maximum: 1 required: - spans - confidence DocumentTable: type: object description: A table object consisting table cells arranged in a rectangular layout. properties: rowCount: type: integer format: int32 description: Number of rows in the table. minimum: 1 columnCount: type: integer format: int32 description: Number of columns in the table. minimum: 1 cells: type: array description: Cells contained within the table. items: $ref: '#/definitions/DocumentTableCell' x-ms-identifiers: [] boundingRegions: type: array description: Bounding regions covering the table. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the table in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] caption: $ref: '#/definitions/DocumentCaption' description: Caption associated with the table. footnotes: type: array description: List of footnotes associated with the table. items: $ref: '#/definitions/DocumentFootnote' x-ms-identifiers: [] required: - rowCount - columnCount - cells - spans DocumentTableCell: type: object description: An object representing the location and content of a table cell. properties: kind: type: string description: Table cell kind. default: content enum: - content - rowHeader - columnHeader - stubHead - description x-ms-enum: name: DocumentTableCellKind modelAsString: true values: - name: content value: content description: Contains the main content/data. - name: rowHeader value: rowHeader description: Describes the content of the row. - name: columnHeader value: columnHeader description: Describes the content of the column. - name: stubHead value: stubHead description: >- Describes the row headers, usually located at the top left corner of a table. - name: description value: description description: Describes the content in (parts of) the table. rowIndex: type: integer format: int32 description: Row index of the cell. columnIndex: type: integer format: int32 description: Column index of the cell. rowSpan: type: integer format: int32 description: Number of rows spanned by this cell. default: 1 minimum: 1 columnSpan: type: integer format: int32 description: Number of columns spanned by this cell. default: 1 minimum: 1 content: type: string description: Concatenated content of the table cell in reading order. boundingRegions: type: array description: Bounding regions covering the table cell. items: $ref: '#/definitions/BoundingRegion' x-ms-identifiers: [] spans: type: array description: Location of the table cell in the reading order concatenated content. items: $ref: '#/definitions/DocumentSpan' x-ms-identifiers: [] elements: type: array description: Child elements of the table cell. items: $ref: '#/definitions/DocumentElement' required: - rowIndex - columnIndex - content - spans 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 required: - fieldSchema DocumentWord: type: object description: >- A word object consisting of a contiguous sequence of characters. For non-space delimited languages, such as Chinese, Japanese, and Korean, each character is represented as its own word. properties: content: type: string description: Text content of the word. polygon: type: array description: >- Bounding polygon of the word, with coordinates specified relative to the top-left of the page. The numbers represent the x, y values of the polygon vertices, clockwise from the left (-180 degrees inclusive) relative to the element orientation. items: type: number format: float span: $ref: '#/definitions/DocumentSpan' description: Location of the word in the reading order concatenated content. confidence: type: number format: float description: Confidence of correctly extracting the word. minimum: 0 maximum: 1 required: - content - span - confidence Error: 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/Error' x-ms-identifiers: [] innererror: $ref: '#/definitions/InnerError' description: >- An object containing more specific information than the current object about the error. required: - code - message ErrorResponse: type: object description: Error response object. properties: error: $ref: '#/definitions/Error' description: Error info. required: - error FontStyle: type: string description: Font style. enum: - normal - italic x-ms-enum: name: FontStyle modelAsString: true values: - name: normal value: normal description: Characters are represented normally. - name: italic value: italic description: Characters are visually slanted to the right. FontWeight: type: string description: Font weight. enum: - normal - bold x-ms-enum: name: FontWeight modelAsString: true values: - name: normal value: normal description: Characters are represented normally. - name: bold value: bold description: Characters are represented with thicker strokes. InnerError: 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/InnerError' description: Inner error. LengthUnit: type: string description: >- The unit used by the width, height, and polygon properties. For images, the unit is "pixel". For PDF, the unit is "inch". enum: - pixel - inch x-ms-enum: name: LengthUnit modelAsString: true values: - name: pixel value: pixel description: Length unit for image files. - name: inch value: inch description: Length unit for PDF files. OperationDetails: type: object description: Operation info. properties: operationId: type: