{ "batchPath": "batch", "revision": "20240615", "id": "documentai:v1beta3", "fullyEncodeReservedExpansion": true, "servicePath": "", "canonicalName": "Document", "title": "Cloud Document AI API", "protocol": "rest", "ownerName": "Google", "discoveryVersion": "v1", "ownerDomain": "google.com", "basePath": "", "baseUrl": "https://documentai.googleapis.com/", "parameters": { "access_token": { "type": "string", "description": "OAuth access token.", "location": "query" }, "alt": { "type": "string", "description": "Data format for response.", "default": "json", "enum": [ "json", "media", "proto" ], "enumDescriptions": [ "Responses with Content-Type of application/json", "Media download with context-dependent Content-Type", "Responses with Content-Type of application/x-protobuf" ], "location": "query" }, "callback": { "type": "string", "description": "JSONP", "location": "query" }, "fields": { "type": "string", "description": "Selector specifying which fields to include in a partial response.", "location": "query" }, "key": { "type": "string", "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.", "location": "query" }, "oauth_token": { "type": "string", "description": "OAuth 2.0 token for the current user.", "location": "query" }, "prettyPrint": { "type": "boolean", "description": "Returns response with indentations and line breaks.", "default": "true", "location": "query" }, "quotaUser": { "type": "string", "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", "location": "query" }, "upload_protocol": { "type": "string", "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", "location": "query" }, "uploadType": { "type": "string", "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", "location": "query" }, "$.xgafv": { "type": "string", "description": "V1 error format.", "enum": [ "1", "2" ], "enumDescriptions": [ "v1 error format", "v2 error format" ], "location": "query" } }, "resources": { "projects": { "resources": { "locations": { "methods": { "fetchProcessorTypes": { "id": "documentai.projects.locations.fetchProcessorTypes", "path": "v1beta3/{+parent}:fetchProcessorTypes", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}:fetchProcessorTypes", "httpMethod": "GET", "parameters": { "parent": { "description": "Required. The location of processor types to list. Format: `projects/{project}/locations/{location}`.", "pattern": "^projects/[^/]+/locations/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "parent" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3FetchProcessorTypesResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Fetches processor types. Note that we don't use ListProcessorTypes here, because it isn't paginated." }, "list": { "id": "documentai.projects.locations.list", "path": "v1beta3/{+name}/locations", "flatPath": "v1beta3/projects/{projectsId}/locations", "httpMethod": "GET", "parameters": { "name": { "description": "The resource that owns the locations collection, if applicable.", "pattern": "^projects/[^/]+$", "location": "path", "required": true, "type": "string" }, "filter": { "description": "A filter to narrow down results to a preferred subset. The filtering language accepts strings like `\"displayName=tokyo\"`, and is documented in more detail in [AIP-160](https://google.aip.dev/160).", "location": "query", "type": "string" }, "pageSize": { "description": "The maximum number of results to return. If not set, the service selects a default.", "location": "query", "type": "integer", "format": "int32" }, "pageToken": { "description": "A page token received from the `next_page_token` field in the response. Send that page token to receive the subsequent page.", "location": "query", "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudLocationListLocationsResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Lists information about the supported locations for this service." }, "get": { "id": "documentai.projects.locations.get", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}", "httpMethod": "GET", "parameters": { "name": { "description": "Resource name for the location.", "pattern": "^projects/[^/]+/locations/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudLocationLocation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Gets information about a location." } }, "resources": { "operations": { "methods": { "list": { "id": "documentai.projects.locations.operations.list", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/operations", "httpMethod": "GET", "parameters": { "name": { "description": "The name of the operation's parent resource.", "pattern": "^projects/[^/]+/locations/[^/]+/operations$", "location": "path", "required": true, "type": "string" }, "filter": { "description": "The standard list filter.", "location": "query", "type": "string" }, "pageSize": { "description": "The standard list page size.", "location": "query", "type": "integer", "format": "int32" }, "pageToken": { "description": "The standard list page token.", "location": "query", "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleLongrunningListOperationsResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`." }, "get": { "id": "documentai.projects.locations.operations.get", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}", "httpMethod": "GET", "parameters": { "name": { "description": "The name of the operation resource.", "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service." }, "cancel": { "id": "documentai.projects.locations.operations.cancel", "path": "v1beta3/{+name}:cancel", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}:cancel", "httpMethod": "POST", "parameters": { "name": { "description": "The name of the operation resource to be cancelled.", "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleProtobufEmpty" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`." } } }, "processors": { "methods": { "process": { "id": "documentai.projects.locations.processors.process", "path": "v1beta3/{+name}:process", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}:process", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The resource name of the Processor or ProcessorVersion to use for processing. If a Processor is specified, the server will use its default version. Format: `projects/{project}/locations/{location}/processors/{processor}`, or `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessRequest" }, "response": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Processes a single document." }, "batchProcess": { "id": "documentai.projects.locations.processors.batchProcess", "path": "v1beta3/{+name}:batchProcess", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}:batchProcess", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The resource name of Processor or ProcessorVersion. Format: `projects/{project}/locations/{location}/processors/{processor}`, or `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3BatchProcessRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "LRO endpoint to batch process many documents. The output is written to Cloud Storage as JSON in the [Document] format." }, "list": { "id": "documentai.projects.locations.processors.list", "path": "v1beta3/{+parent}/processors", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors", "httpMethod": "GET", "parameters": { "parent": { "description": "Required. The parent (project and location) which owns this collection of Processors. Format: `projects/{project}/locations/{location}`", "pattern": "^projects/[^/]+/locations/[^/]+$", "location": "path", "required": true, "type": "string" }, "pageSize": { "description": "The maximum number of processors to return. If unspecified, at most `50` processors will be returned. The maximum value is `100`. Values above `100` will be coerced to `100`.", "location": "query", "type": "integer", "format": "int32" }, "pageToken": { "description": "We will return the processors sorted by creation time. The page token will point to the next processor.", "location": "query", "type": "string" } }, "parameterOrder": [ "parent" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3ListProcessorsResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Lists all processors which belong to this project." }, "get": { "id": "documentai.projects.locations.processors.get", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}", "httpMethod": "GET", "parameters": { "name": { "description": "Required. The processor resource name.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3Processor" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Gets a processor detail." }, "create": { "id": "documentai.projects.locations.processors.create", "path": "v1beta3/{+parent}/processors", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors", "httpMethod": "POST", "parameters": { "parent": { "description": "Required. The parent (project and location) under which to create the processor. Format: `projects/{project}/locations/{location}`", "pattern": "^projects/[^/]+/locations/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "parent" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3Processor" }, "response": { "$ref": "GoogleCloudDocumentaiV1beta3Processor" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Creates a processor from the ProcessorType provided. The processor will be at `ENABLED` state by default after its creation. Note that this method requires the `documentai.processors.create` permission on the project, which is highly privileged. A user or service account with this permission can create new processors that can interact with any gcs bucket in your project." }, "delete": { "id": "documentai.projects.locations.processors.delete", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}", "httpMethod": "DELETE", "parameters": { "name": { "description": "Required. The processor resource name to be deleted.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Deletes the processor, unloads all deployed model artifacts if it was enabled and then deletes all artifacts associated with this processor." }, "enable": { "id": "documentai.projects.locations.processors.enable", "path": "v1beta3/{+name}:enable", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}:enable", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The processor resource name to be enabled.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3EnableProcessorRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Enables a processor" }, "disable": { "id": "documentai.projects.locations.processors.disable", "path": "v1beta3/{+name}:disable", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}:disable", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The processor resource name to be disabled.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3DisableProcessorRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Disables a processor" }, "setDefaultProcessorVersion": { "id": "documentai.projects.locations.processors.setDefaultProcessorVersion", "path": "v1beta3/{+processor}:setDefaultProcessorVersion", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}:setDefaultProcessorVersion", "httpMethod": "POST", "parameters": { "processor": { "description": "Required. The resource name of the Processor to change default version.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "processor" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Set the default (active) version of a Processor that will be used in ProcessDocument and BatchProcessDocuments." }, "updateDataset": { "id": "documentai.projects.locations.processors.updateDataset", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset", "httpMethod": "PATCH", "parameters": { "name": { "description": "Dataset resource name. Format: `projects/{project}/locations/{location}/processors/{processor}/dataset`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset$", "location": "path", "required": true, "type": "string" }, "updateMask": { "description": "The update mask applies to the resource.", "location": "query", "type": "string", "format": "google-fieldmask" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3Dataset" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Updates metadata associated with a dataset. Note that this method requires the `documentai.googleapis.com/datasets.update` permission on the project, which is highly privileged. A user or service account with this permission can create new processors that can interact with any gcs bucket in your project." } }, "resources": { "processorVersions": { "methods": { "process": { "id": "documentai.projects.locations.processors.processorVersions.process", "path": "v1beta3/{+name}:process", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}:process", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The resource name of the Processor or ProcessorVersion to use for processing. If a Processor is specified, the server will use its default version. Format: `projects/{project}/locations/{location}/processors/{processor}`, or `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessRequest" }, "response": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Processes a single document." }, "batchProcess": { "id": "documentai.projects.locations.processors.processorVersions.batchProcess", "path": "v1beta3/{+name}:batchProcess", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}:batchProcess", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The resource name of Processor or ProcessorVersion. Format: `projects/{project}/locations/{location}/processors/{processor}`, or `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3BatchProcessRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "LRO endpoint to batch process many documents. The output is written to Cloud Storage as JSON in the [Document] format." }, "train": { "id": "documentai.projects.locations.processors.processorVersions.train", "path": "v1beta3/{+parent}/processorVersions:train", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions:train", "httpMethod": "POST", "parameters": { "parent": { "description": "Required. The parent (project, location and processor) to create the new version for. Format: `projects/{project}/locations/{location}/processors/{processor}`.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "parent" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Trains a new processor version. Operation metadata is returned as TrainProcessorVersionMetadata." }, "get": { "id": "documentai.projects.locations.processors.processorVersions.get", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}", "httpMethod": "GET", "parameters": { "name": { "description": "Required. The processor resource name.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorVersion" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Gets a processor version detail." }, "list": { "id": "documentai.projects.locations.processors.processorVersions.list", "path": "v1beta3/{+parent}/processorVersions", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions", "httpMethod": "GET", "parameters": { "parent": { "description": "Required. The parent (project, location and processor) to list all versions. Format: `projects/{project}/locations/{location}/processors/{processor}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" }, "pageSize": { "description": "The maximum number of processor versions to return. If unspecified, at most `10` processor versions will be returned. The maximum value is `20`. Values above `20` will be coerced to `20`.", "location": "query", "type": "integer", "format": "int32" }, "pageToken": { "description": "We will return the processor versions sorted by creation time. The page token will point to the next processor version.", "location": "query", "type": "string" } }, "parameterOrder": [ "parent" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3ListProcessorVersionsResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Lists all versions of a processor." }, "delete": { "id": "documentai.projects.locations.processors.processorVersions.delete", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}", "httpMethod": "DELETE", "parameters": { "name": { "description": "Required. The processor version resource name to be deleted.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Deletes the processor version, all artifacts under the processor version will be deleted." }, "deploy": { "id": "documentai.projects.locations.processors.processorVersions.deploy", "path": "v1beta3/{+name}:deploy", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}:deploy", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The processor version resource name to be deployed.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3DeployProcessorVersionRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Deploys the processor version." }, "undeploy": { "id": "documentai.projects.locations.processors.processorVersions.undeploy", "path": "v1beta3/{+name}:undeploy", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}:undeploy", "httpMethod": "POST", "parameters": { "name": { "description": "Required. The processor version resource name to be undeployed.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Undeploys the processor version." }, "evaluateProcessorVersion": { "id": "documentai.projects.locations.processors.processorVersions.evaluateProcessorVersion", "path": "v1beta3/{+processorVersion}:evaluateProcessorVersion", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}:evaluateProcessorVersion", "httpMethod": "POST", "parameters": { "processorVersion": { "description": "Required. The resource name of the ProcessorVersion to evaluate. `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "processorVersion" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Evaluates a ProcessorVersion against annotated documents, producing an Evaluation." }, "importProcessorVersion": { "id": "documentai.projects.locations.processors.processorVersions.importProcessorVersion", "path": "v1beta3/{+parent}/processorVersions:importProcessorVersion", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions:importProcessorVersion", "httpMethod": "POST", "parameters": { "parent": { "description": "Required. The destination processor name to create the processor version in. Format: `projects/{project}/locations/{location}/processors/{processor}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "parent" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3ImportProcessorVersionRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Imports a processor version from source processor version." } }, "resources": { "evaluations": { "methods": { "get": { "id": "documentai.projects.locations.processors.processorVersions.evaluations.get", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}/evaluations/{evaluationsId}", "httpMethod": "GET", "parameters": { "name": { "description": "Required. The resource name of the Evaluation to get. `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}/evaluations/{evaluation}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+/evaluations/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3Evaluation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Retrieves a specific evaluation." }, "list": { "id": "documentai.projects.locations.processors.processorVersions.evaluations.list", "path": "v1beta3/{+parent}/evaluations", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/processorVersions/{processorVersionsId}/evaluations", "httpMethod": "GET", "parameters": { "parent": { "description": "Required. The resource name of the ProcessorVersion to list evaluations for. `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/processorVersions/[^/]+$", "location": "path", "required": true, "type": "string" }, "pageSize": { "description": "The standard list page size. If unspecified, at most `5` evaluations are returned. The maximum value is `100`. Values above `100` are coerced to `100`.", "location": "query", "type": "integer", "format": "int32" }, "pageToken": { "description": "A page token, received from a previous `ListEvaluations` call. Provide this to retrieve the subsequent page.", "location": "query", "type": "string" } }, "parameterOrder": [ "parent" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3ListEvaluationsResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Retrieves a set of evaluations for a given processor version." } } } } }, "humanReviewConfig": { "methods": { "reviewDocument": { "id": "documentai.projects.locations.processors.humanReviewConfig.reviewDocument", "path": "v1beta3/{+humanReviewConfig}:reviewDocument", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/humanReviewConfig:reviewDocument", "httpMethod": "POST", "parameters": { "humanReviewConfig": { "description": "Required. The resource name of the HumanReviewConfig that the document will be reviewed with.", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/humanReviewConfig$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "humanReviewConfig" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3ReviewDocumentRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Send a document for Human Review. The input document should be processed by the specified processor." } } }, "dataset": { "methods": { "importDocuments": { "id": "documentai.projects.locations.processors.dataset.importDocuments", "path": "v1beta3/{+dataset}:importDocuments", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset:importDocuments", "httpMethod": "POST", "parameters": { "dataset": { "description": "Required. The dataset resource name. Format: projects/{project}/locations/{location}/processors/{processor}/dataset", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "dataset" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3ImportDocumentsRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Import documents into a dataset." }, "getDocument": { "id": "documentai.projects.locations.processors.dataset.getDocument", "path": "v1beta3/{+dataset}:getDocument", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset:getDocument", "httpMethod": "GET", "parameters": { "dataset": { "description": "Required. The resource name of the dataset that the document belongs to . Format: projects/{project}/locations/{location}/processors/{processor}/dataset", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset$", "location": "path", "required": true, "type": "string" }, "documentId.gcsManagedDocId.gcsUri": { "description": "Required. The Cloud Storage URI where the actual document is stored.", "location": "query", "type": "string" }, "documentId.gcsManagedDocId.cwDocId": { "description": "Id of the document (indexed) managed by Content Warehouse.", "location": "query", "deprecated": true, "type": "string" }, "documentId.unmanagedDocId.docId": { "description": "Required. The id of the document.", "location": "query", "type": "string" }, "documentId.revisionRef.revisionCase": { "description": "Reads the revision by the predefined case.", "location": "query", "type": "string", "enumDescriptions": [ "Unspecified case, fall back to read the `LATEST_HUMAN_REVIEW`.", "The latest revision made by a human.", "The latest revision based on timestamp.", "The first (OCR) revision." ], "enum": [ "REVISION_CASE_UNSPECIFIED", "LATEST_HUMAN_REVIEW", "LATEST_TIMESTAMP", "BASE_OCR_REVISION" ] }, "documentId.revisionRef.revisionId": { "description": "Reads the revision given by the id.", "location": "query", "type": "string" }, "documentId.revisionRef.latestProcessorVersion": { "description": "Reads the revision generated by the processor version. The format takes the full resource name of processor version. `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "location": "query", "type": "string" }, "readMask": { "description": "If set, only fields listed here will be returned. Otherwise, all fields will be returned by default.", "location": "query", "type": "string", "format": "google-fieldmask" }, "pageRange.start": { "description": "First page number (one-based index) to be returned.", "location": "query", "type": "integer", "format": "int32" }, "pageRange.end": { "description": "Last page number (one-based index) to be returned.", "location": "query", "type": "integer", "format": "int32" } }, "parameterOrder": [ "dataset" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3GetDocumentResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Returns relevant fields present in the requested document." }, "listDocuments": { "id": "documentai.projects.locations.processors.dataset.listDocuments", "path": "v1beta3/{+dataset}:listDocuments", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset:listDocuments", "httpMethod": "POST", "parameters": { "dataset": { "description": "Required. The resource name of the dataset to be listed. Format: projects/{project}/locations/{location}/processors/{processor}/dataset", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "dataset" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3ListDocumentsRequest" }, "response": { "$ref": "GoogleCloudDocumentaiV1beta3ListDocumentsResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Returns a list of documents present in the dataset." }, "batchDeleteDocuments": { "id": "documentai.projects.locations.processors.dataset.batchDeleteDocuments", "path": "v1beta3/{+dataset}:batchDeleteDocuments", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset:batchDeleteDocuments", "httpMethod": "POST", "parameters": { "dataset": { "description": "Required. The dataset resource name. Format: projects/{project}/locations/{location}/processors/{processor}/dataset", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "dataset" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsRequest" }, "response": { "$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Deletes a set of documents." }, "getDatasetSchema": { "id": "documentai.projects.locations.processors.dataset.getDatasetSchema", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset/datasetSchema", "httpMethod": "GET", "parameters": { "name": { "description": "Required. The dataset schema resource name. Format: projects/{project}/locations/{location}/processors/{processor}/dataset/datasetSchema", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset/datasetSchema$", "location": "path", "required": true, "type": "string" }, "visibleFieldsOnly": { "description": "If