{ "swagger": "2.0", "info": { "title": "Content Understanding", "version": "2025-11-01", "description": "The Content Understanding service extracts content and fields from multimodal input.", "x-typespec-generated": [ { "emitter": "@azure-tools/typespec-autorest" } ] }, "schemes": [ "https" ], "x-ms-parameterized-host": { "hostTemplate": "{endpoint}/contentunderstanding", "useSchemePrefix": false, "parameters": [ { "name": "endpoint", "in": "path", "description": "Content Understanding service endpoint.", "required": true, "type": "string", "format": "uri", "x-ms-skip-url-encoding": true } ] }, "produces": [ "application/json" ], "consumes": [ "application/json" ], "security": [ { "AzureKey": [] }, { "EntraIdToken": [ "https://cognitiveservices.azure.com/.default" ] } ], "securityDefinitions": { "AzureKey": { "type": "apiKey", "description": "Key-based authentication using the access key of the Azure resource.", "name": "Ocp-Apim-Subscription-Key", "in": "header" }, "EntraIdToken": { "type": "oauth2", "description": "Microsoft Entra ID OAuth2 authentication using an access token.", "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": [], "paths": { "/analyzerResults/{operationId}": { "get": { "operationId": "ContentAnalyzers_GetResult", "description": "Get the result of an analysis operation.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "operationId", "in": "path", "description": "The unique ID of the operation.", "required": true, "type": "string" } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentAnalyzerAnalyzeOperationStatus" } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Get Analysis Result": { "$ref": "./examples/ContentAnalyzers_GetResult.json" } } }, "delete": { "operationId": "ContentAnalyzers_DeleteResult", "description": "Mark the result of an analysis operation for deletion.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "operationId", "in": "path", "description": "Operation identifier.", "required": true, "type": "string" } ], "responses": { "204": { "description": "There is no content to send for this request, but the headers may be useful." }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Delete Analyzer Result": { "$ref": "./examples/ContentAnalyzers_DeleteResult.json" } } } }, "/analyzerResults/{operationId}/files/{path}": { "get": { "operationId": "ContentAnalyzers_GetResultFile", "description": "Get a file associated with the result of an analysis operation.", "produces": [ "*/*", "application/json" ], "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "operationId", "in": "path", "description": "Operation identifier.", "required": true, "type": "string" }, { "name": "path", "in": "path", "description": "File path.", "required": true, "type": "string", "x-ms-skip-url-encoding": true } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "type": "file" } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Get Analysis Result File": { "$ref": "./examples/ContentAnalyzers_GetResultFile.json" } } } }, "/analyzers": { "get": { "operationId": "ContentAnalyzers_List", "description": "List analyzers.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/PagedContentAnalyzer" }, "headers": { "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "List Analyzers": { "$ref": "./examples/ContentAnalyzers_List.json" } }, "x-ms-pageable": { "nextLinkName": "nextLink" } } }, "/analyzers/{analyzerId}": { "get": { "operationId": "ContentAnalyzers_Get", "description": "Get analyzer properties.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentAnalyzer" }, "headers": { "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Get Analyzer": { "$ref": "./examples/ContentAnalyzers_GetAnalyzer.json" } } }, "put": { "operationId": "ContentAnalyzers_CreateOrReplace", "description": "Create a new analyzer asynchronously.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "name": "allowReplace", "in": "query", "description": "Allow the operation to replace an existing resource.", "required": false, "type": "boolean", "default": false }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" }, { "name": "resource", "in": "body", "description": "The resource instance.", "required": true, "schema": { "$ref": "#/definitions/ContentAnalyzer" } } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentAnalyzer" }, "headers": { "Operation-Location": { "type": "string", "format": "uri", "description": "The location for monitoring the operation state." }, "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "201": { "description": "The request has succeeded and a new resource has been created as a result.", "schema": { "$ref": "#/definitions/ContentAnalyzer" }, "headers": { "Operation-Location": { "type": "string", "format": "uri", "description": "The location for monitoring the operation state." }, "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Create or Replace Analyzer": { "$ref": "./examples/ContentAnalyzers_CreateOrReplace.json" } }, "x-ms-long-running-operation": true }, "patch": { "operationId": "ContentAnalyzers_Update", "description": "Update analyzer properties.", "consumes": [ "application/merge-patch+json" ], "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" }, { "name": "resource", "in": "body", "description": "The resource instance.", "required": true, "schema": { "$ref": "#/definitions/ContentAnalyzerUpdate" } } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentAnalyzer" }, "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": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Update Analyzer": { "$ref": "./examples/ContentAnalyzers_Update.json" } } }, "delete": { "operationId": "ContentAnalyzers_Delete", "description": "Delete analyzer.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" } ], "responses": { "204": { "description": "There is no content to send for this request, but the headers may be useful. ", "headers": { "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Delete Analyzer": { "$ref": "./examples/ContentAnalyzers_DeleteAnalyzer.json" } } } }, "/analyzers/{analyzerId}:analyze": { "post": { "operationId": "ContentAnalyzers_Analyze", "description": "Extract content and fields from input.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "$ref": "#/parameters/AnalyzeParameters.stringEncoding" }, { "$ref": "#/parameters/AnalyzeParameters.processingLocation" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" }, { "name": "body", "in": "body", "required": true, "schema": { "$ref": "#/definitions/AnalyzeRequest" } } ], "responses": { "202": { "description": "The request has been accepted for processing, but processing has not yet completed.", "schema": { "$ref": "#/definitions/ContentAnalyzerAnalyzeOperationStatus" }, "headers": { "Operation-Location": { "type": "string", "format": "uri", "description": "The location for monitoring the operation state." }, "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": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Analyze URL": { "$ref": "./examples/ContentAnalyzers_Analyze.json" } }, "x-ms-long-running-operation": true } }, "/analyzers/{analyzerId}:analyzeBinary": { "post": { "operationId": "ContentAnalyzers_AnalyzeBinary", "description": "Extract content and fields from input.", "consumes": [ "*/*" ], "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "$ref": "#/parameters/AnalyzeParameters.stringEncoding" }, { "$ref": "#/parameters/AnalyzeParameters.processingLocation" }, { "$ref": "#/parameters/AnalyzeBinaryRequest.range" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" }, { "$ref": "#/parameters/AnalyzeBinaryRequest.input" } ], "responses": { "202": { "description": "The request has been accepted for processing, but processing has not yet completed.", "schema": { "$ref": "#/definitions/ContentAnalyzerAnalyzeOperationStatus" }, "headers": { "Operation-Location": { "type": "string", "format": "uri", "description": "The location for monitoring the operation state." }, "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": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Analyze File": { "$ref": "./examples/ContentAnalyzers_AnalyzeBinary.json" } }, "x-ms-long-running-operation": true } }, "/analyzers/{analyzerId}:copy": { "post": { "operationId": "ContentAnalyzers_Copy", "description": "Create a copy of the source analyzer to the current location.