string description: Operation ID x-ms-mutability: - read - create status: $ref: '#/definitions/OperationStatus' description: Operation status. notStarted, running, completed, or failed percentCompleted: type: integer format: int32 description: Operation progress (0-100). minimum: 0 maximum: 100 createdDateTime: type: string format: date-time description: Date and time (UTC) when the operation was created. lastUpdatedDateTime: type: string format: date-time description: Date and time (UTC) when the status was last updated. kind: $ref: '#/definitions/OperationKind' description: Type of operation. resourceLocation: type: string format: uri description: URL of the resource targeted by this operation. apiVersion: type: string description: API version used to create this operation. tags: type: object description: List of key-value tag attributes associated with the document model. additionalProperties: type: string error: $ref: '#/definitions/Error' description: Encountered error. discriminator: kind required: - operationId - status - createdDateTime - lastUpdatedDateTime - kind - resourceLocation OperationKind: type: string description: Type of operation. enum: - documentModelBuild - documentModelCompose - documentModelCopyTo - documentClassifierBuild x-ms-enum: name: OperationKind modelAsString: true values: - name: documentModelBuild value: documentModelBuild description: Build a new custom document model. - name: documentModelCompose value: documentModelCompose description: Compose a new custom document model from existing models. - name: documentModelCopyTo value: documentModelCopyTo description: >- Copy an existing document model to potentially a different resource, region, or subscription. - name: documentClassifierBuild value: documentClassifierBuild description: Build a new custom classifier model. OperationStatus: type: string description: Operation status. enum: - notStarted - running - failed - succeeded - completed - canceled x-ms-enum: name: OperationStatus modelAsString: true values: - name: notStarted value: notStarted description: The operation has not started yet. - name: running value: running description: The operation is in progress. - name: failed value: failed description: The operation has failed. - name: succeeded value: succeeded description: The operation has succeeded. - name: completed value: completed description: The operation has completed. - name: canceled value: canceled description: The operation has been canceled. PagedDocumentClassifierDetails: type: object description: Paged collection of DocumentClassifierDetails items properties: value: type: array description: The DocumentClassifierDetails items on this page items: $ref: '#/definitions/DocumentClassifierDetails' x-ms-identifiers: [] nextLink: type: string format: uri description: The link to the next page of items required: - value PagedDocumentModelDetails: type: object description: Paged collection of DocumentModelDetails items properties: value: type: array description: The DocumentModelDetails items on this page items: $ref: '#/definitions/DocumentModelDetails' x-ms-identifiers: [] nextLink: type: string format: uri description: The link to the next page of items required: - value PagedOperationDetails: type: object description: Paged collection of OperationDetails items properties: value: type: array description: The OperationDetails items on this page items: $ref: '#/definitions/OperationDetails' x-ms-identifiers: [] nextLink: type: string format: uri description: The link to the next page of items required: - value ParagraphRole: type: string description: Semantic role of the paragraph. enum: - pageHeader - pageFooter - pageNumber - title - sectionHeading - footnote - formulaBlock x-ms-enum: name: ParagraphRole modelAsString: true values: - name: pageHeader value: pageHeader description: Text near the top edge of the page. - name: pageFooter value: pageFooter description: Text near the bottom edge of the page. - name: pageNumber value: pageNumber description: Page number. - name: title value: title description: Top-level title describing the entire document. - name: sectionHeading value: sectionHeading description: Sub heading describing a section of the document. - name: footnote value: footnote description: A note usually placed after the main content on a page. - name: formulaBlock value: formulaBlock description: A block of formulas, often with shared alignment. QuotaDetails: type: object description: Quota used, limit, and next reset date/time. properties: used: type: integer format: int32 description: Amount of the resource quota used. quota: type: integer format: int32 description: Resource quota limit. quotaResetDateTime: type: string format: date-time description: Date/time when the resource quota usage will be reset. required: - used - quota - quotaResetDateTime ResourceDetails: type: object description: General information regarding the current resource. properties: customDocumentModels: $ref: '#/definitions/CustomDocumentModelsDetails' description: Details regarding custom document models. customNeuralDocumentModelBuilds: $ref: '#/definitions/QuotaDetails' description: Quota used, limit, and next reset date/time. required: - customDocumentModels - customNeuralDocumentModelBuilds