set, only returns the visible fields of the schema.", "location": "query", "type": "boolean" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3DatasetSchema" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Gets the `DatasetSchema` of a `Dataset`." }, "updateDatasetSchema": { "id": "documentai.projects.locations.processors.dataset.updateDatasetSchema", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processors/{processorsId}/dataset/datasetSchema", "httpMethod": "PATCH", "parameters": { "name": { "description": "Dataset schema resource name. Format: `projects/{project}/locations/{location}/processors/{processor}/dataset/datasetSchema`", "pattern": "^projects/[^/]+/locations/[^/]+/processors/[^/]+/dataset/datasetSchema$", "location": "path", "required": true, "type": "string" }, "updateMask": { "description": "The update mask applies to the resource.", "location": "query", "type": "string", "format": "google-fieldmask" } }, "parameterOrder": [ "name" ], "request": { "$ref": "GoogleCloudDocumentaiV1beta3DatasetSchema" }, "response": { "$ref": "GoogleCloudDocumentaiV1beta3DatasetSchema" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Updates a `DatasetSchema`." } } } } }, "processorTypes": { "methods": { "list": { "id": "documentai.projects.locations.processorTypes.list", "path": "v1beta3/{+parent}/processorTypes", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processorTypes", "httpMethod": "GET", "parameters": { "parent": { "description": "Required. The location of processor types to list. Format: `projects/{project}/locations/{location}`.", "pattern": "^projects/[^/]+/locations/[^/]+$", "location": "path", "required": true, "type": "string" }, "pageSize": { "description": "The maximum number of processor types to return. If unspecified, at most `100` processor types will be returned. The maximum value is `500`. Values above `500` will be coerced to `500`.", "location": "query", "type": "integer", "format": "int32" }, "pageToken": { "description": "Used to retrieve the next page of results, empty if at the end of the list.", "location": "query", "type": "string" } }, "parameterOrder": [ "parent" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3ListProcessorTypesResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Lists the processor types that exist." }, "get": { "id": "documentai.projects.locations.processorTypes.get", "path": "v1beta3/{+name}", "flatPath": "v1beta3/projects/{projectsId}/locations/{locationsId}/processorTypes/{processorTypesId}", "httpMethod": "GET", "parameters": { "name": { "description": "Required. The processor type resource name.", "pattern": "^projects/[^/]+/locations/[^/]+/processorTypes/[^/]+$", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "name" ], "response": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorType" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ], "description": "Gets a processor type detail." } } } } } } } }, "auth": { "oauth2": { "scopes": { "https://www.googleapis.com/auth/cloud-platform": { "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account." } } } }, "mtlsRootUrl": "https://documentai.mtls.googleapis.com/", "kind": "discovery#restDescription", "schemas": { "GoogleLongrunningListOperationsResponse": { "id": "GoogleLongrunningListOperationsResponse", "description": "The response message for Operations.ListOperations.", "type": "object", "properties": { "operations": { "description": "A list of operations that matches the specified filter in the request.", "type": "array", "items": { "$ref": "GoogleLongrunningOperation" } }, "nextPageToken": { "description": "The standard List next-page token.", "type": "string" } } }, "GoogleLongrunningOperation": { "id": "GoogleLongrunningOperation", "description": "This resource represents a long-running operation that is the result of a network API call.", "type": "object", "properties": { "name": { "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.", "type": "string" }, "metadata": { "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "done": { "description": "If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.", "type": "boolean" }, "error": { "description": "The error result of the operation in case of failure or cancellation.", "$ref": "GoogleRpcStatus" }, "response": { "description": "The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.", "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } } } }, "GoogleRpcStatus": { "id": "GoogleRpcStatus", "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).", "type": "object", "properties": { "code": { "description": "The status code, which should be an enum value of google.rpc.Code.", "type": "integer", "format": "int32" }, "message": { "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.", "type": "string" }, "details": { "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.", "type": "array", "items": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } } } } }, "GoogleProtobufEmpty": { "id": "GoogleProtobufEmpty", "description": "A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3ProcessRequest": { "id": "GoogleCloudDocumentaiV1beta3ProcessRequest", "description": "Request message for the ProcessDocument method.", "type": "object", "properties": { "inlineDocument": { "description": "An inline document proto.", "$ref": "GoogleCloudDocumentaiV1beta3Document" }, "rawDocument": { "description": "A raw document content (bytes).", "$ref": "GoogleCloudDocumentaiV1beta3RawDocument" }, "gcsDocument": { "description": "A raw document on Google Cloud Storage.", "$ref": "GoogleCloudDocumentaiV1beta3GcsDocument" }, "document": { "description": "The document payload, the content and mime_type fields must be set.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3Document" }, "skipHumanReview": { "description": "Whether human review should be skipped for this request. Default to `false`.", "type": "boolean" }, "fieldMask": { "description": "Specifies which fields to include in the ProcessResponse.document output. Only supports top-level document and pages field, so it must be in the form of `{document_field_name}` or `pages.{page_field_name}`.", "type": "string", "format": "google-fieldmask" }, "processOptions": { "description": "Inference-time options for the process API", "$ref": "GoogleCloudDocumentaiV1beta3ProcessOptions" }, "labels": { "description": "Optional. The labels with user-defined metadata for the request. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.", "type": "object", "additionalProperties": { "type": "string" } } } }, "GoogleCloudDocumentaiV1beta3Document": { "id": "GoogleCloudDocumentaiV1beta3Document", "description": "Document represents the canonical document resource in Document AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document AI to iterate and optimize for quality.", "type": "object", "properties": { "uri": { "description": "Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. For more information, refer to [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris).", "type": "string" }, "content": { "description": "Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.", "type": "string", "format": "byte" }, "mimeType": { "description": "An IANA published [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml).", "type": "string" }, "text": { "description": "Optional. UTF-8 encoded text in reading order from the document.", "type": "string" }, "textStyles": { "description": "Styles for the Document.text.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentStyle" } }, "pages": { "description": "Visual page layout for the Document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPage" } }, "entities": { "description": "A list of entities detected on Document.text. For document shards, entities in this list may cross shard boundaries.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentEntity" } }, "entityRelations": { "description": "Placeholder. Relationship among Document.entities.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentEntityRelation" } }, "textChanges": { "description": "Placeholder. A list of text corrections made to Document.text. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentTextChange" } }, "shardInfo": { "description": "Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentShardInfo" }, "error": { "description": "Any error that occurred while processing this document.", "$ref": "GoogleRpcStatus" }, "revisions": { "description": "Placeholder. Revision history of this document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentRevision" } }, "documentLayout": { "description": "Parsed layout of the document.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayout" }, "chunkedDocument": { "description": "Document chunked based on chunking config.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocument" } } }, "GoogleCloudDocumentaiV1beta3DocumentStyle": { "id": "GoogleCloudDocumentaiV1beta3DocumentStyle", "description": "Annotation for common text style attributes. This adheres to CSS conventions as much as possible.", "type": "object", "properties": { "textAnchor": { "description": "Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentTextAnchor" }, "color": { "description": "Text color.", "$ref": "GoogleTypeColor" }, "backgroundColor": { "description": "Text background color.", "$ref": "GoogleTypeColor" }, "fontWeight": { "description": "[Font weight](https://www.w3schools.com/cssref/pr_font_weight.asp). Possible values are `normal`, `bold`, `bolder`, and `lighter`.", "type": "string" }, "textStyle": { "description": "[Text style](https://www.w3schools.com/cssref/pr_font_font-style.asp). Possible values are `normal`, `italic`, and `oblique`.", "type": "string" }, "textDecoration": { "description": "[Text decoration](https://www.w3schools.com/cssref/pr_text_text-decoration.asp). Follows CSS standard. ", "type": "string" }, "fontSize": { "description": "Font size.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentStyleFontSize" }, "fontFamily": { "description": "Font family such as `Arial`, `Times New Roman`. https://www.w3schools.com/cssref/pr_font_font-family.asp", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentTextAnchor": { "id": "GoogleCloudDocumentaiV1beta3DocumentTextAnchor", "description": "Text reference indexing into the Document.text.", "type": "object", "properties": { "textSegments": { "description": "The text segments from the Document.text.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentTextAnchorTextSegment" } }, "content": { "description": "Contains the content of the text span so that users do not have to look it up in the text_segments. It is always populated for formFields.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentTextAnchorTextSegment": { "id": "GoogleCloudDocumentaiV1beta3DocumentTextAnchorTextSegment", "description": "A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset", "type": "object", "properties": { "startIndex": { "description": "TextSegment start UTF-8 char index in the Document.text.", "type": "string", "format": "int64" }, "endIndex": { "description": "TextSegment half open end UTF-8 char index in the Document.text.", "type": "string", "format": "int64" } } }, "GoogleTypeColor": { "id": "GoogleTypeColor", "description": "Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to and from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of `java.awt.Color` in Java; it can also be trivially provided to UIColor's `+colorWithRed:green:blue:alpha` method in iOS; and, with just a little work, it can be easily formatted into a CSS `rgba()` string in JavaScript. This reference page doesn't have information about the absolute color space that should be used to interpret the RGB value—for example, sRGB, Adobe RGB, DCI-P3, and BT.2020. By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most `1e-5`. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha \u003c= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red \u003c\u003c 16) | (green \u003c\u003c 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i \u003c missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ...", "type": "object", "properties": { "red": { "description": "The amount of red in the color as a value in the interval [0, 1].", "type": "number", "format": "float" }, "green": { "description": "The amount of green in the color as a value in the interval [0, 1].", "type": "number", "format": "float" }, "blue": { "description": "The amount of blue in the color as a value in the interval [0, 1].", "type": "number", "format": "float" }, "alpha": { "description": "The fraction of this color that should be applied to the pixel. That is, the final pixel color is defined by the equation: `pixel color = alpha * (this color) + (1.0 - alpha) * (background color)` This means that a value of 1.0 corresponds to a solid color, whereas a value of 0.0 corresponds to a completely transparent color. This uses a wrapper message rather than a simple float scalar so that it is possible to distinguish between a default value and the value being unset. If omitted, this color object is rendered as a solid color (as if the alpha value had been explicitly given a value of 1.0).", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3DocumentStyleFontSize": { "id": "GoogleCloudDocumentaiV1beta3DocumentStyleFontSize", "description": "Font size with unit.", "type": "object", "properties": { "size": { "description": "Font size for the text.", "type": "number", "format": "float" }, "unit": { "description": "Unit for the font size. Follows CSS naming (such as `in`, `px`, and `pt`).", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentPage": { "id": "GoogleCloudDocumentaiV1beta3DocumentPage", "description": "A page in a Document.", "type": "object", "properties": { "pageNumber": { "description": "1-based index for current Page in a parent Document. Useful when a page is taken out of a Document for individual processing.", "type": "integer", "format": "int32" }, "image": { "description": "Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageImage" }, "transforms": { "description": "Transformation matrices that were applied to the original document image to produce Page.image.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageMatrix" } }, "dimension": { "description": "Physical dimension of the page.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDimension" }, "layout": { "description": "Layout for the page.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "blocks": { "description": "A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageBlock" } }, "paragraphs": { "description": "A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageParagraph" } }, "lines": { "description": "A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLine" } }, "tokens": { "description": "A list of visually detected tokens on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageToken" } }, "visualElements": { "description": "A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageVisualElement" } }, "tables": { "description": "A list of visually detected tables on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageTable" } }, "formFields": { "description": "A list of visually detected form fields on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageFormField" } }, "symbols": { "description": "A list of visually detected symbols on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageSymbol" } }, "detectedBarcodes": { "description": "A list of detected barcodes.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedBarcode" } }, "imageQualityScores": { "description": "Image quality scores.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageImageQualityScores" }, "provenance": { "description": "The history of this page.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageImage": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageImage", "description": "Rendered image contents for this page.", "type": "object", "properties": { "content": { "description": "Raw byte content of the image.", "type": "string", "format": "byte" }, "mimeType": { "description": "Encoding [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml) for the image.", "type": "string" }, "width": { "description": "Width of the image in pixels.", "type": "integer", "format": "int32" }, "height": { "description": "Height of the image in pixels.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageMatrix": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageMatrix", "description": "Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.", "type": "object", "properties": { "rows": { "description": "Number of rows in the matrix.", "type": "integer", "format": "int32" }, "cols": { "description": "Number of columns in the matrix.", "type": "integer", "format": "int32" }, "type": { "description": "This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html", "type": "integer", "format": "int32" }, "data": { "description": "The matrix data.", "type": "string", "format": "byte" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageDimension": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageDimension", "description": "Dimension for the page.", "type": "object", "properties": { "width": { "description": "Page width.", "type": "number", "format": "float" }, "height": { "description": "Page height.", "type": "number", "format": "float" }, "unit": { "description": "Dimension unit.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageLayout": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageLayout", "description": "Visual element describing a layout unit on a page.", "type": "object", "properties": { "textAnchor": { "description": "Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentTextAnchor" }, "confidence": { "description": "Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range `[0, 1]`.", "type": "number", "format": "float" }, "boundingPoly": { "description": "The bounding polygon for the Layout.", "$ref": "GoogleCloudDocumentaiV1beta3BoundingPoly" }, "orientation": { "description": "Detected orientation for the Layout.", "type": "string", "enumDescriptions": [ "Unspecified orientation.", "Orientation is aligned with page up.", "Orientation is aligned with page right. Turn the head 90 degrees clockwise from upright to read.", "Orientation is aligned with page down. Turn the head 180 degrees from upright to read.", "Orientation is aligned with page left. Turn the head 90 degrees counterclockwise from upright to read." ], "enum": [ "ORIENTATION_UNSPECIFIED", "PAGE_UP", "PAGE_RIGHT", "PAGE_DOWN", "PAGE_LEFT" ] } } }, "GoogleCloudDocumentaiV1beta3BoundingPoly": { "id": "GoogleCloudDocumentaiV1beta3BoundingPoly", "description": "A bounding polygon for the detected image annotation.", "type": "object", "properties": { "vertices": { "description": "The bounding polygon vertices.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3Vertex" } }, "normalizedVertices": { "description": "The bounding polygon normalized vertices.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3NormalizedVertex" } } } }, "GoogleCloudDocumentaiV1beta3Vertex": { "id": "GoogleCloudDocumentaiV1beta3Vertex", "description": "A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "integer", "format": "int32" }, "y": { "description": "Y coordinate (starts from the top of the image).", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3NormalizedVertex": { "id": "GoogleCloudDocumentaiV1beta3NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "number", "format": "float" }, "y": { "description": "Y coordinate (starts from the top of the image).", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage", "description": "Detected language for a structural component.", "type": "object", "properties": { "languageCode": { "description": "The [BCP-47 language code](https://www.unicode.org/reports/tr35/#Unicode_locale_identifier), such as `en-US` or `sr-Latn`.", "type": "string" }, "confidence": { "description": "Confidence of detected language. Range `[0, 1]`.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageBlock": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageBlock", "description": "A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.", "type": "object", "properties": { "layout": { "description": "Layout for Block.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta3DocumentProvenance": { "id": "GoogleCloudDocumentaiV1beta3DocumentProvenance", "description": "Structure to identify provenance relationships between annotations in different revisions.", "type": "object", "properties": { "revision": { "description": "The index of the revision that produced this element.", "deprecated": true, "type": "integer", "format": "int32" }, "id": { "description": "The Id of this operation. Needs to be unique within the scope of the revision.", "deprecated": true, "type": "integer", "format": "int32" }, "parents": { "description": "References to the original elements that are replaced.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenanceParent" } }, "type": { "description": "The type of provenance operation.", "type": "string", "enumDescriptions": [ "Operation type unspecified. If no operation is specified a provenance entry is simply used to match against a `parent`.", "Add an element.", "Remove an element identified by `parent`.", "Updates any fields within the given provenance scope of the message. It overwrites the fields rather than replacing them. Use this when you want to update a field value of an entity without also updating all the child properties.", "Currently unused. Replace an element identified by `parent`.", "Deprecated. Request human review for the element identified by `parent`.", "Deprecated. Element is reviewed and approved at human review, confidence will be set to 1.0.", "Deprecated. Element is skipped in the validation process." ], "enumDeprecated": [ false, false, false, false, false, true, true, true ], "enum": [ "OPERATION_TYPE_UNSPECIFIED", "ADD", "REMOVE", "UPDATE", "REPLACE", "EVAL_REQUESTED", "EVAL_APPROVED", "EVAL_SKIPPED" ] } } }, "GoogleCloudDocumentaiV1beta3DocumentProvenanceParent": { "id": "GoogleCloudDocumentaiV1beta3DocumentProvenanceParent", "description": "The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.", "type": "object", "properties": { "revision": { "description": "The index of the index into current revision's parent_ids list.", "type": "integer", "format": "int32" }, "index": { "description": "The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) in the parent revision.", "type": "integer", "format": "int32" }, "id": { "description": "The id of the parent provenance.", "deprecated": true, "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageParagraph": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageParagraph", "description": "A collection of lines that a human would perceive as a paragraph.", "type": "object", "properties": { "layout": { "description": "Layout for Paragraph.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageLine": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageLine", "description": "A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.", "type": "object", "properties": { "layout": { "description": "Layout for Line.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageToken": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageToken", "description": "A detected token.", "type": "object", "properties": { "layout": { "description": "Layout for Token.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "detectedBreak": { "description": "Detected break at the end of a Token.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageTokenDetectedBreak" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" }, "styleInfo": { "description": "Text style attributes.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageTokenStyleInfo" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageTokenDetectedBreak": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageTokenDetectedBreak", "description": "Detected break at the end of a Token.", "type": "object", "properties": { "type": { "description": "Detected break type.", "type": "string", "enumDescriptions": [ "Unspecified break type.", "A single whitespace.", "A wider whitespace.", "A hyphen that indicates that a token has been split across lines." ], "enum": [ "TYPE_UNSPECIFIED", "SPACE", "WIDE_SPACE", "HYPHEN" ] } } }, "GoogleCloudDocumentaiV1beta3DocumentPageTokenStyleInfo": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageTokenStyleInfo", "description": "Font and other text style attributes.", "type": "object", "properties": { "fontSize": { "description": "Font size in points (`1` point is `¹⁄₇₂` inches).", "type": "integer", "format": "int32" }, "pixelFontSize": { "description": "Font size in pixels, equal to _unrounded font_size_ * _resolution_ ÷ `72.0`.", "type": "number", "format": "double" }, "letterSpacing": { "description": "Letter spacing in points.", "type": "number", "format": "double" }, "fontType": { "description": "Name or style of the font.", "type": "string" }, "bold": { "description": "Whether the text is bold (equivalent to font_weight is at least `700`).", "type": "boolean" }, "italic": { "description": "Whether the text is italic.", "type": "boolean" }, "underlined": { "description": "Whether the text is underlined.", "type": "boolean" }, "strikeout": { "description": "Whether the text is strikethrough. This feature is not supported yet.", "type": "boolean" }, "subscript": { "description": "Whether the text is a subscript. This feature is not supported yet.", "type": "boolean" }, "superscript": { "description": "Whether the text is a superscript. This feature is not supported yet.", "type": "boolean" }, "smallcaps": { "description": "Whether the text is in small caps. This feature is not supported yet.", "type": "boolean" }, "fontWeight": { "description": "TrueType weight on a scale `100` (thin) to `1000` (ultra-heavy). Normal is `400`, bold is `700`.", "type": "integer", "format": "int32" }, "handwritten": { "description": "Whether the text is handwritten.", "type": "boolean" }, "textColor": { "description": "Color of the text.", "$ref": "GoogleTypeColor" }, "backgroundColor": { "description": "Color of the background.", "$ref": "GoogleTypeColor" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageVisualElement": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageVisualElement", "description": "Detected non-text visual elements e.g. checkbox, signature etc. on the page.", "type": "object", "properties": { "layout": { "description": "Layout for VisualElement.