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "name": "allowReplace", "in": "query", "description": "Allow the operation to replace an existing resource.", "required": false, "type": "boolean", "default": false }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" }, { "name": "body", "in": "body", "required": true, "schema": { "$ref": "#/definitions/CopyRequest" } } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentAnalyzer" }, "headers": { "Operation-Location": { "type": "string", "format": "uri", "description": "The location for monitoring the operation state." }, "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "201": { "description": "The request has succeeded and a new resource has been created as a result.", "schema": { "$ref": "#/definitions/ContentAnalyzer" }, "headers": { "Operation-Location": { "type": "string", "format": "uri", "description": "The location for monitoring the operation state." }, "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": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Copy Analyzer": { "$ref": "./examples/ContentAnalyzers_Copy.json" } }, "x-ms-long-running-operation": true } }, "/analyzers/{analyzerId}:grantCopyAuthorization": { "post": { "operationId": "ContentAnalyzers_GrantCopyAuthorization", "description": "Get authorization for copying this analyzer to another location.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "$ref": "#/parameters/Azure.Core.ClientRequestIdHeader" }, { "name": "body", "in": "body", "required": true, "schema": { "$ref": "#/definitions/GrantCopyAuthorizationRequest" } } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/CopyAuthorization" }, "headers": { "x-ms-client-request-id": { "type": "string", "format": "uuid", "description": "An opaque, globally-unique, client-generated string identifier for the request." } } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Grant Copy Authorization": { "$ref": "./examples/ContentAnalyzers_GrantCopyAuthorization.json" } } } }, "/analyzers/{analyzerId}/operations/{operationId}": { "get": { "operationId": "ContentAnalyzers_GetOperationStatus", "description": "Get the status of an analyzer creation operation.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "analyzerId", "in": "path", "description": "The unique identifier of the analyzer.", "required": true, "type": "string", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, { "name": "operationId", "in": "path", "description": "The unique ID of the operation.", "required": true, "type": "string" } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentAnalyzerOperationStatus" } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Get Analyzer Operation Status": { "$ref": "./examples/ContentAnalyzers_GetOperationStatus.json" } } } }, "/defaults": { "get": { "operationId": "ContentAnalyzers_GetDefaults", "description": "Return default settings for this Content Understanding resource.", "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentUnderstandingDefaults" } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Get Defaults": { "$ref": "./examples/ContentAnalyzers_GetDefaults.json" } } }, "patch": { "operationId": "ContentAnalyzers_UpdateDefaults", "description": "Update default settings for this Content Understanding resource.", "consumes": [ "application/merge-patch+json" ], "parameters": [ { "$ref": "#/parameters/Azure.Core.Foundations.ApiVersionParameter" }, { "name": "body", "in": "body", "required": true, "schema": { "$ref": "#/definitions/ContentUnderstandingDefaultsMergePatchUpdate" } } ], "responses": { "200": { "description": "The request has succeeded.", "schema": { "$ref": "#/definitions/ContentUnderstandingDefaults" } }, "default": { "description": "An unexpected error response.", "schema": { "$ref": "#/definitions/Azure.Core.Foundations.ErrorResponse" }, "headers": { "x-ms-error-code": { "type": "string", "description": "String error code indicating what went wrong." } } } }, "x-ms-examples": { "Update Defaults": { "$ref": "./examples/ContentAnalyzers_UpdateDefaults.json" } } } } }, "definitions": { "AnalysisContent": { "type": "object", "description": "Media content base class.", "properties": { "kind": { "$ref": "#/definitions/AnalysisContentKind", "description": "Content kind." }, "mimeType": { "type": "string", "description": "Detected MIME type of the content. Ex. application/pdf, image/jpeg, etc." }, "analyzerId": { "type": "string", "description": "The analyzer that generated this content.", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, "category": { "type": "string", "description": "Classified content category." }, "path": { "type": "string", "description": "The path of the content in the input." }, "markdown": { "type": "string", "description": "Markdown representation of the content." }, "fields": { "type": "object", "description": "Extracted fields from the content.", "additionalProperties": { "$ref": "#/definitions/ContentField" } } }, "discriminator": "kind", "required": [ "kind", "mimeType" ] }, "AnalysisContentKind": { "type": "string", "description": "Kind of media content.", "enum": [ "document", "audioVisual" ], "x-ms-enum": { "name": "AnalysisContentKind", "modelAsString": true, "values": [ { "name": "document", "value": "document", "description": "Document content, such as pdf, image, txt, etc." }, { "name": "audioVisual", "value": "audioVisual", "description": "Audio visual content, such as mp3, mp4, etc." } ] } }, "AnalysisInput": { "type": "object", "description": "Additional input to analyze.", "properties": { "url": { "type": "string", "format": "uri", "description": "The URL of the input to analyze. Only one of url or data should be specified." }, "data": { "type": "string", "format": "byte", "description": "Base64-encoded binary content of the input to analyze. Only one of url or data should be specified." }, "name": { "type": "string", "description": "Name of the input." }, "mimeType": { "type": "string", "description": "The MIME type of the input content. Ex. application/pdf, image/jpeg, etc." }, "range": { "$ref": "#/definitions/RangeExpression", "description": "Range of the input to analyze (ex. `1-3,5,9-`). Document content uses 1-based page numbers, while audio visual content uses integer milliseconds." } } }, "AnalysisResult": { "type": "object", "description": "Analyze operation result.", "properties": { "analyzerId": { "type": "string", "description": "The unique identifier of the analyzer.", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$" }, "apiVersion": { "type": "string", "description": "The version of the API used to analyze the document." }, "createdAt": { "type": "string", "format": "date-time", "description": "The date and time when the result was created." }, "warnings": { "type": "array", "description": "Warnings encountered while analyzing the document.", "items": { "$ref": "#/definitions/Azure.Core.Foundations.Error" } }, "stringEncoding": { "type": "string", "description": " The string encoding format for content spans in the response.\n Possible values are 'codePoint', 'utf16', and `utf8`. Default is `codePoint`.