StringIndexType: type: string description: Method used to compute string offset and length. enum: - textElements - unicodeCodePoint - utf16CodeUnit x-ms-enum: name: StringIndexType modelAsString: true values: - name: textElements value: textElements description: >- User-perceived display character, or grapheme cluster, as defined by Unicode 8.0.0. - name: unicodeCodePoint value: unicodeCodePoint description: >- Character unit represented by a single unicode code point. Used by Python 3. - name: utf16CodeUnit value: utf16CodeUnit description: >- Character unit represented by a 16-bit Unicode code unit. Used by JavaScript, Java, and .NET. Warning: type: object description: The error object. properties: code: type: string description: One of a server-defined set of warning codes. message: type: string description: A human-readable representation of the warning. target: type: string description: The target of the error. required: - code - message parameters: AnalyzeFromStreamRequestParams.input: name: input in: body description: Input content. required: true schema: type: string format: binary x-ms-parameter-location: method Azure.Core.ClientRequestIdHeader: name: x-ms-client-request-id in: header description: >- An opaque, globally-unique, client-generated string identifier for the request. required: false type: string format: uuid x-ms-parameter-location: method x-ms-client-name: clientRequestId 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 DocumentClassifierAnalyzeRequestParams.classifierId: name: classifierId in: path description: Unique document classifier name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ x-ms-parameter-location: method DocumentClassifierAnalyzeRequestParams.split: name: split in: query description: Document splitting mode. required: false type: string 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. x-ms-parameter-location: method DocumentClassifierAnalyzeRequestParams.stringIndexType: name: stringIndexType in: query description: Method used to compute string offset and length. required: false type: string default: textElements enum: - textElements - unicodeCodePoint - utf16CodeUnit x-ms-enum: name: StringIndexType modelAsString: true values: - name: textElements value: textElements description: >- User-perceived display character, or grapheme cluster, as defined by Unicode 8.0.0. - name: unicodeCodePoint value: unicodeCodePoint description: >- Character unit represented by a single unicode code point. Used by Python 3. - name: utf16CodeUnit value: utf16CodeUnit description: >- Character unit represented by a 16-bit Unicode code unit. Used by JavaScript, Java, and .NET. x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.features: name: features in: query description: List of optional analysis features. required: false type: array items: type: string 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. collectionFormat: csv x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.locale: name: locale in: query description: >- Locale hint for text recognition and document analysis. Value may contain only the language code (ex. "en", "fr") or BCP 47 language tag (ex. "en-US"). required: false type: string x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.modelId: name: modelId in: path description: Unique document model name. required: true type: string maxLength: 64 pattern: ^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$ x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.outputContentFormat: name: outputContentFormat in: query description: Format of the analyze result top-level content. required: false type: string default: text enum: - text - markdown x-ms-enum: name: ContentFormat modelAsString: true values: - name: text value: text description: >- Plain text representation of the document content without any formatting. - name: markdown value: markdown description: >- Markdown representation of the document content with section headings, tables, etc. x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.pages: name: pages in: query description: List of 1-based page numbers to analyze. Ex. "1-3,5,7-9" required: false type: string pattern: ^(\d+(-\d+)?)(,\s*(\d+(-\d+)?))*$ x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.queryFields: name: queryFields in: query description: List of additional fields to extract. Ex. "NumberOfGuests,StoreNumber" required: false type: array items: type: string collectionFormat: csv x-ms-parameter-location: method DocumentModelAnalyzeRequestParams.stringIndexType: name: stringIndexType in: query description: Method used to compute string offset and length. required: false type: string default: textElements enum: - textElements - unicodeCodePoint - utf16CodeUnit x-ms-enum: name: StringIndexType modelAsString: true values: - name: textElements value: textElements description: >- User-perceived display character, or grapheme cluster, as defined by Unicode 8.0.0. - name: unicodeCodePoint value: unicodeCodePoint description: >- Character unit represented by a single unicode code point. Used by Python 3. - name: utf16CodeUnit value: utf16CodeUnit description: >- Character unit represented by a 16-bit Unicode code unit. Used by JavaScript, Java, and .NET. x-ms-parameter-location: method