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "type": { "description": "Type of the VisualElement.", "type": "string" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta3DocumentPageTable": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageTable", "description": "A table representation similar to HTML table structure.", "type": "object", "properties": { "layout": { "description": "Layout for Table.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "headerRows": { "description": "Header rows of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageTableTableRow" } }, "bodyRows": { "description": "Body rows of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageTableTableRow" } }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this table.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageTableTableRow": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageTableTableRow", "description": "A row of table cells.", "type": "object", "properties": { "cells": { "description": "Cells that make up this row.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageTableTableCell" } } } }, "GoogleCloudDocumentaiV1beta3DocumentPageTableTableCell": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageTableTableCell", "description": "A cell representation inside the table.", "type": "object", "properties": { "layout": { "description": "Layout for TableCell.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "rowSpan": { "description": "How many rows this cell spans.", "type": "integer", "format": "int32" }, "colSpan": { "description": "How many columns this cell spans.", "type": "integer", "format": "int32" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta3DocumentPageFormField": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageFormField", "description": "A form field detected on the page.", "type": "object", "properties": { "fieldName": { "description": "Layout for the FormField name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "fieldValue": { "description": "Layout for the FormField value.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "nameDetectedLanguages": { "description": "A list of detected languages for name together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "valueDetectedLanguages": { "description": "A list of detected languages for value together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } }, "valueType": { "description": "If the value is non-textual, this field represents the type. Current valid values are: - blank (this indicates the `field_value` is normal text) - `unfilled_checkbox` - `filled_checkbox`", "type": "string" }, "correctedKeyText": { "description": "Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.", "type": "string" }, "correctedValueText": { "description": "Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.", "type": "string" }, "provenance": { "description": "The history of this annotation.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageSymbol": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageSymbol", "description": "A detected symbol.", "type": "object", "properties": { "layout": { "description": "Layout for Symbol.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta3DocumentPageDetectedBarcode": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageDetectedBarcode", "description": "A detected barcode.", "type": "object", "properties": { "layout": { "description": "Layout for DetectedBarcode.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageLayout" }, "barcode": { "description": "Detailed barcode information of the DetectedBarcode.", "$ref": "GoogleCloudDocumentaiV1beta3Barcode" } } }, "GoogleCloudDocumentaiV1beta3Barcode": { "id": "GoogleCloudDocumentaiV1beta3Barcode", "description": "Encodes the detailed information of a barcode.", "type": "object", "properties": { "format": { "description": "Format of a barcode. The supported formats are: - `CODE_128`: Code 128 type. - `CODE_39`: Code 39 type. - `CODE_93`: Code 93 type. - `CODABAR`: Codabar type. - `DATA_MATRIX`: 2D Data Matrix type. - `ITF`: ITF type. - `EAN_13`: EAN-13 type. - `EAN_8`: EAN-8 type. - `QR_CODE`: 2D QR code type. - `UPC_A`: UPC-A type. - `UPC_E`: UPC-E type. - `PDF417`: PDF417 type. - `AZTEC`: 2D Aztec code type. - `DATABAR`: GS1 DataBar code type.", "type": "string" }, "valueFormat": { "description": "Value format describes the format of the value that a barcode encodes. The supported formats are: - `CONTACT_INFO`: Contact information. - `EMAIL`: Email address. - `ISBN`: ISBN identifier. - `PHONE`: Phone number. - `PRODUCT`: Product. - `SMS`: SMS message. - `TEXT`: Text string. - `URL`: URL address. - `WIFI`: Wifi information. - `GEO`: Geo-localization. - `CALENDAR_EVENT`: Calendar event. - `DRIVER_LICENSE`: Driver's license.", "type": "string" }, "rawValue": { "description": "Raw value encoded in the barcode. For example: `'MEBKM:TITLE:Google;URL:https://www.google.com;;'`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageImageQualityScores": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageImageQualityScores", "description": "Image quality scores for the page image.", "type": "object", "properties": { "qualityScore": { "description": "The overall quality score. Range `[0, 1]` where `1` is perfect quality.", "type": "number", "format": "float" }, "detectedDefects": { "description": "A list of detected defects.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageImageQualityScoresDetectedDefect" } } } }, "GoogleCloudDocumentaiV1beta3DocumentPageImageQualityScoresDetectedDefect": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageImageQualityScoresDetectedDefect", "description": "Image Quality Defects", "type": "object", "properties": { "type": { "description": "Name of the defect type. Supported values are: - `quality/defect_blurry` - `quality/defect_noisy` - `quality/defect_dark` - `quality/defect_faint` - `quality/defect_text_too_small` - `quality/defect_document_cutoff` - `quality/defect_text_cutoff` - `quality/defect_glare`", "type": "string" }, "confidence": { "description": "Confidence of detected defect. Range `[0, 1]` where `1` indicates strong confidence that the defect exists.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3DocumentEntity": { "id": "GoogleCloudDocumentaiV1beta3DocumentEntity", "description": "An entity that could be a phrase in the text or a property that belongs to the document. It is a known entity type, such as a person, an organization, or location.", "type": "object", "properties": { "textAnchor": { "description": "Optional. Provenance of the entity. Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentTextAnchor" }, "type": { "description": "Required. Entity type from a schema e.g. `Address`.", "type": "string" }, "mentionText": { "description": "Optional. Text value of the entity e.g. `1600 Amphitheatre Pkwy`.", "type": "string" }, "mentionId": { "description": "Optional. Deprecated. Use `id` field instead.", "type": "string" }, "confidence": { "description": "Optional. Confidence of detected Schema entity. Range `[0, 1]`.", "type": "number", "format": "float" }, "pageAnchor": { "description": "Optional. Represents the provenance of this entity wrt. the location on the page where it was found.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageAnchor" }, "id": { "description": "Optional. Canonical id. This will be a unique value in the entity list for this document.", "type": "string" }, "normalizedValue": { "description": "Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentEntityNormalizedValue" }, "properties": { "description": "Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentEntity" } }, "provenance": { "description": "Optional. The history of this annotation.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" }, "redacted": { "description": "Optional. Whether the entity will be redacted for de-identification purposes.", "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3DocumentPageAnchor": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageAnchor", "description": "Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types.", "type": "object", "properties": { "pageRefs": { "description": "One or more references to visual page elements", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentPageAnchorPageRef" } } } }, "GoogleCloudDocumentaiV1beta3DocumentPageAnchorPageRef": { "id": "GoogleCloudDocumentaiV1beta3DocumentPageAnchorPageRef", "description": "Represents a weak reference to a page element within a document.", "type": "object", "properties": { "page": { "description": "Required. Index into the Document.pages element, for example using `Document.pages` to locate the related page element. This field is skipped when its value is the default `0`. See https://developers.google.com/protocol-buffers/docs/proto3#json.", "type": "string", "format": "int64" }, "layoutType": { "description": "Optional. The type of the layout element that is being referenced if any.", "type": "string", "enumDescriptions": [ "Layout Unspecified.", "References a Page.blocks element.", "References a Page.paragraphs element.", "References a Page.lines element.", "References a Page.tokens element.", "References a Page.visual_elements element.", "Refrrences a Page.tables element.", "References a Page.form_fields element." ], "enum": [ "LAYOUT_TYPE_UNSPECIFIED", "BLOCK", "PARAGRAPH", "LINE", "TOKEN", "VISUAL_ELEMENT", "TABLE", "FORM_FIELD" ] }, "layoutId": { "description": "Optional. Deprecated. Use PageRef.bounding_poly instead.", "deprecated": true, "type": "string" }, "boundingPoly": { "description": "Optional. Identifies the bounding polygon of a layout element on the page. If `layout_type` is set, the bounding polygon must be exactly the same to the layout element it's referring to.", "$ref": "GoogleCloudDocumentaiV1beta3BoundingPoly" }, "confidence": { "description": "Optional. Confidence of detected page element, if applicable. Range `[0, 1]`.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3DocumentEntityNormalizedValue": { "id": "GoogleCloudDocumentaiV1beta3DocumentEntityNormalizedValue", "description": "Parsed and normalized entity value.", "type": "object", "properties": { "moneyValue": { "description": "Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto", "$ref": "GoogleTypeMoney" }, "dateValue": { "description": "Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto", "$ref": "GoogleTypeDate" }, "datetimeValue": { "description": "DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto", "$ref": "GoogleTypeDateTime" }, "addressValue": { "description": "Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto", "$ref": "GoogleTypePostalAddress" }, "booleanValue": { "description": "Boolean value. Can be used for entities with binary values, or for checkboxes.", "type": "boolean" }, "integerValue": { "description": "Integer value.", "type": "integer", "format": "int32" }, "floatValue": { "description": "Float value.", "type": "number", "format": "float" }, "text": { "description": "Optional. An optional field to store a normalized string. For some entity types, one of respective `structured_value` fields may also be populated. Also not all the types of `structured_value` will be normalized. For example, some processors may not generate `float` or `integer` normalized text by default. Below are sample formats mapped to structured values. - Money/Currency type (`money_value`) is in the ISO 4217 text format. - Date type (`date_value`) is in the ISO 8601 text format. - Datetime type (`datetime_value`) is in the ISO 8601 text format.", "type": "string" } } }, "GoogleTypeMoney": { "id": "GoogleTypeMoney", "description": "Represents an amount of money with its currency type.", "type": "object", "properties": { "currencyCode": { "description": "The three-letter currency code defined in ISO 4217.", "type": "string" }, "units": { "description": "The whole units of the amount. For example if `currencyCode` is `\"USD\"`, then 1 unit is one US dollar.", "type": "string", "format": "int64" }, "nanos": { "description": "Number of nano (10^-9) units of the amount. The value must be between -999,999,999 and +999,999,999 inclusive. If `units` is positive, `nanos` must be positive or zero. If `units` is zero, `nanos` can be positive, zero, or negative. If `units` is negative, `nanos` must be negative or zero. For example $-1.75 is represented as `units`=-1 and `nanos`=-750,000,000.", "type": "integer", "format": "int32" } } }, "GoogleTypeDate": { "id": "GoogleTypeDate", "description": "Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp", "type": "object", "properties": { "year": { "description": "Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.", "type": "integer", "format": "int32" }, "month": { "description": "Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.", "type": "integer", "format": "int32" }, "day": { "description": "Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.", "type": "integer", "format": "int32" } } }, "GoogleTypeDateTime": { "id": "GoogleTypeDateTime", "description": "Represents civil time (or occasionally physical time). This type can represent a civil time in one of a few possible ways: * When utc_offset is set and time_zone is unset: a civil time on a calendar day with a particular offset from UTC. * When time_zone is set and utc_offset is unset: a civil time on a calendar day in a particular time zone. * When neither time_zone nor utc_offset is set: a civil time on a calendar day in local time. The date is relative to the Proleptic Gregorian Calendar. If year, month, or day are 0, the DateTime is considered not to have a specific year, month, or day respectively. This type may also be used to represent a physical time if all the date and time fields are set and either case of the `time_offset` oneof is set. Consider using `Timestamp` message for physical time instead. If your use case also would like to store the user's timezone, that can be done in another field. This type is more flexible than some applications may want. Make sure to document and validate your application's limitations.", "type": "object", "properties": { "year": { "description": "Optional. Year of date. Must be from 1 to 9999, or 0 if specifying a datetime without a year.", "type": "integer", "format": "int32" }, "month": { "description": "Optional. Month of year. Must be from 1 to 12, or 0 if specifying a datetime without a month.", "type": "integer", "format": "int32" }, "day": { "description": "Optional. Day of month. Must be from 1 to 31 and valid for the year and month, or 0 if specifying a datetime without a day.", "type": "integer", "format": "int32" }, "hours": { "description": "Optional. Hours of day in 24 hour format. Should be from 0 to 23, defaults to 0 (midnight). An API may choose to allow the value \"24:00:00\" for scenarios like business closing time.", "type": "integer", "format": "int32" }, "minutes": { "description": "Optional. Minutes of hour of day. Must be from 0 to 59, defaults to 0.", "type": "integer", "format": "int32" }, "seconds": { "description": "Optional. Seconds of minutes of the time. Must normally be from 0 to 59, defaults to 0. An API may allow the value 60 if it allows leap-seconds.", "type": "integer", "format": "int32" }, "nanos": { "description": "Optional. Fractions of seconds in nanoseconds. Must be from 0 to 999,999,999, defaults to 0.", "type": "integer", "format": "int32" }, "utcOffset": { "description": "UTC offset. Must be whole seconds, between -18 hours and +18 hours. For example, a UTC offset of -4:00 would be represented as { seconds: -14400 }.", "type": "string", "format": "google-duration" }, "timeZone": { "description": "Time zone.", "$ref": "GoogleTypeTimeZone" } } }, "GoogleTypeTimeZone": { "id": "GoogleTypeTimeZone", "description": "Represents a time zone from the [IANA Time Zone Database](https://www.iana.org/time-zones).", "type": "object", "properties": { "id": { "description": "IANA Time Zone Database time zone, e.g. \"America/New_York\".", "type": "string" }, "version": { "description": "Optional. IANA Time Zone Database version number, e.g. \"2019a\".", "type": "string" } } }, "GoogleTypePostalAddress": { "id": "GoogleTypePostalAddress", "description": "Represents a postal address, e.g. for postal delivery or payments addresses. Given a postal address, a postal service can deliver items to a premise, P.O. Box or similar. It is not intended to model geographical locations (roads, towns, mountains). In typical usage an address would be created via user input or from importing existing data, depending on the type of process. Advice on address input / editing: - Use an internationalization-ready address widget such as https://github.com/google/libaddressinput) - Users should not be presented with UI elements for input or editing of fields outside countries where that field is used. For more guidance on how to use this schema, please see: https://support.google.com/business/answer/6397478", "type": "object", "properties": { "revision": { "description": "The schema revision of the `PostalAddress`. This must be set to 0, which is the latest revision. All new revisions **must** be backward compatible with old revisions.", "type": "integer", "format": "int32" }, "regionCode": { "description": "Required. CLDR region code of the country/region of the address. This is never inferred and it is up to the user to ensure the value is correct. See https://cldr.unicode.org/ and https://www.unicode.org/cldr/charts/30/supplemental/territory_information.html for details. Example: \"CH\" for Switzerland.", "type": "string" }, "languageCode": { "description": "Optional. BCP-47 language code of the contents of this address (if known). This is often the UI language of the input form or is expected to match one of the languages used in the address' country/region, or their transliterated equivalents. This can affect formatting in certain countries, but is not critical to the correctness of the data and will never affect any validation or other non-formatting related operations. If this value is not known, it should be omitted (rather than specifying a possibly incorrect default). Examples: \"zh-Hant\", \"ja\", \"ja-Latn\", \"en\".", "type": "string" }, "postalCode": { "description": "Optional. Postal code of the address. Not all countries use or require postal codes to be present, but where they are used, they may trigger additional validation with other parts of the address (e.g. state/zip validation in the U.S.A.).", "type": "string" }, "sortingCode": { "description": "Optional. Additional, country-specific, sorting code. This is not used in most regions. Where it is used, the value is either a string like \"CEDEX\", optionally followed by a number (e.g. \"CEDEX 7\"), or just a number alone, representing the \"sector code\" (Jamaica), \"delivery area indicator\" (Malawi) or \"post office indicator\" (e.g. Côte d'Ivoire).", "type": "string" }, "administrativeArea": { "description": "Optional. Highest administrative subdivision which is used for postal addresses of a country or region. For example, this can be a state, a province, an oblast, or a prefecture. Specifically, for Spain this is the province and not the autonomous community (e.g. \"Barcelona\" and not \"Catalonia\"). Many countries don't use an administrative area in postal addresses. E.g. in Switzerland this should be left unpopulated.", "type": "string" }, "locality": { "description": "Optional. Generally refers to the city/town portion of the address. Examples: US city, IT comune, UK post town. In regions of the world where localities are not well defined or do not fit into this structure well, leave locality empty and use address_lines.", "type": "string" }, "sublocality": { "description": "Optional. Sublocality of the address. For example, this can be neighborhoods, boroughs, districts.", "type": "string" }, "addressLines": { "description": "Unstructured address lines describing the lower levels of an address. Because values in address_lines do not have type information and may sometimes contain multiple values in a single field (e.g. \"Austin, TX\"), it is important that the line order is clear. The order of address lines should be \"envelope order\" for the country/region of the address. In places where this can vary (e.g. Japan), address_language is used to make it explicit (e.g. \"ja\" for large-to-small ordering and \"ja-Latn\" or \"en\" for small-to-large). This way, the most specific line of an address can be selected based on the language. The minimum permitted structural representation of an address consists of a region_code with all remaining information placed in the address_lines. It would be possible to format such an address very approximately without geocoding, but no semantic reasoning could be made about any of the address components until it was at least partially resolved. Creating an address only containing a region_code and address_lines, and then geocoding is the recommended way to handle completely unstructured addresses (as opposed to guessing which parts of the address should be localities or administrative areas).", "type": "array", "items": { "type": "string" } }, "recipients": { "description": "Optional. The recipient at the address. This field may, under certain circumstances, contain multiline information. For example, it might contain \"care of\" information.", "type": "array", "items": { "type": "string" } }, "organization": { "description": "Optional. The name of the organization at the address.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentEntityRelation": { "id": "GoogleCloudDocumentaiV1beta3DocumentEntityRelation", "description": "Relationship between Entities.", "type": "object", "properties": { "subjectId": { "description": "Subject entity id.", "type": "string" }, "objectId": { "description": "Object entity id.", "type": "string" }, "relation": { "description": "Relationship description.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentTextChange": { "id": "GoogleCloudDocumentaiV1beta3DocumentTextChange", "description": "This message is used for text changes aka. OCR corrections.", "type": "object", "properties": { "textAnchor": { "description": "Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single `TextAnchor.text_segments` element. If the start and end index of the text segment are the same, the text change is inserted before that index.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentTextAnchor" }, "changedText": { "description": "The text that replaces the text identified in the `text_anchor`.", "type": "string" }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentProvenance" } } } }, "GoogleCloudDocumentaiV1beta3DocumentShardInfo": { "id": "GoogleCloudDocumentaiV1beta3DocumentShardInfo", "description": "For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is.", "type": "object", "properties": { "shardIndex": { "description": "The 0-based index of this shard.", "type": "string", "format": "int64" }, "shardCount": { "description": "Total number of shards.", "type": "string", "format": "int64" }, "textOffset": { "description": "The index of the first character in Document.text in the overall document global text.", "type": "string", "format": "int64" } } }, "GoogleCloudDocumentaiV1beta3DocumentRevision": { "id": "GoogleCloudDocumentaiV1beta3DocumentRevision", "description": "Contains past or forward revisions of this document.", "type": "object", "properties": { "agent": { "description": "If the change was made by a person specify the name or id of that person.", "type": "string" }, "processor": { "description": "If the annotation was made by processor identify the processor by its resource name.", "type": "string" }, "id": { "description": "Id of the revision, internally generated by doc proto storage. Unique within the context of the document.", "type": "string" }, "parent": { "description": "The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.", "deprecated": true, "type": "array", "items": { "type": "integer", "format": "int32" } }, "parentIds": { "description": "The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.", "type": "array", "items": { "type": "string" } }, "createTime": { "description": "The time that the revision was created, internally generated by doc proto storage at the time of create.", "type": "string", "format": "google-datetime" }, "humanReview": { "description": "Human Review information of this revision.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentRevisionHumanReview" } } }, "GoogleCloudDocumentaiV1beta3DocumentRevisionHumanReview": { "id": "GoogleCloudDocumentaiV1beta3DocumentRevisionHumanReview", "description": "Human Review information of the document.", "type": "object", "properties": { "state": { "description": "Human review state. e.g. `requested`, `succeeded`, `rejected`.", "type": "string" }, "stateMessage": { "description": "A message providing more details about the current state of processing. For example, the rejection reason when the state is `rejected`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayout": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayout", "description": "Represents the parsed layout of a document as a collection of blocks that the document is divided into.", "type": "object", "properties": { "blocks": { "description": "List of blocks in the document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlock": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlock", "description": "Represents a block. A block could be one of the various types (text, table, list) supported.", "type": "object", "properties": { "textBlock": { "description": "Block consisting of text content.