\")", "default": "codePoint" }, "contents": { "type": "array", "description": "The extracted content.", "items": { "$ref": "#/definitions/AnalysisContent" } } }, "required": [ "contents" ] }, "AnalyzeRequest": { "type": "object", "description": "Analyze operation request.", "properties": { "inputs": { "type": "array", "description": "Inputs to analyze. Currently, only pro mode supports multiple inputs.", "items": { "$ref": "#/definitions/AnalysisInput" } }, "modelDeployments": { "type": "object", "description": "Specify the default mapping of model names to LLM/embedding deployments in Microsoft Foundry. For details and current semantics, see https://aka.ms/cudoc-quickstart-rest.", "additionalProperties": { "type": "string" } } }, "required": [ "inputs" ] }, "ArrayField": { "type": "object", "description": "Array field extracted from the content.", "properties": { "valueArray": { "type": "array", "description": "Array field value.", "items": { "$ref": "#/definitions/ContentField" } } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "array" }, "AudioVisualContent": { "type": "object", "description": "Audio visual content. Ex. audio/wav, video/mp4.", "properties": { "startTimeMs": { "type": "integer", "format": "int64", "description": "Start time of the content in milliseconds." }, "endTimeMs": { "type": "integer", "format": "int64", "description": "End time of the content in milliseconds." }, "width": { "type": "integer", "format": "int32", "description": "Width of each video frame in pixels, if applicable." }, "height": { "type": "integer", "format": "int32", "description": "Height of each video frame in pixels, if applicable." }, "cameraShotTimesMs": { "type": "array", "description": "List of camera shot changes in the video, represented by its timestamp in milliseconds. Only if returnDetails is true.", "items": { "type": "integer", "format": "int64" } }, "keyFrameTimesMs": { "type": "array", "description": "List of key frames in the video, represented by its timestamp in milliseconds. Only if returnDetails is true.", "items": { "type": "integer", "format": "int64" } }, "transcriptPhrases": { "type": "array", "description": "List of transcript phrases. Only if returnDetails is true.", "items": { "$ref": "#/definitions/TranscriptPhrase" } }, "segments": { "type": "array", "description": "List of detected content segments. Only if enableSegment is true.", "items": { "$ref": "#/definitions/AudioVisualContentSegment" } } }, "required": [ "startTimeMs", "endTimeMs" ], "allOf": [ { "$ref": "#/definitions/AnalysisContent" } ], "x-ms-discriminator-value": "audioVisual" }, "AudioVisualContentSegment": { "type": "object", "description": "Detected audio/visual content segment.", "properties": { "segmentId": { "type": "string", "description": "Segment identifier." }, "category": { "type": "string", "description": "Classified content category." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the segment in the markdown content." }, "startTimeMs": { "type": "integer", "format": "int64", "description": "Start time of the segment in milliseconds." }, "endTimeMs": { "type": "integer", "format": "int64", "description": "End time of the segment in milliseconds." } }, "required": [ "segmentId", "category", "span", "startTimeMs", "endTimeMs" ] }, "Azure.Core.Foundations.Error": { "type": "object", "description": "The error object.", "properties": { "code": { "type": "string", "description": "One of a server-defined set of error codes." }, "message": { "type": "string", "description": "A human-readable representation of the error." }, "target": { "type": "string", "description": "The target of the error." }, "details": { "type": "array", "description": "An array of details about specific errors that led to this reported error.", "items": { "$ref": "#/definitions/Azure.Core.Foundations.Error" } }, "innererror": { "$ref": "#/definitions/Azure.Core.Foundations.InnerError", "description": "An object containing more specific information than the current object about the error." } }, "required": [ "code", "message" ] }, "Azure.Core.Foundations.ErrorResponse": { "type": "object", "description": "A response containing error details.", "properties": { "error": { "$ref": "#/definitions/Azure.Core.Foundations.Error", "description": "The error object." } }, "required": [ "error" ] }, "Azure.Core.Foundations.InnerError": { "type": "object", "description": "An object containing more specific information about the error. As per Azure REST API guidelines - https://aka.ms/AzureRestApiGuidelines#handling-errors.", "properties": { "code": { "type": "string", "description": "One of a server-defined set of error codes." }, "innererror": { "$ref": "#/definitions/Azure.Core.Foundations.InnerError", "description": "Inner error." } } }, "Azure.Core.Foundations.OperationState": { "type": "string", "description": "Enum describing allowed operation states.", "enum": [ "NotStarted", "Running", "Succeeded", "Failed", "Canceled" ], "x-ms-enum": { "name": "OperationState", "modelAsString": true, "values": [ { "name": "NotStarted", "value": "NotStarted", "description": "The operation has not started." }, { "name": "Running", "value": "Running", "description": "The operation is in progress." }, { "name": "Succeeded", "value": "Succeeded", "description": "The operation has completed successfully." }, { "name": "Failed", "value": "Failed", "description": "The operation has failed." }, { "name": "Canceled", "value": "Canceled", "description": "The operation has been canceled by the user." } ] } }, "BooleanField": { "type": "object", "description": "Boolean field extracted from the content.", "properties": { "valueBoolean": { "type": "boolean", "description": "Boolean field value." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "boolean" }, "ContentAnalyzer": { "type": "object", "description": "Analyzer that extracts content and fields from multimodal documents.", "properties": { "analyzerId": { "type": "string", "description": "The unique identifier of the analyzer.", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$", "readOnly": true }, "description": { "type": "string", "description": "A description of the analyzer." }, "tags": { "type": "object", "description": "Tags associated with the analyzer.", "additionalProperties": { "type": "string" } }, "status": { "$ref": "#/definitions/ContentAnalyzerStatus", "description": "The status of the analyzer.", "readOnly": true }, "createdAt": { "type": "string", "format": "date-time", "description": "The date and time when the analyzer was created.", "readOnly": true }, "lastModifiedAt": { "type": "string", "format": "date-time", "description": "The date and time when the analyzer was last modified.", "readOnly": true }, "warnings": { "type": "array", "description": "Warnings encountered while creating the analyzer.", "items": { "$ref": "#/definitions/Azure.Core.Foundations.Error" }, "readOnly": true }, "baseAnalyzerId": { "type": "string", "description": "The analyzer to incrementally train from.", "minLength": 1, "maxLength": 64, "pattern": "^[a-zA-Z0-9._-]{1,64}$", "x-ms-mutability": [ "read", "create" ] }, "config": { "$ref": "#/definitions/ContentAnalyzerConfig", "description": "Analyzer configuration settings.", "x-ms-mutability": [ "read", "create" ] }, "fieldSchema": { "$ref": "#/definitions/ContentFieldSchema", "description": "The schema of fields to extracted.", "x-ms-mutability": [ "read", "create" ] }, "dynamicFieldSchema": { "type": "boolean", "description": "Indicates whether the result may contain additional fields outside of the defined schema.", "default": false, "x-ms-mutability": [ "read", "create" ] }, "processingLocation": { "type": "string", "description": "The location where the data may be processed. Defaults to global.", "default": "global", "enum": [ "geography", "dataZone", "global" ], "x-ms-enum": { "name": "ProcessingLocation", "modelAsString": true, "values": [ { "name": "geography", "value": "geography", "description": "Data may be processed in the same geography as the resource." }, { "name": "dataZone", "value": "dataZone", "description": "Data may be processed in the same data zone as the resource." }, { "name": "global", "value": "global", "description": "Data may be processed in any Azure data center globally." } ] }, "x-ms-mutability": [ "read", "create" ] }, "knowledgeSources": { "type": "array", "description": "Additional knowledge sources used to enhance the analyzer.", "items": { "$ref": "#/definitions/KnowledgeSource" }, "x-ms-mutability": [ "read", "create" ] }, "models": { "type": "object", "description": "Mapping of model roles to specific model names.