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock" }, "tableBlock": { "description": "Block consisting of table content/structure.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock" }, "listBlock": { "description": "Block consisting of list content/structure.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock" }, "blockId": { "description": "ID of the block.", "type": "string" }, "pageSpan": { "description": "Page span of the block.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan" } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock", "description": "Represents a text type block.", "type": "object", "properties": { "text": { "description": "Text content stored in the block.", "type": "string" }, "type": { "description": "Type of the text in the block. Available options are: `paragraph`, `subtitle`, `heading-1`, `heading-2`, `heading-3`, `heading-4`, `heading-5`, `header`, `footer`.", "type": "string" }, "blocks": { "description": "A text block could further have child blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock", "description": "Represents a table type block.", "type": "object", "properties": { "headerRows": { "description": "Header rows at the top of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow" } }, "bodyRows": { "description": "Body rows containing main table content.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow" } }, "caption": { "description": "Table caption/title.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow", "description": "Represents a row in a table.", "type": "object", "properties": { "cells": { "description": "A table row is a list of table cells.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell" } } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell", "description": "Represents a cell in a table row.", "type": "object", "properties": { "blocks": { "description": "A table cell is a list of blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlock" } }, "rowSpan": { "description": "How many rows this cell spans.", "type": "integer", "format": "int32" }, "colSpan": { "description": "How many columns this cell spans.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock", "description": "Represents a list type block.", "type": "object", "properties": { "listEntries": { "description": "List entries that constitute a list block.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry" } }, "type": { "description": "Type of the list_entries (if exist). Available options are `ordered` and `unordered`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry", "description": "Represents an entry in the list.", "type": "object", "properties": { "blocks": { "description": "A list entry is a list of blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan": { "id": "GoogleCloudDocumentaiV1beta3DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan", "description": "Represents where the block starts and ends in the document.", "type": "object", "properties": { "pageStart": { "description": "Page where block starts in the document.", "type": "integer", "format": "int32" }, "pageEnd": { "description": "Page where block ends in the document.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentChunkedDocument": { "id": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocument", "description": "Represents the chunks that the document is divided into.", "type": "object", "properties": { "chunks": { "description": "List of chunks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunk" } } } }, "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunk": { "id": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunk", "description": "Represents a chunk.", "type": "object", "properties": { "chunkId": { "description": "ID of the chunk.", "type": "string" }, "sourceBlockIds": { "description": "Unused.", "type": "array", "items": { "type": "string" } }, "content": { "description": "Text content of the chunk.", "type": "string" }, "pageSpan": { "description": "Page span of the chunk.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageSpan" }, "pageHeaders": { "description": "Page headers associated with the chunk.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageHeader" } }, "pageFooters": { "description": "Page footers associated with the chunk.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageFooter" } } } }, "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageSpan": { "id": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageSpan", "description": "Represents where the chunk starts and ends in the document.", "type": "object", "properties": { "pageStart": { "description": "Page where chunk starts in the document.", "type": "integer", "format": "int32" }, "pageEnd": { "description": "Page where chunk ends in the document.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageHeader": { "id": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageHeader", "description": "Represents the page header associated with the chunk.", "type": "object", "properties": { "text": { "description": "Header in text format.", "type": "string" }, "pageSpan": { "description": "Page span of the header.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageSpan" } } }, "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageFooter": { "id": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageFooter", "description": "Represents the page footer associated with the chunk.", "type": "object", "properties": { "text": { "description": "Footer in text format.", "type": "string" }, "pageSpan": { "description": "Page span of the footer.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentChunkedDocumentChunkChunkPageSpan" } } }, "GoogleCloudDocumentaiV1beta3RawDocument": { "id": "GoogleCloudDocumentaiV1beta3RawDocument", "description": "Payload message of raw document content (bytes).", "type": "object", "properties": { "content": { "description": "Inline document content.", "type": "string", "format": "byte" }, "mimeType": { "description": "An IANA MIME type (RFC6838) indicating the nature and format of the content.", "type": "string" }, "displayName": { "description": "The display name of the document, it supports all Unicode characters except the following: `*`, `?`, `[`, `]`, `%`, `{`, `}`,`'`, `\\\"`, `,` `~`, `=` and `:` are reserved. If not specified, a default ID is generated.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3GcsDocument": { "id": "GoogleCloudDocumentaiV1beta3GcsDocument", "description": "Specifies a document stored on Cloud Storage.", "type": "object", "properties": { "gcsUri": { "description": "The Cloud Storage object uri.", "type": "string" }, "mimeType": { "description": "An IANA MIME type (RFC6838) of the content.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ProcessOptions": { "id": "GoogleCloudDocumentaiV1beta3ProcessOptions", "description": "Options for Process API", "type": "object", "properties": { "individualPageSelector": { "description": "Which pages to process (1-indexed).", "$ref": "GoogleCloudDocumentaiV1beta3ProcessOptionsIndividualPageSelector" }, "fromStart": { "description": "Only process certain pages from the start. Process all if the document has fewer pages.", "type": "integer", "format": "int32" }, "fromEnd": { "description": "Only process certain pages from the end, same as above.", "type": "integer", "format": "int32" }, "ocrConfig": { "description": "Only applicable to `OCR_PROCESSOR` and `FORM_PARSER_PROCESSOR`. Returns error if set on other processor types.", "$ref": "GoogleCloudDocumentaiV1beta3OcrConfig" }, "layoutConfig": { "description": "Optional. Only applicable to `LAYOUT_PARSER_PROCESSOR`. Returns error if set on other processor types.", "$ref": "GoogleCloudDocumentaiV1beta3ProcessOptionsLayoutConfig" }, "schemaOverride": { "description": "Optional. Override the schema of the ProcessorVersion. Will return an Invalid Argument error if this field is set when the underlying ProcessorVersion doesn't support schema override.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchema" } } }, "GoogleCloudDocumentaiV1beta3ProcessOptionsIndividualPageSelector": { "id": "GoogleCloudDocumentaiV1beta3ProcessOptionsIndividualPageSelector", "description": "A list of individual page numbers.", "type": "object", "properties": { "pages": { "description": "Optional. Indices of the pages (starting from 1).", "type": "array", "items": { "type": "integer", "format": "int32" } } } }, "GoogleCloudDocumentaiV1beta3OcrConfig": { "id": "GoogleCloudDocumentaiV1beta3OcrConfig", "description": "Config for Document OCR.", "type": "object", "properties": { "hints": { "description": "Hints for the OCR model.", "$ref": "GoogleCloudDocumentaiV1beta3OcrConfigHints" }, "enableNativePdfParsing": { "description": "Enables special handling for PDFs with existing text information. Results in better text extraction quality in such PDF inputs.", "type": "boolean" }, "enableImageQualityScores": { "description": "Enables intelligent document quality scores after OCR. Can help with diagnosing why OCR responses are of poor quality for a given input. Adds additional latency comparable to regular OCR to the process call.", "type": "boolean" }, "advancedOcrOptions": { "description": "A list of advanced OCR options to further fine-tune OCR behavior. Current valid values are: - `legacy_layout`: a heuristics layout detection algorithm, which serves as an alternative to the current ML-based layout detection algorithm. Customers can choose the best suitable layout algorithm based on their situation.", "type": "array", "items": { "type": "string" } }, "enableSymbol": { "description": "Includes symbol level OCR information if set to true.", "type": "boolean" }, "computeStyleInfo": { "description": "Turn on font identification model and return font style information. Deprecated, use PremiumFeatures.compute_style_info instead.", "deprecated": true, "type": "boolean" }, "disableCharacterBoxesDetection": { "description": "Turn off character box detector in OCR engine. Character box detection is enabled by default in OCR 2.0 (and later) processors.", "type": "boolean" }, "premiumFeatures": { "description": "Configurations for premium OCR features.", "$ref": "GoogleCloudDocumentaiV1beta3OcrConfigPremiumFeatures" } } }, "GoogleCloudDocumentaiV1beta3OcrConfigHints": { "id": "GoogleCloudDocumentaiV1beta3OcrConfigHints", "description": "Hints for OCR Engine", "type": "object", "properties": { "languageHints": { "description": "List of BCP-47 language codes to use for OCR. In most cases, not specifying it yields the best results since it enables automatic language detection. For languages based on the Latin alphabet, setting hints is not needed. In rare cases, when the language of the text in the image is known, setting a hint will help get better results (although it will be a significant hindrance if the hint is wrong).", "type": "array", "items": { "type": "string" } } } }, "GoogleCloudDocumentaiV1beta3OcrConfigPremiumFeatures": { "id": "GoogleCloudDocumentaiV1beta3OcrConfigPremiumFeatures", "description": "Configurations for premium OCR features.", "type": "object", "properties": { "enableSelectionMarkDetection": { "description": "Turn on selection mark detector in OCR engine. Only available in OCR 2.0 (and later) processors.", "type": "boolean" }, "computeStyleInfo": { "description": "Turn on font identification model and return font style information.", "type": "boolean" }, "enableMathOcr": { "description": "Turn on the model that can extract LaTeX math formulas.", "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3ProcessOptionsLayoutConfig": { "id": "GoogleCloudDocumentaiV1beta3ProcessOptionsLayoutConfig", "description": "Serving config for layout parser processor.", "type": "object", "properties": { "chunkingConfig": { "description": "Optional. Config for chunking in layout parser processor.", "$ref": "GoogleCloudDocumentaiV1beta3ProcessOptionsLayoutConfigChunkingConfig" } } }, "GoogleCloudDocumentaiV1beta3ProcessOptionsLayoutConfigChunkingConfig": { "id": "GoogleCloudDocumentaiV1beta3ProcessOptionsLayoutConfigChunkingConfig", "description": "Serving config for chunking.", "type": "object", "properties": { "chunkSize": { "description": "Optional. The chunk sizes to use when splitting documents, in order of level.", "type": "integer", "format": "int32" }, "includeAncestorHeadings": { "description": "Optional. Whether or not to include ancestor headings when splitting.", "type": "boolean" }, "semanticChunkingGroupSize": { "description": "Optional. The number of tokens to group together when evaluating semantic similarity.", "type": "boolean" }, "breakpointPercentileThreshold": { "description": "Optional. The percentile of cosine dissimilarity that must be exceeded between a group of tokens and the next. The smaller this number is, the more chunks will be generated.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentSchema": { "id": "GoogleCloudDocumentaiV1beta3DocumentSchema", "description": "The schema defines the output of the processed document by a processor.", "type": "object", "properties": { "displayName": { "description": "Display name to show to users.", "type": "string" }, "description": { "description": "Description of the schema.", "type": "string" }, "entityTypes": { "description": "Entity types of the schema.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityType" } }, "metadata": { "description": "Metadata of the schema.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchemaMetadata" } } }, "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityType": { "id": "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityType", "description": "EntityType is the wrapper of a label of the corresponding model with detailed attributes and limitations for entity-based processors. Multiple types can also compose a dependency tree to represent nested types.", "type": "object", "properties": { "enumValues": { "description": "If specified, lists all the possible values for this entity. This should not be more than a handful of values. If the number of values is \u003e10 or could change frequently use the `EntityType.value_ontology` field and specify a list of all possible values in a value ontology file.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityTypeEnumValues" }, "displayName": { "description": "User defined name for the type.", "type": "string" }, "name": { "description": "Name of the type. It must be unique within the schema file and cannot be a \"Common Type\". The following naming conventions are used: - Use `snake_casing`. - Name matching is case-sensitive. - Maximum 64 characters. - Must start with a letter. - Allowed characters: ASCII letters `[a-z0-9_-]`. (For backward compatibility internal infrastructure and tooling can handle any ascii character.) - The `/` is sometimes used to denote a property of a type. For example `line_item/amount`. This convention is deprecated, but will still be honored for backward compatibility.", "type": "string" }, "baseTypes": { "description": "The entity type that this type is derived from. For now, one and only one should be set.", "type": "array", "items": { "type": "string" } }, "properties": { "description": "Description the nested structure, or composition of an entity.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityTypeProperty" } }, "entityTypeMetadata": { "description": "Metadata for the entity type.", "$ref": "GoogleCloudDocumentaiV1beta3EntityTypeMetadata" } } }, "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityTypeEnumValues": { "id": "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityTypeEnumValues", "description": "Defines the a list of enum values.", "type": "object", "properties": { "values": { "description": "The individual values that this enum values type can include.", "type": "array", "items": { "type": "string" } } } }, "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityTypeProperty": { "id": "GoogleCloudDocumentaiV1beta3DocumentSchemaEntityTypeProperty", "description": "Defines properties that can be part of the entity type.", "type": "object", "properties": { "name": { "description": "The name of the property. Follows the same guidelines as the EntityType name.", "type": "string" }, "displayName": { "description": "User defined name for the property.", "type": "string" }, "valueType": { "description": "A reference to the value type of the property. This type is subject to the same conventions as the `Entity.base_types` field.", "type": "string" }, "occurrenceType": { "description": "Occurrence type limits the number of instances an entity type appears in the document.", "type": "string", "enumDescriptions": [ "Unspecified occurrence type.", "There will be zero or one instance of this entity type. The same entity instance may be mentioned multiple times.", "The entity type will appear zero or multiple times.", "The entity type will only appear exactly once. The same entity instance may be mentioned multiple times.", "The entity type will appear once or more times." ], "enum": [ "OCCURRENCE_TYPE_UNSPECIFIED", "OPTIONAL_ONCE", "OPTIONAL_MULTIPLE", "REQUIRED_ONCE", "REQUIRED_MULTIPLE" ] }, "propertyMetadata": { "description": "Any additional metadata about the property can be added here.", "$ref": "GoogleCloudDocumentaiV1beta3PropertyMetadata" } } }, "GoogleCloudDocumentaiV1beta3PropertyMetadata": { "id": "GoogleCloudDocumentaiV1beta3PropertyMetadata", "description": "Metadata about a property.", "type": "object", "properties": { "inactive": { "description": "Whether the property should be considered as \"inactive\".", "type": "boolean" }, "fieldExtractionMetadata": { "description": "Field extraction metadata on the property.", "$ref": "GoogleCloudDocumentaiV1beta3FieldExtractionMetadata" } } }, "GoogleCloudDocumentaiV1beta3FieldExtractionMetadata": { "id": "GoogleCloudDocumentaiV1beta3FieldExtractionMetadata", "description": "Metadata for how this field value is extracted.", "type": "object", "properties": { "summaryOptions": { "description": "Summary options config.", "$ref": "GoogleCloudDocumentaiV1beta3SummaryOptions" } } }, "GoogleCloudDocumentaiV1beta3SummaryOptions": { "id": "GoogleCloudDocumentaiV1beta3SummaryOptions", "description": "Metadata for document summarization.", "type": "object", "properties": { "length": { "description": "How long the summary should be.", "type": "string", "enumDescriptions": [ "Default.", "A brief summary of one or two sentences.", "A paragraph-length summary.", "The longest option available." ], "enum": [ "LENGTH_UNSPECIFIED", "BRIEF", "MODERATE", "COMPREHENSIVE" ] }, "format": { "description": "The format the summary should be in.", "type": "string", "enumDescriptions": [ "Default.", "Format the output in paragraphs.", "Format the output in bullets." ], "enum": [ "FORMAT_UNSPECIFIED", "PARAGRAPH", "BULLETS" ] } } }, "GoogleCloudDocumentaiV1beta3EntityTypeMetadata": { "id": "GoogleCloudDocumentaiV1beta3EntityTypeMetadata", "description": "Metadata about an entity type.", "type": "object", "properties": { "inactive": { "description": "Whether the entity type should be considered inactive.", "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3DocumentSchemaMetadata": { "id": "GoogleCloudDocumentaiV1beta3DocumentSchemaMetadata", "description": "Metadata for global schema behavior.", "type": "object", "properties": { "documentSplitter": { "description": "If true, a `document` entity type can be applied to subdocument (splitting). Otherwise, it can only be applied to the entire document (classification).", "type": "boolean" }, "documentAllowMultipleLabels": { "description": "If true, on a given page, there can be multiple `document` annotations covering it.", "type": "boolean" }, "prefixedNamingOnProperties": { "description": "If set, all the nested entities must be prefixed with the parents.", "type": "boolean" }, "skipNamingValidation": { "description": "If set, we will skip the naming format validation in the schema. So the string values in `DocumentSchema.EntityType.name` and `DocumentSchema.EntityType.Property.name` will not be checked.", "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3ProcessResponse": { "id": "GoogleCloudDocumentaiV1beta3ProcessResponse", "description": "Response message for the ProcessDocument method.", "type": "object", "properties": { "document": { "description": "The document payload, will populate fields based on the processor's behavior.", "$ref": "GoogleCloudDocumentaiV1beta3Document" }, "humanReviewOperation": { "description": "The name of the operation triggered by the processed document. If the human review process isn't triggered, this field is empty. It has the same response type and metadata as the long-running operation returned by ReviewDocument.", "deprecated": true, "type": "string" }, "humanReviewStatus": { "description": "The status of human review on the processed document.", "$ref": "GoogleCloudDocumentaiV1beta3HumanReviewStatus" } } }, "GoogleCloudDocumentaiV1beta3HumanReviewStatus": { "id": "GoogleCloudDocumentaiV1beta3HumanReviewStatus", "description": "The status of human review on a processed document.", "type": "object", "properties": { "state": { "description": "The state of human review on the processing request.", "type": "string", "enumDescriptions": [ "Human review state is unspecified. Most likely due to an internal error.", "Human review is skipped for the document. This can happen because human review isn't enabled on the processor or the processing request has been set to skip this document.", "Human review validation is triggered and passed, so no review is needed.", "Human review validation is triggered and the document is under review.", "Some error happened during triggering human review, see the state_message for details." ], "enum": [ "STATE_UNSPECIFIED", "SKIPPED", "VALIDATION_PASSED", "IN_PROGRESS", "ERROR" ] }, "stateMessage": { "description": "A message providing more details about the human review state.", "type": "string" }, "humanReviewOperation": { "description": "The name of the operation triggered by the processed document. This field is populated only when the state is `HUMAN_REVIEW_IN_PROGRESS`. It has the same response type and metadata as the long-running operation returned by ReviewDocument.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3BatchProcessRequest": { "id": "GoogleCloudDocumentaiV1beta3BatchProcessRequest", "description": "Request message for BatchProcessDocuments.", "type": "object", "properties": { "inputConfigs": { "description": "The input config for each single document in the batch process.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3BatchProcessRequestBatchInputConfig" } }, "outputConfig": { "description": "The overall output config for batch process.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3BatchProcessRequestBatchOutputConfig" }, "inputDocuments": { "description": "The input documents for the BatchProcessDocuments method.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig" }, "documentOutputConfig": { "description": "The output configuration for the BatchProcessDocuments method.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentOutputConfig" }, "skipHumanReview": { "description": "Whether human review should be skipped for this request. Default to `false`.", "type": "boolean" }, "processOptions": { "description": "Inference-time options for the process API", "$ref": "GoogleCloudDocumentaiV1beta3ProcessOptions" }, "labels": { "description": "Optional. The labels with user-defined metadata for the request. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.", "type": "object", "additionalProperties": { "type": "string" } } } }, "GoogleCloudDocumentaiV1beta3BatchProcessRequestBatchInputConfig": { "id": "GoogleCloudDocumentaiV1beta3BatchProcessRequestBatchInputConfig", "deprecated": true, "description": "The message for input config in batch process.", "type": "object", "properties": { "gcsSource": { "description": "The Cloud Storage location as the source of the document.", "type": "string" }, "mimeType": { "description": "An IANA published [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml) of the input. If the input is a raw document, refer to [supported file types](https://cloud.google.com/document-ai/docs/file-types) for the list of media types. If the input is a Document, the type should be `application/json`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3BatchProcessRequestBatchOutputConfig": { "id": "GoogleCloudDocumentaiV1beta3BatchProcessRequestBatchOutputConfig", "deprecated": true, "description": "The output configuration in the BatchProcessDocuments method.", "type": "object", "properties": { "gcsDestination": { "description": "The output Cloud Storage directory to put the processed documents.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig": { "id": "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig", "description": "The common config to specify a set of documents used as input.", "type": "object", "properties": { "gcsPrefix": { "description": "The set of documents that match the specified Cloud Storage `gcs_prefix`.", "$ref": "GoogleCloudDocumentaiV1beta3GcsPrefix" }, "gcsDocuments": { "description": "The set of documents individually specified on Cloud Storage.", "$ref": "GoogleCloudDocumentaiV1beta3GcsDocuments" } } }, "GoogleCloudDocumentaiV1beta3GcsPrefix": { "id": "GoogleCloudDocumentaiV1beta3GcsPrefix", "description": "Specifies all documents on Cloud Storage with a common prefix.", "type": "object", "properties": { "gcsUriPrefix": { "description": "The URI prefix.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3GcsDocuments": { "id": "GoogleCloudDocumentaiV1beta3GcsDocuments", "description": "Specifies a set of documents on Cloud Storage.", "type": "object", "properties": { "documents": { "description": "The list of documents.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3GcsDocument" } } } }, "GoogleCloudDocumentaiV1beta3DocumentOutputConfig": { "id": "GoogleCloudDocumentaiV1beta3DocumentOutputConfig", "description": "Config that controls the output of documents. All documents will be written as a JSON file.", "type": "object", "properties": { "gcsOutputConfig": { "description": "Output config to write the results to Cloud Storage.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentOutputConfigGcsOutputConfig" } } }, "GoogleCloudDocumentaiV1beta3DocumentOutputConfigGcsOutputConfig": { "id": "GoogleCloudDocumentaiV1beta3DocumentOutputConfigGcsOutputConfig", "description": "The configuration used when outputting documents.", "type": "object", "properties": { "gcsUri": { "description": "The Cloud Storage uri (a directory) of the output.", "type": "string" }, "fieldMask": { "description": "Specifies which fields to include in the output documents. Only supports top level document and pages field so it must be in the form of `{document_field_name}` or `pages.{page_field_name}`.", "type": "string", "format": "google-fieldmask" }, "shardingConfig": { "description": "Specifies the sharding config for the output document.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentOutputConfigGcsOutputConfigShardingConfig" } } }, "GoogleCloudDocumentaiV1beta3DocumentOutputConfigGcsOutputConfigShardingConfig": { "id": "GoogleCloudDocumentaiV1beta3DocumentOutputConfigGcsOutputConfigShardingConfig", "description": "The sharding config for the output document.", "type": "object", "properties": { "pagesPerShard": { "description": "The number of pages per shard.", "type": "integer", "format": "int32" }, "pagesOverlap": { "description": "The number of overlapping pages between consecutive shards.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3FetchProcessorTypesResponse": { "id": "GoogleCloudDocumentaiV1beta3FetchProcessorTypesResponse", "description": "Response message for the FetchProcessorTypes method.", "type": "object", "properties": { "processorTypes": { "description": "The list of processor types.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorType" } } } }, "GoogleCloudDocumentaiV1beta3ProcessorType": { "id": "GoogleCloudDocumentaiV1beta3ProcessorType", "description": "A processor type is responsible for performing a certain document understanding task on a certain type of document.", "type": "object", "properties": { "name": { "description": "The resource name of the processor type. Format: `projects/{project}/processorTypes/{processor_type}`", "type": "string" }, "type": { "description": "The processor type, such as: `OCR_PROCESSOR`, `INVOICE_PROCESSOR`.", "type": "string" }, "category": { "description": "The processor category, used by UI to group processor types.", "type": "string" }, "availableLocations": { "description": "The locations in which this processor is available.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorTypeLocationInfo" } }, "allowCreation": { "description": "Whether the processor type allows creation. If true, users can create a processor of this processor type. Otherwise, users need to request access.", "type": "boolean" }, "launchStage": { "description": "Launch stage of the processor type", "type": "string", "enumDescriptions": [ "Do not use this default value.", "The feature is not yet implemented. Users can not use it.", "Prelaunch features are hidden from users and are only visible internally.", "Early Access features are limited to a closed group of testers. To use these features, you must sign up in advance and sign a Trusted Tester agreement (which includes confidentiality provisions). These features may be unstable, changed in backward-incompatible ways, and are not guaranteed to be released.", "Alpha is a limited availability test for releases before they are cleared for widespread use. By Alpha, all significant design issues are resolved and we are in the process of verifying functionality. Alpha customers need to apply for access, agree to applicable terms, and have their projects allowlisted. Alpha releases don't have to be feature complete, no SLAs are provided, and there are no technical support obligations, but they will be far enough along that customers can actually use them in test environments or for limited-use tests -- just like they would in normal production cases.", "Beta is the point at which we are ready to open a release for any customer to use. There are no SLA or technical support obligations in a Beta release. Products will be complete from a feature perspective, but may have some open outstanding issues. Beta releases are suitable for limited production use cases.", "GA features are open to all developers and are considered stable and fully qualified for production use.", "Deprecated features are scheduled to be shut down and removed. For more information, see the \"Deprecation Policy\" section of our [Terms of Service](https://cloud.google.com/terms/) and the [Google Cloud Platform Subject to the Deprecation Policy](https://cloud.google.com/terms/deprecation) documentation." ], "enum": [ "LAUNCH_STAGE_UNSPECIFIED", "UNIMPLEMENTED", "PRELAUNCH", "EARLY_ACCESS", "ALPHA", "BETA", "GA", "DEPRECATED" ] }, "sampleDocumentUris": { "description": "A set of Cloud Storage URIs of sample documents for this processor.", "type": "array", "items": { "type": "string" } } } }, "GoogleCloudDocumentaiV1beta3ProcessorTypeLocationInfo": { "id": "GoogleCloudDocumentaiV1beta3ProcessorTypeLocationInfo", "description": "The location information about where the processor is available.", "type": "object", "properties": { "locationId": { "description": "The location ID. For supported locations, refer to [regional and multi-regional support](/document-ai/docs/regions).", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ListProcessorTypesResponse": { "id": "GoogleCloudDocumentaiV1beta3ListProcessorTypesResponse", "description": "Response message for the ListProcessorTypes method.", "type": "object", "properties": { "processorTypes": { "description": "The processor types.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorType" } }, "nextPageToken": { "description": "Points to the next page, otherwise empty.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ListProcessorsResponse": { "id": "GoogleCloudDocumentaiV1beta3ListProcessorsResponse", "description": "Response message for the ListProcessors method.", "type": "object", "properties": { "processors": { "description": "The list of processors.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3Processor" } }, "nextPageToken": { "description": "Points to the next processor, otherwise empty.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3Processor": { "id": "GoogleCloudDocumentaiV1beta3Processor", "description": "The first-class citizen for Document AI. Each processor defines how to extract structural information from a document.", "type": "object", "properties": { "name": { "description": "Output only. Immutable. The resource name of the processor. Format: `projects/{project}/locations/{location}/processors/{processor}`", "readOnly": true, "type": "string" }, "type": { "description": "The processor type, such as: `OCR_PROCESSOR`, `INVOICE_PROCESSOR`. To get a list of processor types, see FetchProcessorTypes.", "type": "string" }, "displayName": { "description": "The display name of the processor.", "type": "string" }, "state": { "description": "Output only. The state of the processor.", "readOnly": true, "type": "string", "enumDescriptions": [ "The processor is in an unspecified state.", "The processor is enabled, i.e., has an enabled version which can currently serve processing requests and all the feature dependencies have been successfully initialized.", "The processor is disabled.", "The processor is being enabled, will become `ENABLED` if successful.", "The processor is being disabled, will become `DISABLED` if successful.", "The processor is being created, will become either `ENABLED` (for successful creation) or `FAILED` (for failed ones). Once a processor is in this state, it can then be used for document processing, but the feature dependencies of the processor might not be fully created yet.", "The processor failed during creation or initialization of feature dependencies. The user should delete the processor and recreate one as all the functionalities of the processor are disabled.", "The processor is being deleted, will be removed if successful." ], "enum": [ "STATE_UNSPECIFIED", "ENABLED", "DISABLED", "ENABLING", "DISABLING", "CREATING", "FAILED", "DELETING" ] }, "defaultProcessorVersion": { "description": "The default processor version.", "type": "string" }, "processorVersionAliases": { "description": "Output only. The processor version aliases.", "readOnly": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorVersionAlias" } }, "processEndpoint": { "description": "Output only. Immutable. The http endpoint that can be called to invoke processing.", "readOnly": true, "type": "string" }, "createTime": { "description": "The time the processor was created.", "type": "string", "format": "google-datetime" }, "kmsKeyName": { "description": "The [KMS key](https://cloud.google.com/security-key-management) used for encryption and decryption in CMEK scenarios.", "type": "string" }, "satisfiesPzs": { "description": "Output only. Reserved for future use.", "readOnly": true, "type": "boolean" }, "satisfiesPzi": { "description": "Output only. Reserved for future use.", "readOnly": true, "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3ProcessorVersionAlias": { "id": "GoogleCloudDocumentaiV1beta3ProcessorVersionAlias", "description": "Contains the alias and the aliased resource name of processor version.", "type": "object", "properties": { "alias": { "description": "The alias in the form of `processor_version` resource name.", "type": "string" }, "processorVersion": { "description": "The resource name of aliased processor version.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequest": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequest", "description": "Request message for the TrainProcessorVersion method.", "type": "object", "properties": { "customDocumentExtractionOptions": { "description": "Options to control Custom Document Extraction (CDE) Processor.", "$ref": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestCustomDocumentExtractionOptions" }, "foundationModelTuningOptions": { "description": "Options to control foundation model tuning of a processor.", "$ref": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestFoundationModelTuningOptions" }, "processorVersion": { "description": "Required. The processor version to be created.", "$ref": "GoogleCloudDocumentaiV1beta3ProcessorVersion" }, "documentSchema": { "description": "Optional. The schema the processor version will be trained with.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchema" }, "inputData": { "description": "Optional. The input data used to train the ProcessorVersion.", "$ref": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestInputData" }, "baseProcessorVersion": { "description": "Optional. The processor version to use as a base for training. This processor version must be a child of `parent`. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestCustomDocumentExtractionOptions": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestCustomDocumentExtractionOptions", "description": "Options to control the training of the Custom Document Extraction (CDE) Processor.", "type": "object", "properties": { "trainingMethod": { "description": "Training method to use for CDE training.", "type": "string", "enumDescriptions": [ "", "", "" ], "enum": [ "TRAINING_METHOD_UNSPECIFIED", "MODEL_BASED", "TEMPLATE_BASED" ] } } }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestFoundationModelTuningOptions": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestFoundationModelTuningOptions", "description": "Options to control foundation model tuning of the processor.", "type": "object", "properties": { "trainSteps": { "description": "Optional. The number of steps to run for model tuning. Valid values are between 1 and 400. If not provided, recommended steps will be used.", "type": "integer", "format": "int32" }, "learningRateMultiplier": { "description": "Optional. The multiplier to apply to the recommended learning rate. Valid values are between 0.1 and 10. If not provided, recommended learning rate will be used.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3ProcessorVersion": { "id": "GoogleCloudDocumentaiV1beta3ProcessorVersion", "description": "A processor version is an implementation of a processor. Each processor can have multiple versions, pretrained by Google internally or uptrained by the customer. A processor can only have one default version at a time. Its document-processing behavior is defined by that version.", "type": "object", "properties": { "name": { "description": "Identifier. The resource name of the processor version. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processor_version}`", "type": "string" }, "displayName": { "description": "The display name of the processor version.", "type": "string" }, "documentSchema": { "description": "The schema of the processor version. Describes the output.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchema" }, "state": { "description": "Output only. The state of the processor version.", "readOnly": true, "type": "string", "enumDescriptions": [ "The processor version is in an unspecified state.", "The processor version is deployed and can be used for processing.", "The processor version is being deployed.", "The processor version is not deployed and cannot be used for processing.", "The processor version is being undeployed.", "The processor version is being created.", "The processor version is being deleted.", "The processor version failed and is in an indeterminate state.", "The processor version is being imported." ], "enum": [ "STATE_UNSPECIFIED", "DEPLOYED", "DEPLOYING", "UNDEPLOYED", "UNDEPLOYING", "CREATING", "DELETING", "FAILED", "IMPORTING" ] }, "createTime": { "description": "The time the processor version was created.", "type": "string", "format": "google-datetime" }, "latestEvaluation": { "description": "The most recently invoked evaluation for the processor version.", "$ref": "GoogleCloudDocumentaiV1beta3EvaluationReference" }, "kmsKeyName": { "description": "The KMS key name used for encryption.", "type": "string" }, "kmsKeyVersionName": { "description": "The KMS key version with which data is encrypted.", "type": "string" }, "googleManaged": { "description": "Output only. Denotes that this `ProcessorVersion` is managed by Google.", "readOnly": true, "type": "boolean" }, "deprecationInfo": { "description": "If set, information about the eventual deprecation of this version.", "$ref": "GoogleCloudDocumentaiV1beta3ProcessorVersionDeprecationInfo" }, "modelType": { "description": "Output only. The model type of this processor version.", "readOnly": true, "type": "string", "enumDescriptions": [ "The processor version has unspecified model type.", "The processor version has generative model type.", "The processor version has custom model type." ], "enum": [ "MODEL_TYPE_UNSPECIFIED", "MODEL_TYPE_GENERATIVE", "MODEL_TYPE_CUSTOM" ] }, "satisfiesPzs": { "description": "Output only. Reserved for future use.", "readOnly": true, "type": "boolean" }, "satisfiesPzi": { "description": "Output only. Reserved for future use.", "readOnly": true, "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3EvaluationReference": { "id": "GoogleCloudDocumentaiV1beta3EvaluationReference", "description": "Gives a short summary of an evaluation, and links to the evaluation itself.", "type": "object", "properties": { "operation": { "description": "The resource name of the Long Running Operation for the evaluation.", "type": "string" }, "evaluation": { "description": "The resource name of the evaluation.", "type": "string" }, "aggregateMetrics": { "description": "An aggregate of the statistics for the evaluation with fuzzy matching on.", "$ref": "GoogleCloudDocumentaiV1beta3EvaluationMetrics" }, "aggregateMetricsExact": { "description": "An aggregate of the statistics for the evaluation with fuzzy matching off.", "$ref": "GoogleCloudDocumentaiV1beta3EvaluationMetrics" } } }, "GoogleCloudDocumentaiV1beta3EvaluationMetrics": { "id": "GoogleCloudDocumentaiV1beta3EvaluationMetrics", "description": "Evaluation metrics, either in aggregate or about a specific entity.", "type": "object", "properties": { "precision": { "description": "The calculated precision.", "type": "number", "format": "float" }, "recall": { "description": "The calculated recall.", "type": "number", "format": "float" }, "f1Score": { "description": "The calculated f1 score.", "type": "number", "format": "float" }, "predictedOccurrencesCount": { "description": "The amount of occurrences in predicted documents.", "type": "integer", "format": "int32" }, "groundTruthOccurrencesCount": { "description": "The amount of occurrences in ground truth documents.", "type": "integer", "format": "int32" }, "predictedDocumentCount": { "description": "The amount of documents with a predicted occurrence.", "type": "integer", "format": "int32" }, "groundTruthDocumentCount": { "description": "The amount of documents with a ground truth occurrence.", "type": "integer", "format": "int32" }, "truePositivesCount": { "description": "The amount of true positives.", "type": "integer", "format": "int32" }, "falsePositivesCount": { "description": "The amount of false positives.", "type": "integer", "format": "int32" }, "falseNegativesCount": { "description": "The amount of false negatives.", "type": "integer", "format": "int32" }, "totalDocumentsCount": { "description": "The amount of documents that had an occurrence of this label.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3ProcessorVersionDeprecationInfo": { "id": "GoogleCloudDocumentaiV1beta3ProcessorVersionDeprecationInfo", "description": "Information about the upcoming deprecation of this processor version.", "type": "object", "properties": { "deprecationTime": { "description": "The time at which this processor version will be deprecated.", "type": "string", "format": "google-datetime" }, "replacementProcessorVersion": { "description": "If set, the processor version that will be used as a replacement.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestInputData": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionRequestInputData", "description": "The input data used to train a new ProcessorVersion.", "type": "object", "properties": { "trainingDocuments": { "description": "The documents used for training the new version.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig" }, "testDocuments": { "description": "The documents used for testing the trained version.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig" } } }, "GoogleCloudDocumentaiV1beta3ListProcessorVersionsResponse": { "id": "GoogleCloudDocumentaiV1beta3ListProcessorVersionsResponse", "description": "Response message for the ListProcessorVersions method.", "type": "object", "properties": { "processorVersions": { "description": "The list of processors.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ProcessorVersion" } }, "nextPageToken": { "description": "Points to the next processor, otherwise empty.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DeployProcessorVersionRequest": { "id": "GoogleCloudDocumentaiV1beta3DeployProcessorVersionRequest", "description": "Request message for the DeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionRequest": { "id": "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionRequest", "description": "Request message for the UndeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3EnableProcessorRequest": { "id": "GoogleCloudDocumentaiV1beta3EnableProcessorRequest", "description": "Request message for the EnableProcessor method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3DisableProcessorRequest": { "id": "GoogleCloudDocumentaiV1beta3DisableProcessorRequest", "description": "Request message for the DisableProcessor method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionRequest": { "id": "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionRequest", "description": "Request message for the SetDefaultProcessorVersion method.", "type": "object", "properties": { "defaultProcessorVersion": { "description": "Required. The resource name of child ProcessorVersion to use as default. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{version}`", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ReviewDocumentRequest": { "id": "GoogleCloudDocumentaiV1beta3ReviewDocumentRequest", "description": "Request message for the ReviewDocument method.", "type": "object", "properties": { "inlineDocument": { "description": "An inline document proto.", "$ref": "GoogleCloudDocumentaiV1beta3Document" }, "document": { "description": "The document that needs human review.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3Document" }, "enableSchemaValidation": { "description": "Whether the validation should be performed on the ad-hoc review request.", "type": "boolean" }, "priority": { "description": "The priority of the human review task.", "type": "string", "enumDescriptions": [ "The default priority level.", "The urgent priority level. The labeling manager should allocate labeler resource to the urgent task queue to respect this priority level." ], "enum": [ "DEFAULT", "URGENT" ] }, "documentSchema": { "description": "The document schema of the human review task.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchema" } } }, "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionRequest": { "id": "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionRequest", "description": "Evaluates the given ProcessorVersion against the supplied documents.", "type": "object", "properties": { "evaluationDocuments": { "description": "Optional. The documents used in the evaluation. If unspecified, use the processor's dataset as evaluation input.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig" } } }, "GoogleCloudDocumentaiV1beta3Evaluation": { "id": "GoogleCloudDocumentaiV1beta3Evaluation", "description": "An evaluation of a ProcessorVersion's performance.", "type": "object", "properties": { "name": { "description": "The resource name of the evaluation. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processor_version}/evaluations/{evaluation}`", "type": "string" }, "createTime": { "description": "The time that the evaluation was created.", "type": "string", "format": "google-datetime" }, "documentCounters": { "description": "Counters for the documents used in the evaluation.", "$ref": "GoogleCloudDocumentaiV1beta3EvaluationCounters" }, "allEntitiesMetrics": { "description": "Metrics for all the entities in aggregate.", "$ref": "GoogleCloudDocumentaiV1beta3EvaluationMultiConfidenceMetrics" }, "entityMetrics": { "description": "Metrics across confidence levels, for different entities.", "type": "object", "additionalProperties": { "$ref": "GoogleCloudDocumentaiV1beta3EvaluationMultiConfidenceMetrics" } }, "kmsKeyName": { "description": "The KMS key name used for encryption.", "type": "string" }, "kmsKeyVersionName": { "description": "The KMS key version with which data is encrypted.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3EvaluationCounters": { "id": "GoogleCloudDocumentaiV1beta3EvaluationCounters", "description": "Evaluation counters for the documents that were used.", "type": "object", "properties": { "inputDocumentsCount": { "description": "How many documents were sent for evaluation.", "type": "integer", "format": "int32" }, "invalidDocumentsCount": { "description": "How many documents were not included in the evaluation as they didn't pass validation.", "type": "integer", "format": "int32" }, "failedDocumentsCount": { "description": "How many documents were not included in the evaluation as Document AI failed to process them.", "type": "integer", "format": "int32" }, "evaluatedDocumentsCount": { "description": "How many documents were used in the evaluation.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3EvaluationMultiConfidenceMetrics": { "id": "GoogleCloudDocumentaiV1beta3EvaluationMultiConfidenceMetrics", "description": "Metrics across multiple confidence levels.", "type": "object", "properties": { "confidenceLevelMetrics": { "description": "Metrics across confidence levels with fuzzy matching enabled.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3EvaluationConfidenceLevelMetrics" } }, "confidenceLevelMetricsExact": { "description": "Metrics across confidence levels with only exact matching.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3EvaluationConfidenceLevelMetrics" } }, "auprc": { "description": "The calculated area under the precision recall curve (AUPRC), computed by integrating over all confidence thresholds.", "type": "number", "format": "float" }, "estimatedCalibrationError": { "description": "The Estimated Calibration Error (ECE) of the confidence of the predicted entities.", "type": "number", "format": "float" }, "auprcExact": { "description": "The AUPRC for metrics with fuzzy matching disabled, i.e., exact matching only.", "type": "number", "format": "float" }, "estimatedCalibrationErrorExact": { "description": "The ECE for the predicted entities with fuzzy matching disabled, i.e., exact matching only.", "type": "number", "format": "float" }, "metricsType": { "description": "The metrics type for the label.", "type": "string", "enumDescriptions": [ "The metrics type is unspecified. By default, metrics without a particular specification are for leaf entity types (i.e., top-level entity types without child types, or child types which are not parent types themselves).", "Indicates whether metrics for this particular label type represent an aggregate of metrics for other types instead of being based on actual TP/FP/FN values for the label type. Metrics for parent (i.e., non-leaf) entity types are an aggregate of metrics for their children." ], "enum": [ "METRICS_TYPE_UNSPECIFIED", "AGGREGATE" ] } } }, "GoogleCloudDocumentaiV1beta3EvaluationConfidenceLevelMetrics": { "id": "GoogleCloudDocumentaiV1beta3EvaluationConfidenceLevelMetrics", "description": "Evaluations metrics, at a specific confidence level.", "type": "object", "properties": { "confidenceLevel": { "description": "The confidence level.", "type": "number", "format": "float" }, "metrics": { "description": "The metrics at the specific confidence level.", "$ref": "GoogleCloudDocumentaiV1beta3EvaluationMetrics" } } }, "GoogleCloudDocumentaiV1beta3ListEvaluationsResponse": { "id": "GoogleCloudDocumentaiV1beta3ListEvaluationsResponse", "description": "The response from `ListEvaluations`.", "type": "object", "properties": { "evaluations": { "description": "The evaluations requested.