\nEx. { \"completion\": \"gpt-4.1\", \"embedding\": \"text-embedding-3-large\" }.", "additionalProperties": { "type": "string" }, "x-ms-mutability": [ "read", "create" ] }, "supportedModels": { "$ref": "#/definitions/SupportedModels", "description": "Chat completion and embedding models supported by the analyzer.", "readOnly": true } }, "required": [ "analyzerId", "status", "createdAt", "lastModifiedAt" ] }, "ContentAnalyzerAnalyzeOperationStatus": { "type": "object", "description": "Provides status details for analyze operations.", "properties": { "id": { "type": "string", "description": "The unique ID of the operation." }, "status": { "$ref": "#/definitions/Azure.Core.Foundations.OperationState", "description": "The status of the operation" }, "error": { "$ref": "#/definitions/Azure.Core.Foundations.Error", "description": "Error object that describes the error when status is \"Failed\"." }, "result": { "$ref": "#/definitions/AnalysisResult", "description": "The result of the operation." }, "usage": { "$ref": "#/definitions/UsageDetails", "description": "Usage details of the analyze operation." } }, "required": [ "id", "status" ] }, "ContentAnalyzerConfig": { "type": "object", "description": "Configuration settings for an analyzer.", "properties": { "returnDetails": { "type": "boolean", "description": "Return all content details." }, "locales": { "type": "array", "description": "List of locale hints for speech transcription.", "items": { "type": "string" } }, "enableOcr": { "type": "boolean", "description": "Enable optical character recognition (OCR)." }, "enableLayout": { "type": "boolean", "description": "Enable layout analysis." }, "enableFigureDescription": { "type": "boolean", "description": "Enable generation of figure description." }, "enableFigureAnalysis": { "type": "boolean", "description": "Enable analysis of figures, such as charts and diagrams." }, "enableFormula": { "type": "boolean", "description": "Enable mathematical formula detection." }, "tableFormat": { "type": "string", "description": "Representation format of tables in analyze result markdown.", "default": "html", "enum": [ "html", "markdown" ], "x-ms-enum": { "name": "TableFormat", "modelAsString": true, "values": [ { "name": "html", "value": "html", "description": "Represent tables using HTML table elements: \\, \\, \\
, \\
." }, { "name": "markdown", "value": "markdown", "description": "Represent tables using GitHub Flavored Markdown table syntax, which does not support merged cells or rich headers." } ] } }, "chartFormat": { "type": "string", "description": "Representation format of charts in analyze result markdown.", "default": "chartJs", "enum": [ "chartJs", "markdown" ], "x-ms-enum": { "name": "ChartFormat", "modelAsString": true, "values": [ { "name": "chartJs", "value": "chartJs", "description": "Represent charts as Chart.js code blocks." }, { "name": "markdown", "value": "markdown", "description": "Represent charts as markdown tables." } ] } }, "annotationFormat": { "type": "string", "description": "Representation format of annotations in analyze result markdown.", "default": "markdown", "enum": [ "none", "markdown" ], "x-ms-enum": { "name": "AnnotationFormat", "modelAsString": true, "values": [ { "name": "none", "value": "none", "description": "Do not represent annotations." }, { "name": "markdown", "value": "markdown", "description": "Represent basic annotation information using markdown formatting." } ] } }, "disableFaceBlurring": { "type": "boolean", "description": "Disable the default blurring of faces for privacy while processing the content." }, "estimateFieldSourceAndConfidence": { "type": "boolean", "description": "Return field grounding source and confidence." }, "contentCategories": { "type": "object", "description": "Map of categories to classify the input content(s) against.", "additionalProperties": { "$ref": "#/definitions/ContentCategoryDefinition" } }, "enableSegment": { "type": "boolean", "description": "Enable segmentation of the input by contentCategories." }, "segmentPerPage": { "type": "boolean", "description": "Force segmentation of document content by page." }, "omitContent": { "type": "boolean", "description": "Omit the content for this analyzer from analyze result.\nOnly return content(s) from additional analyzers specified in contentCategories, if any." } } }, "ContentAnalyzerOperationStatus": { "type": "object", "description": "Provides status details for analyzer creation operations.", "properties": { "id": { "type": "string", "description": "The unique ID of the operation." }, "status": { "$ref": "#/definitions/Azure.Core.Foundations.OperationState", "description": "The status of the operation" }, "error": { "$ref": "#/definitions/Azure.Core.Foundations.Error", "description": "Error object that describes the error when status is \"Failed\"." }, "result": { "$ref": "#/definitions/ContentAnalyzer", "description": "The result of the operation." }, "usage": { "$ref": "#/definitions/UsageDetails", "description": "Usage details of the analyzer creation operation." } }, "required": [ "id", "status" ] }, "ContentAnalyzerStatus": { "type": "string", "description": "Status of a resource.", "enum": [ "creating", "ready", "deleting", "failed" ], "x-ms-enum": { "name": "ContentAnalyzerStatus", "modelAsString": true, "values": [ { "name": "creating", "value": "creating", "description": "The resource is being created." }, { "name": "ready", "value": "ready", "description": "The resource is ready." }, { "name": "deleting", "value": "deleting", "description": "The resource is being deleted." }, { "name": "failed", "value": "failed", "description": "The resource failed during creation." } ] } }, "ContentAnalyzerUpdate": { "type": "object", "description": "Analyzer that extracts content and fields from multimodal documents.", "properties": { "description": { "type": "string", "description": "A description of the analyzer." }, "tags": { "type": "object", "description": "Tags associated with the analyzer.", "additionalProperties": { "type": "string" } } } }, "ContentCategoryDefinition": { "type": "object", "description": "Content category definition.", "properties": { "description": { "type": "string", "description": "The description of the category." }, "analyzerId": { "type": "string", "description": "Optional analyzer used to process the content." }, "analyzer": { "$ref": "#/definitions/ContentAnalyzer", "description": "Optional inline definition of analyzer used to process the content." } } }, "ContentField": { "type": "object", "description": "Field extracted from the content.", "properties": { "type": { "$ref": "#/definitions/ContentFieldType", "description": "Semantic data type of the field value." }, "spans": { "type": "array", "description": "Span(s) associated with the field value in the markdown content.", "items": { "$ref": "#/definitions/ContentSpan" } }, "confidence": { "type": "number", "format": "float", "description": "Confidence of predicting the field value.", "minimum": 0, "maximum": 1 }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the field value in the content." } }, "discriminator": "type", "required": [ "type" ] }, "ContentFieldDefinition": { "type": "object", "description": "Definition of the field using a JSON Schema like syntax.", "properties": { "method": { "$ref": "#/definitions/GenerationMethod", "description": "Generation method." }, "type": { "$ref": "#/definitions/ContentFieldType", "description": "Semantic data type of the field value." }, "description": { "type": "string", "description": "Field description." }, "items": { "$ref": "#/definitions/ContentFieldDefinition", "description": "Field type schema of each array element, if type is array." }, "properties": { "type": "object", "description": "Named sub-fields, if type is object.", "additionalProperties": { "$ref": "#/definitions/ContentFieldDefinition" } }, "examples": { "type": "array", "description": "Examples of field values.", "items": { "type": "string" } }, "enum": { "type": "array", "description": "Enumeration of possible field