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3Evaluation" } }, "nextPageToken": { "description": "A token, which can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ImportProcessorVersionRequest": { "id": "GoogleCloudDocumentaiV1beta3ImportProcessorVersionRequest", "description": "The request message for the ImportProcessorVersion method. The Document AI [Service Agent](https://cloud.google.com/iam/docs/service-agents) of the destination project must have [Document AI Editor role](https://cloud.google.com/document-ai/docs/access-control/iam-roles) on the source project. The destination project is specified as part of the parent field. The source project is specified as part of the source or external_processor_version_source field.", "type": "object", "properties": { "processorVersionSource": { "description": "The source processor version to import from. The source processor version and destination processor need to be in the same environment and region. Note that ProcessorVersions with `model_type` `MODEL_TYPE_LLM` are not supported.", "type": "string" }, "externalProcessorVersionSource": { "description": "The source processor version to import from. It can be from a different environment and region than the destination processor.", "$ref": "GoogleCloudDocumentaiV1beta3ImportProcessorVersionRequestExternalProcessorVersionSource" } } }, "GoogleCloudDocumentaiV1beta3ImportProcessorVersionRequestExternalProcessorVersionSource": { "id": "GoogleCloudDocumentaiV1beta3ImportProcessorVersionRequestExternalProcessorVersionSource", "description": "The external source processor version.", "type": "object", "properties": { "processorVersion": { "description": "Required. The processor version name. Format: `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "type": "string" }, "serviceEndpoint": { "description": "Optional. The Document AI service endpoint. For example, 'https://us-documentai.googleapis.com'", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3Dataset": { "id": "GoogleCloudDocumentaiV1beta3Dataset", "description": "A singleton resource under a Processor which configures a collection of documents.", "type": "object", "properties": { "gcsManagedConfig": { "description": "Optional. User-managed Cloud Storage dataset configuration. Use this configuration if the dataset documents are stored under a user-managed Cloud Storage location.", "$ref": "GoogleCloudDocumentaiV1beta3DatasetGCSManagedConfig" }, "documentWarehouseConfig": { "description": "Optional. Deprecated. Warehouse-based dataset configuration is not supported.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta3DatasetDocumentWarehouseConfig" }, "unmanagedDatasetConfig": { "description": "Optional. Unmanaged dataset configuration. Use this configuration if the dataset documents are managed by the document service internally (not user-managed).", "$ref": "GoogleCloudDocumentaiV1beta3DatasetUnmanagedDatasetConfig" }, "spannerIndexingConfig": { "description": "Optional. A lightweight indexing source with low latency and high reliability, but lacking advanced features like CMEK and content-based search.", "$ref": "GoogleCloudDocumentaiV1beta3DatasetSpannerIndexingConfig" }, "name": { "description": "Dataset resource name. Format: `projects/{project}/locations/{location}/processors/{processor}/dataset`", "type": "string" }, "state": { "description": "Required. State of the dataset. Ignored when updating dataset.", "type": "string", "enumDescriptions": [ "Default unspecified enum, should not be used.", "Dataset has not been initialized.", "Dataset is being initialized.", "Dataset has been initialized." ], "enum": [ "STATE_UNSPECIFIED", "UNINITIALIZED", "INITIALIZING", "INITIALIZED" ] }, "satisfiesPzs": { "description": "Output only. Reserved for future use.", "readOnly": true, "type": "boolean" }, "satisfiesPzi": { "description": "Output only. Reserved for future use.", "readOnly": true, "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta3DatasetGCSManagedConfig": { "id": "GoogleCloudDocumentaiV1beta3DatasetGCSManagedConfig", "description": "Configuration specific to the Cloud Storage-based implementation.", "type": "object", "properties": { "gcsPrefix": { "description": "Required. The Cloud Storage URI (a directory) where the documents belonging to the dataset must be stored.", "$ref": "GoogleCloudDocumentaiV1beta3GcsPrefix" } } }, "GoogleCloudDocumentaiV1beta3DatasetDocumentWarehouseConfig": { "id": "GoogleCloudDocumentaiV1beta3DatasetDocumentWarehouseConfig", "description": "Configuration specific to the Document AI Warehouse-based implementation.", "type": "object", "properties": { "collection": { "description": "Output only. The collection in Document AI Warehouse associated with the dataset.", "readOnly": true, "type": "string" }, "schema": { "description": "Output only. The schema in Document AI Warehouse associated with the dataset.", "readOnly": true, "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DatasetUnmanagedDatasetConfig": { "id": "GoogleCloudDocumentaiV1beta3DatasetUnmanagedDatasetConfig", "description": "Configuration specific to an unmanaged dataset.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3DatasetSpannerIndexingConfig": { "id": "GoogleCloudDocumentaiV1beta3DatasetSpannerIndexingConfig", "description": "Configuration specific to spanner-based indexing.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3ImportDocumentsRequest": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsRequest", "type": "object", "properties": { "batchDocumentsImportConfigs": { "description": "Required. The Cloud Storage uri containing raw documents that must be imported.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ImportDocumentsRequestBatchDocumentsImportConfig" } } } }, "GoogleCloudDocumentaiV1beta3ImportDocumentsRequestBatchDocumentsImportConfig": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsRequestBatchDocumentsImportConfig", "description": "Config for importing documents. Each batch can have its own dataset split type.", "type": "object", "properties": { "datasetSplit": { "description": "Target dataset split where the documents must be stored.", "type": "string", "enumDescriptions": [ "Default value if the enum is not set.", "Identifies the train documents.", "Identifies the test documents.", "Identifies the unassigned documents." ], "enum": [ "DATASET_SPLIT_TYPE_UNSPECIFIED", "DATASET_SPLIT_TRAIN", "DATASET_SPLIT_TEST", "DATASET_SPLIT_UNASSIGNED" ] }, "autoSplitConfig": { "description": "If set, documents will be automatically split into training and test split category with the specified ratio.", "$ref": "GoogleCloudDocumentaiV1beta3ImportDocumentsRequestBatchDocumentsImportConfigAutoSplitConfig" }, "batchInputConfig": { "description": "The common config to specify a set of documents used as input.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDocumentsInputConfig" } } }, "GoogleCloudDocumentaiV1beta3ImportDocumentsRequestBatchDocumentsImportConfigAutoSplitConfig": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsRequestBatchDocumentsImportConfigAutoSplitConfig", "description": "The config for auto-split.", "type": "object", "properties": { "trainingSplitRatio": { "description": "Ratio of training dataset split.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta3GetDocumentResponse": { "id": "GoogleCloudDocumentaiV1beta3GetDocumentResponse", "type": "object", "properties": { "document": { "$ref": "GoogleCloudDocumentaiV1beta3Document" } } }, "GoogleCloudDocumentaiV1beta3ListDocumentsRequest": { "id": "GoogleCloudDocumentaiV1beta3ListDocumentsRequest", "type": "object", "properties": { "pageSize": { "description": "The maximum number of documents to return. The service may return fewer than this value. If unspecified, at most 20 documents will be returned. The maximum value is 100; values above 100 will be coerced to 100.", "type": "integer", "format": "int32" }, "pageToken": { "description": "A page token, received from a previous `ListDocuments` call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to `ListDocuments` must match the call that provided the page token.", "type": "string" }, "filter": { "description": "Optional. Query to filter the documents based on https://google.aip.dev/160. ## Currently support query strings are: `SplitType=DATASET_SPLIT_TEST|DATASET_SPLIT_TRAIN|DATASET_SPLIT_UNASSIGNED` - `LabelingState=DOCUMENT_LABELED|DOCUMENT_UNLABELED|DOCUMENT_AUTO_LABELED` - `DisplayName=\\\"file_name.pdf\\\"` - `EntityType=abc/def` - `TagName=\\\"auto-labeling-running\\\"|\\\"sampled\\\"` Note: - Only `AND`, `=` and `!=` are supported. e.g. `DisplayName=file_name AND EntityType!=abc` IS supported. - Wildcard `*` is supported only in `DisplayName` filter - No duplicate filter keys are allowed, e.g. `EntityType=a AND EntityType=b` is NOT supported. - String match is case sensitive (for filter `DisplayName` & `EntityType`).", "type": "string" }, "returnTotalSize": { "description": "Optional. Controls if the request requires a total size of matched documents. See ListDocumentsResponse.total_size. Enabling this flag may adversely impact performance. Defaults to false.", "type": "boolean" }, "skip": { "description": "Optional. Number of results to skip beginning from the `page_token` if provided. https://google.aip.dev/158#skipping-results. It must be a non-negative integer. Negative values will be rejected. Note that this is not the number of pages to skip. If this value causes the cursor to move past the end of results, ListDocumentsResponse.document_metadata and ListDocumentsResponse.next_page_token will be empty.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3ListDocumentsResponse": { "id": "GoogleCloudDocumentaiV1beta3ListDocumentsResponse", "type": "object", "properties": { "documentMetadata": { "description": "Document metadata corresponding to the listed documents.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentMetadata" } }, "nextPageToken": { "description": "A token, which can be sent as ListDocumentsRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.", "type": "string" }, "totalSize": { "description": "Total count of documents queried.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3DocumentMetadata": { "id": "GoogleCloudDocumentaiV1beta3DocumentMetadata", "description": "Metadata about a document.", "type": "object", "properties": { "documentId": { "description": "Document identifier.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentId" }, "pageCount": { "description": "Number of pages in the document.", "type": "integer", "format": "int32" }, "datasetType": { "description": "Type of the dataset split to which the document belongs.", "type": "string", "enumDescriptions": [ "Default value if the enum is not set.", "Identifies the train documents.", "Identifies the test documents.", "Identifies the unassigned documents." ], "enum": [ "DATASET_SPLIT_TYPE_UNSPECIFIED", "DATASET_SPLIT_TRAIN", "DATASET_SPLIT_TEST", "DATASET_SPLIT_UNASSIGNED" ] }, "labelingState": { "description": "Labeling state of the document.", "type": "string", "enumDescriptions": [ "Default value if the enum is not set.", "Document has been labeled.", "Document has not been labeled.", "Document has been auto-labeled." ], "enum": [ "DOCUMENT_LABELING_STATE_UNSPECIFIED", "DOCUMENT_LABELED", "DOCUMENT_UNLABELED", "DOCUMENT_AUTO_LABELED" ] }, "displayName": { "description": "The display name of the document.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentId": { "id": "GoogleCloudDocumentaiV1beta3DocumentId", "description": "Document Identifier.", "type": "object", "properties": { "gcsManagedDocId": { "description": "A document id within user-managed Cloud Storage.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentIdGCSManagedDocumentId" }, "unmanagedDocId": { "description": "A document id within unmanaged dataset.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentIdUnmanagedDocumentId" }, "revisionRef": { "description": "Points to a specific revision of the document if set.", "$ref": "GoogleCloudDocumentaiV1beta3RevisionRef" } } }, "GoogleCloudDocumentaiV1beta3DocumentIdGCSManagedDocumentId": { "id": "GoogleCloudDocumentaiV1beta3DocumentIdGCSManagedDocumentId", "description": "Identifies a document uniquely within the scope of a dataset in the user-managed Cloud Storage option.", "type": "object", "properties": { "gcsUri": { "description": "Required. The Cloud Storage URI where the actual document is stored.", "type": "string" }, "cwDocId": { "description": "Id of the document (indexed) managed by Content Warehouse.", "deprecated": true, "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DocumentIdUnmanagedDocumentId": { "id": "GoogleCloudDocumentaiV1beta3DocumentIdUnmanagedDocumentId", "description": "Identifies a document uniquely within the scope of a dataset in unmanaged option.", "type": "object", "properties": { "docId": { "description": "Required. The id of the document.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3RevisionRef": { "id": "GoogleCloudDocumentaiV1beta3RevisionRef", "description": "The revision reference specifies which revision on the document to read.", "type": "object", "properties": { "revisionCase": { "description": "Reads the revision by the predefined case.", "type": "string", "enumDescriptions": [ "Unspecified case, fall back to read the `LATEST_HUMAN_REVIEW`.", "The latest revision made by a human.", "The latest revision based on timestamp.", "The first (OCR) revision." ], "enum": [ "REVISION_CASE_UNSPECIFIED", "LATEST_HUMAN_REVIEW", "LATEST_TIMESTAMP", "BASE_OCR_REVISION" ] }, "revisionId": { "description": "Reads the revision given by the id.", "type": "string" }, "latestProcessorVersion": { "description": "Reads the revision generated by the processor version. The format takes the full resource name of processor version. `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsRequest": { "id": "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsRequest", "type": "object", "properties": { "datasetDocuments": { "description": "Required. Dataset documents input. If given `filter`, all documents satisfying the filter will be deleted. If given documentIds, a maximum of 50 documents can be deleted in a batch. The request will be rejected if more than 50 document_ids are provided.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDatasetDocuments" } } }, "GoogleCloudDocumentaiV1beta3BatchDatasetDocuments": { "id": "GoogleCloudDocumentaiV1beta3BatchDatasetDocuments", "description": "Dataset documents that the batch operation will be applied to.", "type": "object", "properties": { "individualDocumentIds": { "description": "Document identifiers.", "$ref": "GoogleCloudDocumentaiV1beta3BatchDatasetDocumentsIndividualDocumentIds" }, "filter": { "description": "A filter matching the documents. Follows the same format and restriction as [google.cloud.documentai.master.ListDocumentsRequest.filter].", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3BatchDatasetDocumentsIndividualDocumentIds": { "id": "GoogleCloudDocumentaiV1beta3BatchDatasetDocumentsIndividualDocumentIds", "description": "List of individual DocumentIds.", "type": "object", "properties": { "documentIds": { "description": "Required. List of Document IDs indicating where the actual documents are stored.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3DocumentId" } } } }, "GoogleCloudDocumentaiV1beta3DatasetSchema": { "id": "GoogleCloudDocumentaiV1beta3DatasetSchema", "description": "Dataset Schema.", "type": "object", "properties": { "name": { "description": "Dataset schema resource name. Format: `projects/{project}/locations/{location}/processors/{processor}/dataset/datasetSchema`", "type": "string" }, "documentSchema": { "description": "Optional. Schema of the dataset.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentSchema" } } }, "GoogleCloudLocationListLocationsResponse": { "id": "GoogleCloudLocationListLocationsResponse", "description": "The response message for Locations.ListLocations.", "type": "object", "properties": { "locations": { "description": "A list of locations that matches the specified filter in the request.", "type": "array", "items": { "$ref": "GoogleCloudLocationLocation" } }, "nextPageToken": { "description": "The standard List next-page token.", "type": "string" } } }, "GoogleCloudLocationLocation": { "id": "GoogleCloudLocationLocation", "description": "A resource that represents a Google Cloud location.", "type": "object", "properties": { "name": { "description": "Resource name for the location, which may vary between implementations. For example: `\"projects/example-project/locations/us-east1\"`", "type": "string" }, "locationId": { "description": "The canonical id for this location. For example: `\"us-east1\"`.", "type": "string" }, "displayName": { "description": "The friendly name for this location, typically a nearby city name. For example, \"Tokyo\".", "type": "string" }, "labels": { "description": "Cross-service attributes for the location. For example {\"cloud.googleapis.com/region\": \"us-east1\"}", "type": "object", "additionalProperties": { "type": "string" } }, "metadata": { "description": "Service-specific metadata. For example the available capacity at the given location.", "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } } } }, "GoogleCloudDocumentaiV1BatchProcessResponse": { "id": "GoogleCloudDocumentaiV1BatchProcessResponse", "description": "Response message for BatchProcessDocuments.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1BatchProcessMetadata": { "id": "GoogleCloudDocumentaiV1BatchProcessMetadata", "description": "The long-running operation metadata for BatchProcessDocuments.", "type": "object", "properties": { "state": { "description": "The state of the current batch processing.", "type": "string", "enumDescriptions": [ "The default value. This value is used if the state is omitted.", "Request operation is waiting for scheduling.", "Request is being processed.", "The batch processing completed successfully.", "The batch processing was being cancelled.", "The batch processing was cancelled.", "The batch processing has failed." ], "enum": [ "STATE_UNSPECIFIED", "WAITING", "RUNNING", "SUCCEEDED", "CANCELLING", "CANCELLED", "FAILED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing. For example, the error message if the operation is failed.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" }, "individualProcessStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1BatchProcessMetadataIndividualProcessStatus" } } } }, "GoogleCloudDocumentaiV1BatchProcessMetadataIndividualProcessStatus": { "id": "GoogleCloudDocumentaiV1BatchProcessMetadataIndividualProcessStatus", "description": "The status of a each individual document in the batch process.", "type": "object", "properties": { "inputGcsSource": { "description": "The source of the document, same as the input_gcs_source field in the request when the batch process started.", "type": "string" }, "status": { "description": "The status processing the document.", "$ref": "GoogleRpcStatus" }, "outputGcsDestination": { "description": "The Cloud Storage output destination (in the request as DocumentOutputConfig.GcsOutputConfig.gcs_uri) of the processed document if it was successful, otherwise empty.", "type": "string" }, "humanReviewStatus": { "description": "The status of human review on the processed document.", "$ref": "GoogleCloudDocumentaiV1HumanReviewStatus" } } }, "GoogleCloudDocumentaiV1HumanReviewStatus": { "id": "GoogleCloudDocumentaiV1HumanReviewStatus", "description": "The status of human review on a processed document.", "type": "object", "properties": { "state": { "description": "The state of human review on the processing request.", "type": "string", "enumDescriptions": [ "Human review state is unspecified. Most likely due to an internal error.", "Human review is skipped for the document. This can happen because human review isn't enabled on the processor or the processing request has been set to skip this document.", "Human review validation is triggered and passed, so no review is needed.", "Human review validation is triggered and the document is under review.", "Some error happened during triggering human review, see the state_message for details." ], "enum": [ "STATE_UNSPECIFIED", "SKIPPED", "VALIDATION_PASSED", "IN_PROGRESS", "ERROR" ] }, "stateMessage": { "description": "A message providing more details about the human review state.", "type": "string" }, "humanReviewOperation": { "description": "The name of the operation triggered by the processed document. This field is populated only when the state is `HUMAN_REVIEW_IN_PROGRESS`. It has the same response type and metadata as the long-running operation returned by ReviewDocument.", "type": "string" } } }, "GoogleCloudDocumentaiV1ReviewDocumentResponse": { "id": "GoogleCloudDocumentaiV1ReviewDocumentResponse", "description": "Response message for the ReviewDocument method.", "type": "object", "properties": { "gcsDestination": { "description": "The Cloud Storage uri for the human reviewed document if the review is succeeded.", "type": "string" }, "state": { "description": "The state of the review operation.", "type": "string", "enumDescriptions": [ "The default value. This value is used if the state is omitted.", "The review operation is rejected by the reviewer.", "The review operation is succeeded." ], "enum": [ "STATE_UNSPECIFIED", "REJECTED", "SUCCEEDED" ] }, "rejectionReason": { "description": "The reason why the review is rejected by reviewer.", "type": "string" } } }, "GoogleCloudDocumentaiV1ReviewDocumentOperationMetadata": { "id": "GoogleCloudDocumentaiV1ReviewDocumentOperationMetadata", "description": "The long-running operation metadata for the ReviewDocument method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" }, "questionId": { "description": "The Crowd Compute question ID.", "type": "string" } } }, "GoogleCloudDocumentaiV1CommonOperationMetadata": { "id": "GoogleCloudDocumentaiV1CommonOperationMetadata", "description": "The common metadata for long running operations.", "type": "object", "properties": { "state": { "description": "The state of the operation.", "type": "string", "enumDescriptions": [ "Unspecified state.", "Operation is still running.", "Operation is being cancelled.", "Operation succeeded.", "Operation failed.", "Operation is cancelled." ], "enum": [ "STATE_UNSPECIFIED", "RUNNING", "CANCELLING", "SUCCEEDED", "FAILED", "CANCELLED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing.", "type": "string" }, "resource": { "description": "A related resource to this operation.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" } } }, "GoogleCloudDocumentaiV1DeleteProcessorMetadata": { "id": "GoogleCloudDocumentaiV1DeleteProcessorMetadata", "description": "The long-running operation metadata for the DeleteProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1EnableProcessorResponse": { "id": "GoogleCloudDocumentaiV1EnableProcessorResponse", "description": "Response message for the EnableProcessor method. Intentionally empty proto for adding fields in future.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1EnableProcessorMetadata": { "id": "GoogleCloudDocumentaiV1EnableProcessorMetadata", "description": "The long-running operation metadata for the EnableProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1DisableProcessorResponse": { "id": "GoogleCloudDocumentaiV1DisableProcessorResponse", "description": "Response message for the DisableProcessor method. Intentionally empty proto for adding fields in future.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1DisableProcessorMetadata": { "id": "GoogleCloudDocumentaiV1DisableProcessorMetadata", "description": "The long-running operation metadata for the DisableProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1DeleteProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1DeleteProcessorVersionMetadata", "description": "The long-running operation metadata for the DeleteProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1DeployProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1DeployProcessorVersionMetadata", "description": "The long-running operation metadata for the DeployProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1DeployProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1DeployProcessorVersionResponse", "description": "Response message for the DeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1UndeployProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1UndeployProcessorVersionMetadata", "description": "The long-running operation metadata for the UndeployProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1UndeployProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1UndeployProcessorVersionResponse", "description": "Response message for the UndeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1SetDefaultProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1SetDefaultProcessorVersionMetadata", "description": "The long-running operation metadata for the SetDefaultProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1SetDefaultProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1SetDefaultProcessorVersionResponse", "description": "Response message for the SetDefaultProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1TrainProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1TrainProcessorVersionMetadata", "description": "The metadata that represents a processor version being created.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" }, "trainingDatasetValidation": { "description": "The training dataset validation information.", "$ref": "GoogleCloudDocumentaiV1TrainProcessorVersionMetadataDatasetValidation" }, "testDatasetValidation": { "description": "The test dataset validation information.", "$ref": "GoogleCloudDocumentaiV1TrainProcessorVersionMetadataDatasetValidation" } } }, "GoogleCloudDocumentaiV1TrainProcessorVersionMetadataDatasetValidation": { "id": "GoogleCloudDocumentaiV1TrainProcessorVersionMetadataDatasetValidation", "description": "The dataset validation information. This includes any and all errors with documents and the dataset.", "type": "object", "properties": { "documentErrorCount": { "description": "The total number of document errors.", "type": "integer", "format": "int32" }, "datasetErrorCount": { "description": "The total number of dataset errors.", "type": "integer", "format": "int32" }, "documentErrors": { "description": "Error information pertaining to specific documents. A maximum of 10 document errors will be returned. Any document with errors will not be used throughout training.", "type": "array", "items": { "$ref": "GoogleRpcStatus" } }, "datasetErrors": { "description": "Error information for the dataset as a whole. A maximum of 10 dataset errors will be returned. A single dataset error is terminal for training.", "type": "array", "items": { "$ref": "GoogleRpcStatus" } } } }, "GoogleCloudDocumentaiV1TrainProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1TrainProcessorVersionResponse", "description": "The response for TrainProcessorVersion.", "type": "object", "properties": { "processorVersion": { "description": "The resource name of the processor version produced by training.", "type": "string" } } }, "GoogleCloudDocumentaiV1EvaluateProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1EvaluateProcessorVersionMetadata", "description": "Metadata of the EvaluateProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1EvaluateProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1EvaluateProcessorVersionResponse", "description": "Response of the EvaluateProcessorVersion method.", "type": "object", "properties": { "evaluation": { "description": "The resource name of the created evaluation.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1BatchProcessDocumentsResponse": { "id": "GoogleCloudDocumentaiV1beta1BatchProcessDocumentsResponse", "description": "Response to an batch document processing request. This is returned in the LRO Operation after the operation is complete.", "type": "object", "properties": { "responses": { "description": "Responses for each individual document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1ProcessDocumentResponse" } } } }, "GoogleCloudDocumentaiV1beta1ProcessDocumentResponse": { "id": "GoogleCloudDocumentaiV1beta1ProcessDocumentResponse", "description": "Response to a single document processing request.", "type": "object", "properties": { "inputConfig": { "description": "Information about the input file. This is the same as the corresponding input config in the request.", "$ref": "GoogleCloudDocumentaiV1beta1InputConfig" }, "outputConfig": { "description": "The output location of the parsed responses. The responses are written to this location as JSON-serialized `Document` objects.", "$ref": "GoogleCloudDocumentaiV1beta1OutputConfig" } } }, "GoogleCloudDocumentaiV1beta1InputConfig": { "id": "GoogleCloudDocumentaiV1beta1InputConfig", "description": "The desired input location and metadata.", "type": "object", "properties": { "gcsSource": { "description": "The Google Cloud Storage location to read the input from. This must be a single file.", "$ref": "GoogleCloudDocumentaiV1beta1GcsSource" }, "mimeType": { "description": "Required. Mimetype of the input. Current supported mimetypes are application/pdf, image/tiff, and image/gif. In addition, application/json type is supported for requests with ProcessDocumentRequest.automl_params field set. The JSON file needs to be in Document format.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1GcsSource": { "id": "GoogleCloudDocumentaiV1beta1GcsSource", "description": "The Google Cloud Storage location where the input file will be read from.", "type": "object", "properties": { "uri": { "type": "string" } } }, "GoogleCloudDocumentaiV1beta1OutputConfig": { "id": "GoogleCloudDocumentaiV1beta1OutputConfig", "description": "The desired output location and metadata.", "type": "object", "properties": { "gcsDestination": { "description": "The Google Cloud Storage location to write the output to.", "$ref": "GoogleCloudDocumentaiV1beta1GcsDestination" }, "pagesPerShard": { "description": "The max number of pages to include into each output Document shard JSON on Google Cloud Storage. The valid range is [1, 100]. If not specified, the default value is 20. For example, for one pdf file with 100 pages, 100 parsed pages will be produced. If `pages_per_shard` = 20, then 5 Document shard JSON files each containing 20 parsed pages will be written under the prefix OutputConfig.gcs_destination.uri and suffix pages-x-to-y.json where x and y are 1-indexed page numbers. Example GCS outputs with 157 pages and pages_per_shard = 50: pages-001-to-050.json pages-051-to-100.json pages-101-to-150.json pages-151-to-157.json", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1GcsDestination": { "id": "GoogleCloudDocumentaiV1beta1GcsDestination", "description": "The Google Cloud Storage location where the output file will be written to.", "type": "object", "properties": { "uri": { "type": "string" } } }, "GoogleCloudDocumentaiV1beta1Document": { "id": "GoogleCloudDocumentaiV1beta1Document", "description": "Document represents the canonical document resource in Document AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document AI to iterate and optimize for quality.", "type": "object", "properties": { "uri": { "description": "Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. For more information, refer to [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris).", "type": "string" }, "content": { "description": "Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.", "type": "string", "format": "byte" }, "mimeType": { "description": "An IANA published [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml).", "type": "string" }, "text": { "description": "Optional. UTF-8 encoded text in reading order from the document.", "type": "string" }, "textStyles": { "description": "Styles for the Document.text.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentStyle" } }, "pages": { "description": "Visual page layout for the Document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPage" } }, "entities": { "description": "A list of entities detected on Document.text. For document shards, entities in this list may cross shard boundaries.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentEntity" } }, "entityRelations": { "description": "Placeholder. Relationship among Document.entities.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentEntityRelation" } }, "textChanges": { "description": "Placeholder. A list of text corrections made to Document.text. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentTextChange" } }, "shardInfo": { "description": "Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentShardInfo" }, "error": { "description": "Any error that occurred while processing this document.", "$ref": "GoogleRpcStatus" }, "revisions": { "description": "Placeholder. Revision history of this document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentRevision" } }, "documentLayout": { "description": "Parsed layout of the document.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayout" }, "chunkedDocument": { "description": "Document chunked based on chunking config.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocument" } } }, "GoogleCloudDocumentaiV1beta1DocumentStyle": { "id": "GoogleCloudDocumentaiV1beta1DocumentStyle", "description": "Annotation for common text style attributes. This adheres to CSS conventions as much as possible.", "type": "object", "properties": { "textAnchor": { "description": "Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentTextAnchor" }, "color": { "description": "Text color.", "$ref": "GoogleTypeColor" }, "backgroundColor": { "description": "Text background color.", "$ref": "GoogleTypeColor" }, "fontWeight": { "description": "[Font weight](https://www.w3schools.com/cssref/pr_font_weight.asp). Possible values are `normal`, `bold`, `bolder`, and `lighter`.", "type": "string" }, "textStyle": { "description": "[Text style](https://www.w3schools.com/cssref/pr_font_font-style.asp). Possible values are `normal`, `italic`, and `oblique`.", "type": "string" }, "textDecoration": { "description": "[Text decoration](https://www.w3schools.com/cssref/pr_text_text-decoration.asp). Follows CSS standard. ", "type": "string" }, "fontSize": { "description": "Font size.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentStyleFontSize" }, "fontFamily": { "description": "Font family such as `Arial`, `Times New Roman`. https://www.w3schools.com/cssref/pr_font_font-family.asp", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentTextAnchor": { "id": "GoogleCloudDocumentaiV1beta1DocumentTextAnchor", "description": "Text reference indexing into the Document.text.", "type": "object", "properties": { "textSegments": { "description": "The text segments from the Document.text.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentTextAnchorTextSegment" } }, "content": { "description": "Contains the content of the text span so that users do not have to look it up in the text_segments. It is always populated for formFields.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentTextAnchorTextSegment": { "id": "GoogleCloudDocumentaiV1beta1DocumentTextAnchorTextSegment", "description": "A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset", "type": "object", "properties": { "startIndex": { "description": "TextSegment start UTF-8 char index in the Document.text.", "type": "string", "format": "int64" }, "endIndex": { "description": "TextSegment half open end UTF-8 char index in the Document.text.", "type": "string", "format": "int64" } } }, "GoogleCloudDocumentaiV1beta1DocumentStyleFontSize": { "id": "GoogleCloudDocumentaiV1beta1DocumentStyleFontSize", "description": "Font size with unit.", "type": "object", "properties": { "size": { "description": "Font size for the text.", "type": "number", "format": "float" }, "unit": { "description": "Unit for the font size. Follows CSS naming (such as `in`, `px`, and `pt`).", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentPage": { "id": "GoogleCloudDocumentaiV1beta1DocumentPage", "description": "A page in a Document.", "type": "object", "properties": { "pageNumber": { "description": "1-based index for current Page in a parent Document. Useful when a page is taken out of a Document for individual processing.", "type": "integer", "format": "int32" }, "image": { "description": "Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageImage" }, "transforms": { "description": "Transformation matrices that were applied to the original document image to produce Page.image.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageMatrix" } }, "dimension": { "description": "Physical dimension of the page.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDimension" }, "layout": { "description": "Layout for the page.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "blocks": { "description": "A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageBlock" } }, "paragraphs": { "description": "A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageParagraph" } }, "lines": { "description": "A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLine" } }, "tokens": { "description": "A list of visually detected tokens on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageToken" } }, "visualElements": { "description": "A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageVisualElement" } }, "tables": { "description": "A list of visually detected tables on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageTable" } }, "formFields": { "description": "A list of visually detected form fields on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageFormField" } }, "symbols": { "description": "A list of visually detected symbols on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageSymbol" } }, "detectedBarcodes": { "description": "A list of detected barcodes.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedBarcode" } }, "imageQualityScores": { "description": "Image quality scores.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageImageQualityScores" }, "provenance": { "description": "The history of this page.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageImage": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageImage", "description": "Rendered image contents for this page.", "type": "object", "properties": { "content": { "description": "Raw byte content of the image.", "type": "string", "format": "byte" }, "mimeType": { "description": "Encoding [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml) for the image.", "type": "string" }, "width": { "description": "Width of the image in pixels.", "type": "integer", "format": "int32" }, "height": { "description": "Height of the image in pixels.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageMatrix": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageMatrix", "description": "Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.", "type": "object", "properties": { "rows": { "description": "Number of rows in the matrix.", "type": "integer", "format": "int32" }, "cols": { "description": "Number of columns in the matrix.", "type": "integer", "format": "int32" }, "type": { "description": "This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html", "type": "integer", "format": "int32" }, "data": { "description": "The matrix data.", "type": "string", "format": "byte" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageDimension": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageDimension", "description": "Dimension for the page.", "type": "object", "properties": { "width": { "description": "Page width.", "type": "number", "format": "float" }, "height": { "description": "Page height.", "type": "number", "format": "float" }, "unit": { "description": "Dimension unit.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageLayout": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageLayout", "description": "Visual element describing a layout unit on a page.", "type": "object", "properties": { "textAnchor": { "description": "Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentTextAnchor" }, "confidence": { "description": "Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range `[0, 1]`.", "type": "number", "format": "float" }, "boundingPoly": { "description": "The bounding polygon for the Layout.", "$ref": "GoogleCloudDocumentaiV1beta1BoundingPoly" }, "orientation": { "description": "Detected orientation for the Layout.", "type": "string", "enumDescriptions": [ "Unspecified orientation.", "Orientation is aligned with page up.", "Orientation is aligned with page right. Turn the head 90 degrees clockwise from upright to read.", "Orientation is aligned with page down. Turn the head 180 degrees from upright to read.", "Orientation is aligned with page left. Turn the head 90 degrees counterclockwise from upright to read." ], "enum": [ "ORIENTATION_UNSPECIFIED", "PAGE_UP", "PAGE_RIGHT", "PAGE_DOWN", "PAGE_LEFT" ] } } }, "GoogleCloudDocumentaiV1beta1BoundingPoly": { "id": "GoogleCloudDocumentaiV1beta1BoundingPoly", "description": "A bounding polygon for the detected image annotation.", "type": "object", "properties": { "vertices": { "description": "The bounding polygon vertices.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1Vertex" } }, "normalizedVertices": { "description": "The bounding polygon normalized vertices.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1NormalizedVertex" } } } }, "GoogleCloudDocumentaiV1beta1Vertex": { "id": "GoogleCloudDocumentaiV1beta1Vertex", "description": "A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "integer", "format": "int32" }, "y": { "description": "Y coordinate (starts from the top of the image).", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1NormalizedVertex": { "id": "GoogleCloudDocumentaiV1beta1NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "number", "format": "float" }, "y": { "description": "Y coordinate (starts from the top of the image).", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage", "description": "Detected language for a structural component.", "type": "object", "properties": { "languageCode": { "description": "The [BCP-47 language code](https://www.unicode.org/reports/tr35/#Unicode_locale_identifier), such as `en-US` or `sr-Latn`.", "type": "string" }, "confidence": { "description": "Confidence of detected language. Range `[0, 1]`.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageBlock": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageBlock", "description": "A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.", "type": "object", "properties": { "layout": { "description": "Layout for Block.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta1DocumentProvenance": { "id": "GoogleCloudDocumentaiV1beta1DocumentProvenance", "description": "Structure to identify provenance relationships between annotations in different revisions.", "type": "object", "properties": { "revision": { "description": "The index of the revision that produced this element.", "deprecated": true, "type": "integer", "format": "int32" }, "id": { "description": "The Id of this operation. Needs to be unique within the scope of the revision.", "deprecated": true, "type": "integer", "format": "int32" }, "parents": { "description": "References to the original elements that are replaced.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenanceParent" } }, "type": { "description": "The type of provenance operation.", "type": "string", "enumDescriptions": [ "Operation type unspecified. If no operation is specified a provenance entry is simply used to match against a `parent`.", "Add an element.", "Remove an element identified by `parent`.", "Updates any fields within the given provenance scope of the message. It overwrites the fields rather than replacing them. Use this when you want to update a field value of an entity without also updating all the child properties.", "Currently unused. Replace an element identified by `parent`.", "Deprecated. Request human review for the element identified by `parent`.", "Deprecated. Element is reviewed and approved at human review, confidence will be set to 1.0.", "Deprecated. Element is skipped in the validation process." ], "enumDeprecated": [ false, false, false, false, false, true, true, true ], "enum": [ "OPERATION_TYPE_UNSPECIFIED", "ADD", "REMOVE", "UPDATE", "REPLACE", "EVAL_REQUESTED", "EVAL_APPROVED", "EVAL_SKIPPED" ] } } }, "GoogleCloudDocumentaiV1beta1DocumentProvenanceParent": { "id": "GoogleCloudDocumentaiV1beta1DocumentProvenanceParent", "description": "The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.", "type": "object", "properties": { "revision": { "description": "The index of the index into current revision's parent_ids list.", "type": "integer", "format": "int32" }, "index": { "description": "The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) in the parent revision.", "type": "integer", "format": "int32" }, "id": { "description": "The id of the parent provenance.", "deprecated": true, "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageParagraph": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageParagraph", "description": "A collection of lines that a human would perceive as a paragraph.", "type": "object", "properties": { "layout": { "description": "Layout for Paragraph.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageLine": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageLine", "description": "A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.", "type": "object", "properties": { "layout": { "description": "Layout for Line.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageToken": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageToken", "description": "A detected token.", "type": "object", "properties": { "layout": { "description": "Layout for Token.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "detectedBreak": { "description": "Detected break at the end of a Token.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageTokenDetectedBreak" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" }, "styleInfo": { "description": "Text style attributes.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageTokenStyleInfo" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageTokenDetectedBreak": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageTokenDetectedBreak", "description": "Detected break at the end of a Token.", "type": "object", "properties": { "type": { "description": "Detected break type.", "type": "string", "enumDescriptions": [ "Unspecified break type.", "A single whitespace.", "A wider whitespace.", "A hyphen that indicates that a token has been split across lines." ], "enum": [ "TYPE_UNSPECIFIED", "SPACE", "WIDE_SPACE", "HYPHEN" ] } } }, "GoogleCloudDocumentaiV1beta1DocumentPageTokenStyleInfo": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageTokenStyleInfo", "description": "Font and other text style attributes.", "type": "object", "properties": { "fontSize": { "description": "Font size in points (`1` point is `¹⁄₇₂` inches).", "type": "integer", "format": "int32" }, "pixelFontSize": { "description": "Font size in pixels, equal to _unrounded font_size_ * _resolution_ ÷ `72.0`.", "type": "number", "format": "double" }, "letterSpacing": { "description": "Letter spacing in points.", "type": "number", "format": "double" }, "fontType": { "description": "Name or style of the font.", "type": "string" }, "bold": { "description": "Whether the text is bold (equivalent to font_weight is at least `700`).", "type": "boolean" }, "italic": { "description": "Whether the text is italic.", "type": "boolean" }, "underlined": { "description": "Whether the text is underlined.", "type": "boolean" }, "strikeout": { "description": "Whether the text is strikethrough. This feature is not supported yet.", "type": "boolean" }, "subscript": { "description": "Whether the text is a subscript. This feature is not supported yet.", "type": "boolean" }, "superscript": { "description": "Whether the text is a superscript. This feature is not supported yet.", "type": "boolean" }, "smallcaps": { "description": "Whether the text is in small caps. This feature is not supported yet.", "type": "boolean" }, "fontWeight": { "description": "TrueType weight on a scale `100` (thin) to `1000` (ultra-heavy). Normal is `400`, bold is `700`.", "type": "integer", "format": "int32" }, "handwritten": { "description": "Whether the text is handwritten.", "type": "boolean" }, "textColor": { "description": "Color of the text.", "$ref": "GoogleTypeColor" }, "backgroundColor": { "description": "Color of the background.", "$ref": "GoogleTypeColor" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageVisualElement": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageVisualElement", "description": "Detected non-text visual elements e.g. checkbox, signature etc. on the page.", "type": "object", "properties": { "layout": { "description": "Layout for VisualElement.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "type": { "description": "Type of the VisualElement.", "type": "string" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta1DocumentPageTable": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageTable", "description": "A table representation similar to HTML table structure.", "type": "object", "properties": { "layout": { "description": "Layout for Table.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "headerRows": { "description": "Header rows of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageTableTableRow" } }, "bodyRows": { "description": "Body rows of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageTableTableRow" } }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this table.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageTableTableRow": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageTableTableRow", "description": "A row of table cells.", "type": "object", "properties": { "cells": { "description": "Cells that make up this row.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageTableTableCell" } } } }, "GoogleCloudDocumentaiV1beta1DocumentPageTableTableCell": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageTableTableCell", "description": "A cell representation inside the table.", "type": "object", "properties": { "layout": { "description": "Layout for TableCell.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "rowSpan": { "description": "How many rows this cell spans.", "type": "integer", "format": "int32" }, "colSpan": { "description": "How many columns this cell spans.", "type": "integer", "format": "int32" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta1DocumentPageFormField": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageFormField", "description": "A form field detected on the page.", "type": "object", "properties": { "fieldName": { "description": "Layout for the FormField name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "fieldValue": { "description": "Layout for the FormField value.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "nameDetectedLanguages": { "description": "A list of detected languages for name together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "valueDetectedLanguages": { "description": "A list of detected languages for value together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } }, "valueType": { "description": "If the value is non-textual, this field represents the type. Current valid values are: - blank (this indicates the `field_value` is normal text) - `unfilled_checkbox` - `filled_checkbox`", "type": "string" }, "correctedKeyText": { "description": "Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.", "type": "string" }, "correctedValueText": { "description": "Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.", "type": "string" }, "provenance": { "description": "The history of this annotation.