values.", "items": { "type": "string" } }, "enumDescriptions": { "type": "object", "description": "Descriptions for each enumeration value.", "additionalProperties": { "type": "string" } }, "$ref": { "type": "string", "description": "Reference to another field definition." }, "estimateSourceAndConfidence": { "type": "boolean", "description": "Return grounding source and confidence." } } }, "ContentFieldSchema": { "type": "object", "description": "Schema of fields to be extracted from documents.", "properties": { "name": { "type": "string", "description": "The name of the field schema.", "x-ms-mutability": [ "read", "create" ] }, "description": { "type": "string", "description": "A description of the field schema.", "x-ms-mutability": [ "read", "create" ] }, "fields": { "type": "object", "description": "The fields defined in the schema.", "additionalProperties": { "$ref": "#/definitions/ContentFieldDefinition" }, "x-ms-mutability": [ "read", "create" ] }, "definitions": { "type": "object", "description": "Additional definitions referenced by the fields in the schema.", "additionalProperties": { "$ref": "#/definitions/ContentFieldDefinition" }, "x-ms-mutability": [ "read", "create" ] } }, "required": [ "fields" ] }, "ContentFieldType": { "type": "string", "description": "Semantic data type of the field value.", "enum": [ "string", "date", "time", "number", "integer", "boolean", "array", "object", "json" ], "x-ms-enum": { "name": "ContentFieldType", "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": "number", "value": "number", "description": "Number as double precision floating point." }, { "name": "integer", "value": "integer", "description": "Integer as 64-bit signed integer." }, { "name": "boolean", "value": "boolean", "description": "Boolean value." }, { "name": "array", "value": "array", "description": "List of subfields of the same type." }, { "name": "object", "value": "object", "description": "Named list of subfields." }, { "name": "json", "value": "json", "description": "JSON object." } ] } }, "ContentSpan": { "type": "object", "description": "Position of the element in markdown, specified as a character offset and length.", "properties": { "offset": { "type": "integer", "format": "int32", "description": "Starting position (0-indexed) of the element in markdown, specified in characters." }, "length": { "type": "integer", "format": "int32", "description": "Length of the element in markdown, specified in characters." } }, "required": [ "offset", "length" ] }, "ContentUnderstandingDefaults": { "type": "object", "description": "Default settings for this Content Understanding resource.", "properties": { "modelDeployments": { "type": "object", "description": "Specify the default mapping of model names to LLM/embedding deployments in Microsoft Foundry. For details and current semantics, see https://aka.ms/cudoc-quickstart-rest.", "additionalProperties": { "type": "string" }, "x-ms-mutability": [ "read", "update", "create" ] } }, "required": [ "modelDeployments" ] }, "ContentUnderstandingDefaultsMergePatchUpdate": { "type": "object", "description": "Default settings for this Content Understanding resource.", "properties": { "modelDeployments": { "type": "object", "description": "Specify the default mapping of model names to LLM/embedding deployments in Microsoft Foundry. For details and current semantics, see https://aka.ms/cudoc-quickstart-rest.", "additionalProperties": { "type": "string" } } } }, "CopyAuthorization": { "type": "object", "description": "Copy authorization details for cross-resource copy.", "properties": { "source": { "type": "string", "description": "Full path of the source analyzer." }, "targetAzureResourceId": { "type": "string", "description": "Azure resource ID of the target location to copy to." }, "expiresAt": { "type": "string", "format": "date-time", "description": "Date/time when the copy authorization expires." } }, "required": [ "source", "targetAzureResourceId", "expiresAt" ] }, "CopyRequest": { "type": "object", "description": "Copy operation request.", "properties": { "sourceAzureResourceId": { "type": "string", "description": "Azure resource ID of the source analyzer location. Defaults to the current resource." }, "sourceRegion": { "type": "string", "description": "Azure region of the source analyzer location. Defaults to current region." }, "sourceAnalyzerId": { "type": "string", "description": "Source analyzer ID." } }, "required": [ "sourceAnalyzerId" ] }, "DateField": { "type": "object", "description": "Date field extracted from the content.", "properties": { "valueDate": { "type": "string", "format": "date", "description": "Date field value, in ISO 8601 (YYYY-MM-DD) format." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "date" }, "DocumentAnnotation": { "type": "object", "description": "Annotation in a document, such as a strikethrough or a comment.", "properties": { "id": { "type": "string", "description": "Annotation identifier." }, "kind": { "$ref": "#/definitions/DocumentAnnotationKind", "description": "Annotation kind." }, "spans": { "type": "array", "description": "Spans of the content associated with the annotation.", "items": { "$ref": "#/definitions/ContentSpan" } }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Position of the annotation." }, "comments": { "type": "array", "description": "Comments associated with the annotation.", "items": { "$ref": "#/definitions/DocumentAnnotationComment" } }, "author": { "type": "string", "description": "Annotation author." }, "createdAt": { "type": "string", "format": "date-time", "description": "Date and time when the annotation was created." }, "lastModifiedAt": { "type": "string", "format": "date-time", "description": "Date and time when the annotation was last modified." }, "tags": { "type": "array", "description": "Tags associated with the annotation.", "items": { "type": "string" } } }, "required": [ "id", "kind" ] }, "DocumentAnnotationComment": { "type": "object", "description": "Comment associated with a document annotation.", "properties": { "message": { "type": "string", "description": "Comment message in Markdown." }, "author": { "type": "string", "description": "Author of the comment." }, "createdAt": { "type": "string", "format": "date-time", "description": "Date and time when the comment was created." }, "lastModifiedAt": { "type": "string", "format": "date-time", "description": "Date and time when the comment was last modified." }, "tags": { "type": "array", "description": "Tags associated with the comment.", "items": { "type": "string" } } }, "required": [ "message" ] }, "DocumentAnnotationKind": { "type": "string", "description": "Document annotation kind.", "enum": [ "highlight", "strikethrough", "underline", "italic", "bold", "circle", "note" ], "x-ms-enum": { "name": "DocumentAnnotationKind", "modelAsString": true, "values": [ { "name": "highlight", "value": "highlight", "description": "Highlight annotation." }, { "name": "strikethrough", "value": "strikethrough", "description": "Strikethrough annotation." }, { "name": "underline", "value": "underline", "description": "Underline annotation." }, { "name": "italic", "value": "italic", "description": "Italic annotation." }, { "name": "bold", "value": "bold", "description": "Bold annotation." }, { "name": "circle", "value": "circle", "description": "Circle annotation." }, { "name": "note", "value": "note", "description": "Note annotation." } ] } }, "DocumentBarcode": { "type": "object", "description": "Barcode in a document.", "properties": { "kind": { "$ref": "#/definitions/DocumentBarcodeKind", "description": "Barcode kind." }, "value": { "type": "string", "description": "Barcode value." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the barcode in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the barcode in the markdown content." }, "confidence": { "type": "number", "format": "float", "description": "Confidence of predicting the barcode.", "minimum": 0, "maximum": 1 } }, "required": [ "kind", "value" ] }, "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." } ] } }, "DocumentCaption": { "type": "object", "description": "Caption of a table or figure.", "properties": { "content": { "type": "string", "description": "Content of the caption." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the caption in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the caption in the markdown content." }, "elements": { "type": "array", "description": "Child elements of the caption.", "items": { "$ref": "#/definitions/DocumentElement" } } }, "required": [ "content" ] }, "DocumentChartFigure": { "type": "object", "description": "Figure containing a chart, such as a bar chart, line chart, or pie chart.", "properties": { "content": { "type": "object", "description": "Chart content represented using [Chart.js config](https://www.chartjs.org/docs/latest/configuration/).", "additionalProperties": {} } }, "required": [ "content" ], "allOf": [ { "$ref": "#/definitions/DocumentFigure" } ], "x-ms-discriminator-value": "chart" }, "DocumentContent": { "type": "object", "description": "Document content. Ex. text/plain, application/pdf, image/jpeg.", "properties": { "startPageNumber": { "type": "integer", "format": "int32", "description": "Start page number (1-indexed) of the content." }, "endPageNumber": { "type": "integer", "format": "int32", "description": "End page number (1-indexed) of the content." }, "unit": { "$ref": "#/definitions/LengthUnit", "description": "Length unit used by the width, height, and source properties.\nFor images/tiff, the default unit is pixel. For PDF, the default unit is inch." }, "pages": { "type": "array", "description": "List of pages in the document.", "items": { "$ref": "#/definitions/DocumentPage" } }, "paragraphs": { "type": "array", "description": "List of paragraphs in the document. Only if enableOcr and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentParagraph" } }, "sections": { "type": "array", "description": "List of sections in the document. Only if enableLayout and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentSection" } }, "tables": { "type": "array", "description": "List of tables in the document. Only if enableLayout and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentTable" } }, "figures": { "type": "array", "description": "List of figures in the document. Only if enableLayout and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentFigure" } }, "annotations": { "type": "array", "description": "List of annotations in the document. Only if enableAnnotations and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentAnnotation" } }, "hyperlinks": { "type": "array", "description": "List of hyperlinks in the document. Only if returnDetails are true.", "items": { "$ref": "#/definitions/DocumentHyperlink" } }, "segments": { "type": "array", "description": "List of detected content segments. Only if enableSegment is true.", "items": { "$ref": "#/definitions/DocumentContentSegment" } } }, "required": [ "startPageNumber", "endPageNumber" ], "allOf": [ { "$ref": "#/definitions/AnalysisContent" } ], "x-ms-discriminator-value": "document" }, "DocumentContentSegment": { "type": "object", "description": "Detected document content segment.", "properties": { "segmentId": { "type": "string", "description": "Segment identifier." }, "category": { "type": "string", "description": "Classified content category." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the segment in the markdown content." }, "startPageNumber": { "type": "integer", "format": "int32", "description": "Start page number (1-indexed) of the segment." }, "endPageNumber": { "type": "integer", "format": "int32", "description": "End page number (1-indexed) of the segment." } }, "required": [ "segmentId", "category", "span", "startPageNumber", "endPageNumber" ] }, "DocumentElement": { "type": "string", "description": "JSON pointer referencing an element of the document, such as paragraph,\ntable, section, etc." }, "DocumentFigure": { "type": "object", "description": "Figure in a document.", "properties": { "kind": { "type": "string", "description": "Figure kind.", "default": "unknown", "enum": [ "unknown", "chart", "mermaid" ], "x-ms-enum": { "name": "DocumentFigureKind", "modelAsString": true, "values": [ { "name": "unknown", "value": "unknown", "description": "Unknown figure kind." }, { "name": "chart", "value": "chart", "description": "Figure containing a chart, such as a bar chart, line chart, or pie chart." }, { "name": "mermaid", "value": "mermaid", "description": "Figure containing a diagram, such as a flowchart or network diagram." } ] } }, "id": { "type": "string", "description": "Figure identifier." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the figure in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the figure in the markdown content." }, "elements": { "type": "array", "description": "Child elements of the figure, excluding any caption or footnotes.", "items": { "$ref": "#/definitions/DocumentElement" } }, "caption": { "$ref": "#/definitions/DocumentCaption", "description": "Figure caption." }, "footnotes": { "type": "array", "description": "List of figure footnotes.", "items": { "$ref": "#/definitions/DocumentFootnote" } }, "description": { "type": "string", "description": "Description of the figure." }, "role": { "$ref": "#/definitions/SemanticRole", "description": "Semantic role of the figure." } }, "discriminator": "kind", "required": [ "kind", "id" ] }, "DocumentFootnote": { "type": "object", "description": "Footnote of a table or figure.", "properties": { "content": { "type": "string", "description": "Content of the footnote." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the footnote in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the footnote in the markdown content." }, "elements": { "type": "array", "description": "Child elements of the footnote.", "items": { "$ref": "#/definitions/DocumentElement" } } }, "required": [ "content" ] }, "DocumentFormula": { "type": "object", "description": "Mathematical formula in a document.", "properties": { "kind": { "$ref": "#/definitions/DocumentFormulaKind", "description": "Formula kind." }, "value": { "type": "string", "description": "LaTex expression describing the formula." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the formula in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the formula in the markdown content." }, "confidence": { "type": "number", "format": "float", "description": "Confidence of predicting the formula.", "minimum": 0, "maximum": 1 } }, "required": [ "kind", "value" ] }, "DocumentFormulaKind": { "type": "string", "description": "Formula kind.", "enum": [ "inline", "display" ], "x-ms-enum": { "name": "DocumentFormulaKind", "modelAsString": true, "values": [ { "name": "inline", "value": "inline", "description": "A formula embedded within the content of a paragraph." }, { "name": "display", "value": "display", "description": "A formula in display mode that takes up an entire line." } ] } }, "DocumentHyperlink": { "type": "object", "description": "Hyperlink in a document, such as a link to a web page or an email address.", "properties": { "content": { "type": "string", "description": "Hyperlinked content." }, "url": { "type": "string", "description": "URL of the hyperlink." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the hyperlink in the markdown content." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Position of the hyperlink." } }, "required": [ "content", "url" ] }, "DocumentLine": { "type": "object", "description": "Line in a document, consisting of an contiguous sequence of words.", "properties": { "content": { "type": "string", "description": "Line text." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the line in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the line in the markdown content." } }, "required": [ "content" ] }, "DocumentMermaidFigure": { "type": "object", "description": "Figure containing a diagram, such as a flowchart or network diagram.", "properties": { "content": { "type": "string", "description": "Diagram content represented using [Mermaid syntax](https://mermaid.js.org/intro/)." } }, "required": [ "content" ], "allOf": [ { "$ref": "#/definitions/DocumentFigure" } ], "x-ms-discriminator-value": "mermaid" }, "DocumentPage": { "type": "object", "description": "Content from a document page.", "properties": { "pageNumber": { "type": "integer", "format": "int32", "description": "Page number (1-based).", "minimum": 1 }, "width": { "type": "number", "format": "float", "description": "Width of the page." }, "height": { "type": "number", "format": "float", "description": "Height of the page." }, "spans": { "type": "array", "description": "Span(s) associated with the page in the markdown content.", "items": { "$ref": "#/definitions/ContentSpan" } }, "angle": { "type": "number", "format": "float", "description": "The general orientation of the content in clockwise direction,\nmeasured in degrees between (-180, 180].\nOnly if enableOcr is true.", "maximum": 180 }, "words": { "type": "array", "description": "List of words in the page. Only if enableOcr and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentWord" } }, "lines": { "type": "array", "description": "List of lines in the page. Only if enableOcr and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentLine" } }, "barcodes": { "type": "array", "description": "List of barcodes in the page. Only if enableBarcode and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentBarcode" } }, "formulas": { "type": "array", "description": "List of mathematical formulas in the page. Only if enableFormula and returnDetails are true.", "items": { "$ref": "#/definitions/DocumentFormula" } } }, "required": [ "pageNumber" ] }, "DocumentParagraph": { "type": "object", "description": "Paragraph in a document, generally consisting of an contiguous sequence of lines\nwith common alignment and spacing.", "properties": { "role": { "$ref": "#/definitions/SemanticRole", "description": "Semantic role of the paragraph." }, "content": { "type": "string", "description": "Paragraph text." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the paragraph in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the paragraph in the markdown content." } }, "required": [ "content" ] }, "DocumentSection": { "type": "object", "description": "Section in a document.", "properties": { "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the section in the markdown content." }, "elements": { "type": "array", "description": "Child elements of the section.", "items": { "$ref": "#/definitions/DocumentElement" } } } }, "DocumentTable": { "type": "object", "description": "Table in a document, 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": { "$ref": "#/definitions/DocumentTableCell" } }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the table in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the table in the markdown content." }, "caption": { "$ref": "#/definitions/DocumentCaption", "description": "Table caption." }, "footnotes": { "type": "array", "description": "List of table footnotes.", "items": { "$ref": "#/definitions/DocumentFootnote" } }, "role": { "$ref": "#/definitions/SemanticRole", "description": "Semantic role of the table." } }, "required": [ "rowCount", "columnCount", "cells" ] }, "DocumentTableCell": { "type": "object", "description": "Table cell in a document table.", "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": "Main content/data." }, { "name": "rowHeader", "value": "rowHeader", "description": "Description of the row content." }, { "name": "columnHeader", "value": "columnHeader", "description": "Description the column content." }, { "name": "stubHead", "value": "stubHead", "description": "Description of the row headers, usually located at the top left corner of a table." }, { "name": "description", "value": "description", "description": "Description of 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": "Content of the table cell." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the table cell in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the table cell in the markdown content." }, "elements": { "type": "array", "description": "Child elements of the table cell.", "items": { "$ref": "#/definitions/DocumentElement" } } }, "required": [ "rowIndex", "columnIndex", "content" ] }, "DocumentWord": { "type": "object", "description": "Word in a document, consisting of a contiguous sequence of characters.\nFor non-space delimited languages, such as Chinese, Japanese, and Korean, \neach character is represented as its own word.", "properties": { "content": { "type": "string", "description": "Word text." }, "source": { "$ref": "#/definitions/SourceExpression", "description": "Encoded source that identifies the position of the word in the content." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the word in the markdown content." }, "confidence": { "type": "number", "format": "float", "description": "Confidence of predicting the word.", "minimum": 0, "maximum": 1 } }, "required": [ "content" ] }, "GenerationMethod": { "type": "string", "description": "Generation method.", "enum": [ "generate", "extract", "classify" ], "x-ms-enum": { "name": "GenerationMethod", "modelAsString": true, "values": [ { "name": "generate", "value": "generate", "description": "Values are generated freely based on the content." }, { "name": "extract", "value": "extract", "description": "Values are extracted as they appear in the content." }, { "name": "classify", "value": "classify", "description": "Values are classified against a predefined set of categories." } ] } }, "GrantCopyAuthorizationRequest": { "type": "object", "description": "Grant copy authorization request.", "properties": { "targetAzureResourceId": { "type": "string", "description": "Azure resource ID of the target analyzer location." }, "targetRegion": { "type": "string", "description": "Azure region of the target analyzer location. Defaults to current region." } }, "required": [ "targetAzureResourceId" ] }, "IntegerField": { "type": "object", "description": "Integer field extracted from the content.", "properties": { "valueInteger": { "type": "integer", "format": "int64", "description": "Integer field value." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "integer" }, "JsonField": { "type": "object", "description": "JSON field extracted from the content.", "properties": { "valueJson": { "description": "JSON field value." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "json" }, "KnowledgeSource": { "type": "object", "description": "Knowledge source.", "properties": { "kind": { "$ref": "#/definitions/KnowledgeSourceKind", "description": "The kind of knowledge source." } }, "discriminator": "kind", "required": [ "kind" ] }, "KnowledgeSourceKind": { "type": "string", "description": "Knowledge source kind.", "enum": [ "labeledData" ], "x-ms-enum": { "name": "KnowledgeSourceKind", "modelAsString": true, "values": [ { "name": "labeledData", "value": "labeledData", "description": "A labeled data knowledge source." } ] } }, "LabeledDataKnowledgeSource": { "type": "object", "description": "Labeled data knowledge source.", "properties": { "containerUrl": { "type": "string", "format": "uri", "description": "The URL of the blob container containing labeled data." }, "prefix": { "type": "string", "description": "An optional prefix to filter blobs within the container." }, "fileListPath": { "type": "string", "description": "An optional path to a file listing specific blobs to include." } }, "required": [ "containerUrl", "fileListPath" ], "allOf": [ { "$ref": "#/definitions/KnowledgeSource" } ], "x-ms-discriminator-value": "labeledData" }, "LengthUnit": { "type": "string", "description": "Length unit used by the width, height, and source properties.", "enum": [ "pixel", "inch" ], "x-ms-enum": { "name": "LengthUnit", "modelAsString": true, "values": [ { "name": "pixel", "value": "pixel", "description": "Pixel unit." }, { "name": "inch", "value": "inch", "description": "Inch unit." } ] } }, "NumberField": { "type": "object", "description": "Number field extracted from the content.", "properties": { "valueNumber": { "type": "number", "format": "double", "description": "Number field value." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "number" }, "ObjectField": { "type": "object", "description": "Object field extracted from the content.", "properties": { "valueObject": { "type": "object", "description": "Object field value.", "additionalProperties": { "$ref": "#/definitions/ContentField" } } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "object" }, "PagedContentAnalyzer": { "type": "object", "description": "Paged collection of ContentAnalyzer items", "properties": { "value": { "type": "array", "description": "The ContentAnalyzer items on this page", "items": { "$ref": "#/definitions/ContentAnalyzer" } }, "nextLink": { "type": "string", "format": "uri", "description": "The link to the next page of items" } }, "required": [ "value" ] }, "RangeExpression": { "type": "string", "description": " Range expression for specifying parts of the input to analyze (ex. `1-3,5,9-`).\n Document content uses 1-based page numbers, while audio visual content uses integer milliseconds." }, "SemanticRole": { "type": "string", "description": "Semantic role of the paragraph.", "enum": [ "pageHeader", "pageFooter", "pageNumber", "title", "sectionHeading", "footnote", "formulaBlock" ], "x-ms-enum": { "name": "SemanticRole", "modelAsString": true, "values": [ { "name": "pageHeader", "value": "pageHeader", "description": "Text near the top edge of the page." }, { "name": "pageFooter", "value": "pageFooter", "description": "Text near the bottom edge of the page." }, { "name": "pageNumber", "value": "pageNumber", "description": "Page number." }, { "name": "title", "value": "title", "description": "Top-level title describing the entire document." }, { "name": "sectionHeading", "value": "sectionHeading", "description": "Sub heading describing a section of the document." }, { "name": "footnote", "value": "footnote", "description": "Note usually placed after the main content on a page." }, { "name": "formulaBlock", "value": "formulaBlock", "description": "Block of formulas, often with shared alignment." } ] } }, "SourceExpression": { "type": "string", "description": "Encoded string expression that describes positions in the content." }, "StringField": { "type": "object", "description": "String field extracted from the content.", "properties": { "valueString": { "type": "string", "description": "String field value." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "string" }, "SupportedModels": { "type": "object", "description": "Chat completion and embedding models supported by the analyzer.", "properties": { "completion": { "type": "array", "description": "Chat completion models supported by the analyzer.", "items": { "type": "string" } }, "embedding": { "type": "array", "description": "Embedding models supported by the analyzer.", "items": { "type": "string" } } } }, "TimeField": { "type": "object", "description": "Time field extracted from the content.", "properties": { "valueTime": { "type": "string", "format": "time", "description": "Time field value, in ISO 8601 (hh:mm:ss) format." } }, "allOf": [ { "$ref": "#/definitions/ContentField" } ], "x-ms-discriminator-value": "time" }, "TranscriptPhrase": { "type": "object", "description": "Transcript phrase.", "properties": { "speaker": { "type": "string", "description": "Speaker index or name." }, "startTimeMs": { "type": "integer", "format": "int64", "description": "Start time of the phrase in milliseconds." }, "endTimeMs": { "type": "integer", "format": "int64", "description": "End time of the phrase in milliseconds." }, "locale": { "type": "string", "description": "Detected locale of the phrase. Ex. en-US." }, "text": { "type": "string", "description": "Transcript text." }, "confidence": { "type": "number", "format": "float", "description": "Confidence of predicting the phrase.", "minimum": 0, "maximum": 1 }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the phrase in the markdown content." }, "words": { "type": "array", "description": "List of words in the phrase.", "items": { "$ref": "#/definitions/TranscriptWord" } } }, "required": [ "startTimeMs", "endTimeMs", "text", "words" ] }, "TranscriptWord": { "type": "object", "description": "Transcript word.", "properties": { "startTimeMs": { "type": "integer", "format": "int64", "description": "Start time of the word in milliseconds." }, "endTimeMs": { "type": "integer", "format": "int64", "description": "End time of the word in milliseconds." }, "text": { "type": "string", "description": "Transcript text." }, "span": { "$ref": "#/definitions/ContentSpan", "description": "Span of the word in the markdown content." } }, "required": [ "startTimeMs", "endTimeMs", "text" ] }, "UsageDetails": { "type": "object", "description": "Usage details.", "properties": { "documentPagesMinimal": { "type": "integer", "format": "int32", "description": "The number of document pages processed at the minimal level.\nFor documents without explicit pages (ex. txt, html), every 3000 UTF-16 characters is counted as one page." }, "documentPagesBasic": { "type": "integer", "format": "int32", "description": "The number of document pages processed at the basic level.\nFor documents without explicit pages (ex. txt, html), every 3000 UTF-16 characters is counted as one page." }, "documentPagesStandard": { "type": "integer", "format": "int32", "description": "The number of document pages processed at the standard level.\nFor documents without explicit pages (ex. txt, html), every 3000 UTF-16 characters is counted as one page." }, "audioHours": { "type": "number", "format": "float", "description": "The hours of audio processed." }, "videoHours": { "type": "number", "format": "float", "description": "The hours of video processed." }, "contextualizationTokens": { "type": "integer", "format": "int32", "description": "The number of contextualization tokens consumed for preparing context, generating confidence scores, source grounding, and output formatting." }, "tokens": { "type": "object", "description": "The number of LLM and embedding tokens consumed, grouped by model (ex. GTP 4.1) and type (ex. input, cached input, output).", "additionalProperties": { "format": "int32", "type": "integer" } } } } }, "parameters": { "AnalyzeBinaryRequest.input": { "name": "input", "in": "body", "description": "The binary content of the document to analyze.", "required": true, "schema": { "type": "string", "format": "binary" }, "x-ms-parameter-location": "method" }, "AnalyzeBinaryRequest.range": { "name": "range", "in": "query", "description": "Range of the input to analyze (ex. `1-3,5,9-`). Document content uses 1-based page numbers, while audio visual content uses integer milliseconds.", "required": false, "type": "string", "x-ms-parameter-location": "method" }, "AnalyzeParameters.processingLocation": { "name": "processingLocation", "in": "query", "description": "The location where the data may be processed. Defaults to global.", "required": false, "type": "string", "default": "global", "enum": [ "geography", "dataZone", "global" ], "x-ms-enum": { "name": "ProcessingLocation", "modelAsString": true, "values": [ { "name": "geography", "value": "geography", "description": "Data may be processed in the same geography as the resource." }, { "name": "dataZone", "value": "dataZone", "description": "Data may be processed in the same data zone as the resource." }, { "name": "global", "value": "global", "description": "Data may be processed in any Azure data center globally." } ] }, "x-ms-parameter-location": "method" }, "AnalyzeParameters.stringEncoding": { "name": "stringEncoding", "in": "query", "description": " The string encoding format for content spans in the response.\n Possible values are 'codePoint', 'utf16', and `utf8`. Default is `codePoint`.\")", "required": false, "type": "string", "default": "codePoint", "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" } } }