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageSymbol": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageSymbol", "description": "A detected symbol.", "type": "object", "properties": { "layout": { "description": "Layout for Symbol.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta1DocumentPageDetectedBarcode": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageDetectedBarcode", "description": "A detected barcode.", "type": "object", "properties": { "layout": { "description": "Layout for DetectedBarcode.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageLayout" }, "barcode": { "description": "Detailed barcode information of the DetectedBarcode.", "$ref": "GoogleCloudDocumentaiV1beta1Barcode" } } }, "GoogleCloudDocumentaiV1beta1Barcode": { "id": "GoogleCloudDocumentaiV1beta1Barcode", "description": "Encodes the detailed information of a barcode.", "type": "object", "properties": { "format": { "description": "Format of a barcode. The supported formats are: - `CODE_128`: Code 128 type. - `CODE_39`: Code 39 type. - `CODE_93`: Code 93 type. - `CODABAR`: Codabar type. - `DATA_MATRIX`: 2D Data Matrix type. - `ITF`: ITF type. - `EAN_13`: EAN-13 type. - `EAN_8`: EAN-8 type. - `QR_CODE`: 2D QR code type. - `UPC_A`: UPC-A type. - `UPC_E`: UPC-E type. - `PDF417`: PDF417 type. - `AZTEC`: 2D Aztec code type. - `DATABAR`: GS1 DataBar code type.", "type": "string" }, "valueFormat": { "description": "Value format describes the format of the value that a barcode encodes. The supported formats are: - `CONTACT_INFO`: Contact information. - `EMAIL`: Email address. - `ISBN`: ISBN identifier. - `PHONE`: Phone number. - `PRODUCT`: Product. - `SMS`: SMS message. - `TEXT`: Text string. - `URL`: URL address. - `WIFI`: Wifi information. - `GEO`: Geo-localization. - `CALENDAR_EVENT`: Calendar event. - `DRIVER_LICENSE`: Driver's license.", "type": "string" }, "rawValue": { "description": "Raw value encoded in the barcode. For example: `'MEBKM:TITLE:Google;URL:https://www.google.com;;'`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageImageQualityScores": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageImageQualityScores", "description": "Image quality scores for the page image.", "type": "object", "properties": { "qualityScore": { "description": "The overall quality score. Range `[0, 1]` where `1` is perfect quality.", "type": "number", "format": "float" }, "detectedDefects": { "description": "A list of detected defects.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageImageQualityScoresDetectedDefect" } } } }, "GoogleCloudDocumentaiV1beta1DocumentPageImageQualityScoresDetectedDefect": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageImageQualityScoresDetectedDefect", "description": "Image Quality Defects", "type": "object", "properties": { "type": { "description": "Name of the defect type. Supported values are: - `quality/defect_blurry` - `quality/defect_noisy` - `quality/defect_dark` - `quality/defect_faint` - `quality/defect_text_too_small` - `quality/defect_document_cutoff` - `quality/defect_text_cutoff` - `quality/defect_glare`", "type": "string" }, "confidence": { "description": "Confidence of detected defect. Range `[0, 1]` where `1` indicates strong confidence that the defect exists.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta1DocumentEntity": { "id": "GoogleCloudDocumentaiV1beta1DocumentEntity", "description": "An entity that could be a phrase in the text or a property that belongs to the document. It is a known entity type, such as a person, an organization, or location.", "type": "object", "properties": { "textAnchor": { "description": "Optional. Provenance of the entity. Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentTextAnchor" }, "type": { "description": "Required. Entity type from a schema e.g. `Address`.", "type": "string" }, "mentionText": { "description": "Optional. Text value of the entity e.g. `1600 Amphitheatre Pkwy`.", "type": "string" }, "mentionId": { "description": "Optional. Deprecated. Use `id` field instead.", "type": "string" }, "confidence": { "description": "Optional. Confidence of detected Schema entity. Range `[0, 1]`.", "type": "number", "format": "float" }, "pageAnchor": { "description": "Optional. Represents the provenance of this entity wrt. the location on the page where it was found.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageAnchor" }, "id": { "description": "Optional. Canonical id. This will be a unique value in the entity list for this document.", "type": "string" }, "normalizedValue": { "description": "Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentEntityNormalizedValue" }, "properties": { "description": "Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentEntity" } }, "provenance": { "description": "Optional. The history of this annotation.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" }, "redacted": { "description": "Optional. Whether the entity will be redacted for de-identification purposes.", "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta1DocumentPageAnchor": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageAnchor", "description": "Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types.", "type": "object", "properties": { "pageRefs": { "description": "One or more references to visual page elements", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentPageAnchorPageRef" } } } }, "GoogleCloudDocumentaiV1beta1DocumentPageAnchorPageRef": { "id": "GoogleCloudDocumentaiV1beta1DocumentPageAnchorPageRef", "description": "Represents a weak reference to a page element within a document.", "type": "object", "properties": { "page": { "description": "Required. Index into the Document.pages element, for example using `Document.pages` to locate the related page element. This field is skipped when its value is the default `0`. See https://developers.google.com/protocol-buffers/docs/proto3#json.", "type": "string", "format": "int64" }, "layoutType": { "description": "Optional. The type of the layout element that is being referenced if any.", "type": "string", "enumDescriptions": [ "Layout Unspecified.", "References a Page.blocks element.", "References a Page.paragraphs element.", "References a Page.lines element.", "References a Page.tokens element.", "References a Page.visual_elements element.", "Refrrences a Page.tables element.", "References a Page.form_fields element." ], "enum": [ "LAYOUT_TYPE_UNSPECIFIED", "BLOCK", "PARAGRAPH", "LINE", "TOKEN", "VISUAL_ELEMENT", "TABLE", "FORM_FIELD" ] }, "layoutId": { "description": "Optional. Deprecated. Use PageRef.bounding_poly instead.", "deprecated": true, "type": "string" }, "boundingPoly": { "description": "Optional. Identifies the bounding polygon of a layout element on the page. If `layout_type` is set, the bounding polygon must be exactly the same to the layout element it's referring to.", "$ref": "GoogleCloudDocumentaiV1beta1BoundingPoly" }, "confidence": { "description": "Optional. Confidence of detected page element, if applicable. Range `[0, 1]`.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta1DocumentEntityNormalizedValue": { "id": "GoogleCloudDocumentaiV1beta1DocumentEntityNormalizedValue", "description": "Parsed and normalized entity value.", "type": "object", "properties": { "moneyValue": { "description": "Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto", "$ref": "GoogleTypeMoney" }, "dateValue": { "description": "Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto", "$ref": "GoogleTypeDate" }, "datetimeValue": { "description": "DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto", "$ref": "GoogleTypeDateTime" }, "addressValue": { "description": "Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto", "$ref": "GoogleTypePostalAddress" }, "booleanValue": { "description": "Boolean value. Can be used for entities with binary values, or for checkboxes.", "type": "boolean" }, "integerValue": { "description": "Integer value.", "type": "integer", "format": "int32" }, "floatValue": { "description": "Float value.", "type": "number", "format": "float" }, "text": { "description": "Optional. An optional field to store a normalized string. For some entity types, one of respective `structured_value` fields may also be populated. Also not all the types of `structured_value` will be normalized. For example, some processors may not generate `float` or `integer` normalized text by default. Below are sample formats mapped to structured values. - Money/Currency type (`money_value`) is in the ISO 4217 text format. - Date type (`date_value`) is in the ISO 8601 text format. - Datetime type (`datetime_value`) is in the ISO 8601 text format.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentEntityRelation": { "id": "GoogleCloudDocumentaiV1beta1DocumentEntityRelation", "description": "Relationship between Entities.", "type": "object", "properties": { "subjectId": { "description": "Subject entity id.", "type": "string" }, "objectId": { "description": "Object entity id.", "type": "string" }, "relation": { "description": "Relationship description.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentTextChange": { "id": "GoogleCloudDocumentaiV1beta1DocumentTextChange", "description": "This message is used for text changes aka. OCR corrections.", "type": "object", "properties": { "textAnchor": { "description": "Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single `TextAnchor.text_segments` element. If the start and end index of the text segment are the same, the text change is inserted before that index.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentTextAnchor" }, "changedText": { "description": "The text that replaces the text identified in the `text_anchor`.", "type": "string" }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentProvenance" } } } }, "GoogleCloudDocumentaiV1beta1DocumentShardInfo": { "id": "GoogleCloudDocumentaiV1beta1DocumentShardInfo", "description": "For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is.", "type": "object", "properties": { "shardIndex": { "description": "The 0-based index of this shard.", "type": "string", "format": "int64" }, "shardCount": { "description": "Total number of shards.", "type": "string", "format": "int64" }, "textOffset": { "description": "The index of the first character in Document.text in the overall document global text.", "type": "string", "format": "int64" } } }, "GoogleCloudDocumentaiV1beta1DocumentRevision": { "id": "GoogleCloudDocumentaiV1beta1DocumentRevision", "description": "Contains past or forward revisions of this document.", "type": "object", "properties": { "agent": { "description": "If the change was made by a person specify the name or id of that person.", "type": "string" }, "processor": { "description": "If the annotation was made by processor identify the processor by its resource name.", "type": "string" }, "id": { "description": "Id of the revision, internally generated by doc proto storage. Unique within the context of the document.", "type": "string" }, "parent": { "description": "The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.", "deprecated": true, "type": "array", "items": { "type": "integer", "format": "int32" } }, "parentIds": { "description": "The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.", "type": "array", "items": { "type": "string" } }, "createTime": { "description": "The time that the revision was created, internally generated by doc proto storage at the time of create.", "type": "string", "format": "google-datetime" }, "humanReview": { "description": "Human Review information of this revision.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentRevisionHumanReview" } } }, "GoogleCloudDocumentaiV1beta1DocumentRevisionHumanReview": { "id": "GoogleCloudDocumentaiV1beta1DocumentRevisionHumanReview", "description": "Human Review information of the document.", "type": "object", "properties": { "state": { "description": "Human review state. e.g. `requested`, `succeeded`, `rejected`.", "type": "string" }, "stateMessage": { "description": "A message providing more details about the current state of processing. For example, the rejection reason when the state is `rejected`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayout": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayout", "description": "Represents the parsed layout of a document as a collection of blocks that the document is divided into.", "type": "object", "properties": { "blocks": { "description": "List of blocks in the document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlock": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlock", "description": "Represents a block. A block could be one of the various types (text, table, list) supported.", "type": "object", "properties": { "textBlock": { "description": "Block consisting of text content.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock" }, "tableBlock": { "description": "Block consisting of table content/structure.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock" }, "listBlock": { "description": "Block consisting of list content/structure.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock" }, "blockId": { "description": "ID of the block.", "type": "string" }, "pageSpan": { "description": "Page span of the block.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan" } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock", "description": "Represents a text type block.", "type": "object", "properties": { "text": { "description": "Text content stored in the block.", "type": "string" }, "type": { "description": "Type of the text in the block. Available options are: `paragraph`, `subtitle`, `heading-1`, `heading-2`, `heading-3`, `heading-4`, `heading-5`, `header`, `footer`.", "type": "string" }, "blocks": { "description": "A text block could further have child blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock", "description": "Represents a table type block.", "type": "object", "properties": { "headerRows": { "description": "Header rows at the top of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow" } }, "bodyRows": { "description": "Body rows containing main table content.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow" } }, "caption": { "description": "Table caption/title.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow", "description": "Represents a row in a table.", "type": "object", "properties": { "cells": { "description": "A table row is a list of table cells.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell" } } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell", "description": "Represents a cell in a table row.", "type": "object", "properties": { "blocks": { "description": "A table cell is a list of blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlock" } }, "rowSpan": { "description": "How many rows this cell spans.", "type": "integer", "format": "int32" }, "colSpan": { "description": "How many columns this cell spans.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock", "description": "Represents a list type block.", "type": "object", "properties": { "listEntries": { "description": "List entries that constitute a list block.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry" } }, "type": { "description": "Type of the list_entries (if exist). Available options are `ordered` and `unordered`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry", "description": "Represents an entry in the list.", "type": "object", "properties": { "blocks": { "description": "A list entry is a list of blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan": { "id": "GoogleCloudDocumentaiV1beta1DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan", "description": "Represents where the block starts and ends in the document.", "type": "object", "properties": { "pageStart": { "description": "Page where block starts in the document.", "type": "integer", "format": "int32" }, "pageEnd": { "description": "Page where block ends in the document.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1DocumentChunkedDocument": { "id": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocument", "description": "Represents the chunks that the document is divided into.", "type": "object", "properties": { "chunks": { "description": "List of chunks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunk" } } } }, "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunk": { "id": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunk", "description": "Represents a chunk.", "type": "object", "properties": { "chunkId": { "description": "ID of the chunk.", "type": "string" }, "sourceBlockIds": { "description": "Unused.", "type": "array", "items": { "type": "string" } }, "content": { "description": "Text content of the chunk.", "type": "string" }, "pageSpan": { "description": "Page span of the chunk.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageSpan" }, "pageHeaders": { "description": "Page headers associated with the chunk.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageHeader" } }, "pageFooters": { "description": "Page footers associated with the chunk.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageFooter" } } } }, "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageSpan": { "id": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageSpan", "description": "Represents where the chunk starts and ends in the document.", "type": "object", "properties": { "pageStart": { "description": "Page where chunk starts in the document.", "type": "integer", "format": "int32" }, "pageEnd": { "description": "Page where chunk ends in the document.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageHeader": { "id": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageHeader", "description": "Represents the page header associated with the chunk.", "type": "object", "properties": { "text": { "description": "Header in text format.", "type": "string" }, "pageSpan": { "description": "Page span of the header.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageSpan" } } }, "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageFooter": { "id": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageFooter", "description": "Represents the page footer associated with the chunk.", "type": "object", "properties": { "text": { "description": "Footer in text format.", "type": "string" }, "pageSpan": { "description": "Page span of the footer.", "$ref": "GoogleCloudDocumentaiV1beta1DocumentChunkedDocumentChunkChunkPageSpan" } } }, "GoogleCloudDocumentaiV1beta1OperationMetadata": { "id": "GoogleCloudDocumentaiV1beta1OperationMetadata", "description": "Contains metadata for the BatchProcessDocuments operation.", "type": "object", "properties": { "state": { "description": "The state of the current batch processing.", "type": "string", "enumDescriptions": [ "The default value. This value is used if the state is omitted.", "Request is received.", "Request operation is waiting for scheduling.", "Request is being processed.", "The batch processing completed successfully.", "The batch processing was cancelled.", "The batch processing has failed." ], "enum": [ "STATE_UNSPECIFIED", "ACCEPTED", "WAITING", "RUNNING", "SUCCEEDED", "CANCELLED", "FAILED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" } } }, "GoogleCloudDocumentaiV1beta2BatchProcessDocumentsResponse": { "id": "GoogleCloudDocumentaiV1beta2BatchProcessDocumentsResponse", "description": "Response to an batch document processing request. This is returned in the LRO Operation after the operation is complete.", "type": "object", "properties": { "responses": { "description": "Responses for each individual document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2ProcessDocumentResponse" } } } }, "GoogleCloudDocumentaiV1beta2ProcessDocumentResponse": { "id": "GoogleCloudDocumentaiV1beta2ProcessDocumentResponse", "description": "Response to a single document processing request.", "type": "object", "properties": { "inputConfig": { "description": "Information about the input file. This is the same as the corresponding input config in the request.", "$ref": "GoogleCloudDocumentaiV1beta2InputConfig" }, "outputConfig": { "description": "The output location of the parsed responses. The responses are written to this location as JSON-serialized `Document` objects.", "$ref": "GoogleCloudDocumentaiV1beta2OutputConfig" } } }, "GoogleCloudDocumentaiV1beta2InputConfig": { "id": "GoogleCloudDocumentaiV1beta2InputConfig", "description": "The desired input location and metadata.", "type": "object", "properties": { "gcsSource": { "description": "The Google Cloud Storage location to read the input from. This must be a single file.", "$ref": "GoogleCloudDocumentaiV1beta2GcsSource" }, "contents": { "description": "Content in bytes, represented as a stream of bytes. Note: As with all `bytes` fields, proto buffer messages use a pure binary representation, whereas JSON representations use base64. This field only works for synchronous ProcessDocument method.", "type": "string", "format": "byte" }, "mimeType": { "description": "Required. Mimetype of the input. Current supported mimetypes are application/pdf, image/tiff, and image/gif. In addition, application/json type is supported for requests with ProcessDocumentRequest.automl_params field set. The JSON file needs to be in Document format.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2GcsSource": { "id": "GoogleCloudDocumentaiV1beta2GcsSource", "description": "The Google Cloud Storage location where the input file will be read from.", "type": "object", "properties": { "uri": { "type": "string" } } }, "GoogleCloudDocumentaiV1beta2OutputConfig": { "id": "GoogleCloudDocumentaiV1beta2OutputConfig", "description": "The desired output location and metadata.", "type": "object", "properties": { "gcsDestination": { "description": "The Google Cloud Storage location to write the output to.", "$ref": "GoogleCloudDocumentaiV1beta2GcsDestination" }, "pagesPerShard": { "description": "The max number of pages to include into each output Document shard JSON on Google Cloud Storage. The valid range is [1, 100]. If not specified, the default value is 20. For example, for one pdf file with 100 pages, 100 parsed pages will be produced. If `pages_per_shard` = 20, then 5 Document shard JSON files each containing 20 parsed pages will be written under the prefix OutputConfig.gcs_destination.uri and suffix pages-x-to-y.json where x and y are 1-indexed page numbers. Example GCS outputs with 157 pages and pages_per_shard = 50: pages-001-to-050.json pages-051-to-100.json pages-101-to-150.json pages-151-to-157.json", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2GcsDestination": { "id": "GoogleCloudDocumentaiV1beta2GcsDestination", "description": "The Google Cloud Storage location where the output file will be written to.", "type": "object", "properties": { "uri": { "type": "string" } } }, "GoogleCloudDocumentaiV1beta2Document": { "id": "GoogleCloudDocumentaiV1beta2Document", "description": "Document represents the canonical document resource in Document AI. It is an interchange format that provides insights into documents and allows for collaboration between users and Document AI to iterate and optimize for quality.", "type": "object", "properties": { "uri": { "description": "Optional. Currently supports Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. For more information, refer to [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris).", "type": "string" }, "content": { "description": "Optional. Inline document content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.", "type": "string", "format": "byte" }, "mimeType": { "description": "An IANA published [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml).", "type": "string" }, "text": { "description": "Optional. UTF-8 encoded text in reading order from the document.", "type": "string" }, "textStyles": { "description": "Styles for the Document.text.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentStyle" } }, "pages": { "description": "Visual page layout for the Document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPage" } }, "entities": { "description": "A list of entities detected on Document.text. For document shards, entities in this list may cross shard boundaries.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentEntity" } }, "entityRelations": { "description": "Placeholder. Relationship among Document.entities.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentEntityRelation" } }, "textChanges": { "description": "Placeholder. A list of text corrections made to Document.text. This is usually used for annotating corrections to OCR mistakes. Text changes for a given revision may not overlap with each other.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentTextChange" } }, "shardInfo": { "description": "Information about the sharding if this document is sharded part of a larger document. If the document is not sharded, this message is not specified.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentShardInfo" }, "labels": { "description": "Labels for this document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentLabel" } }, "error": { "description": "Any error that occurred while processing this document.", "$ref": "GoogleRpcStatus" }, "revisions": { "description": "Placeholder. Revision history of this document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentRevision" } }, "documentLayout": { "description": "Parsed layout of the document.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayout" }, "chunkedDocument": { "description": "Document chunked based on chunking config.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocument" } } }, "GoogleCloudDocumentaiV1beta2DocumentStyle": { "id": "GoogleCloudDocumentaiV1beta2DocumentStyle", "description": "Annotation for common text style attributes. This adheres to CSS conventions as much as possible.", "type": "object", "properties": { "textAnchor": { "description": "Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentTextAnchor" }, "color": { "description": "Text color.", "$ref": "GoogleTypeColor" }, "backgroundColor": { "description": "Text background color.", "$ref": "GoogleTypeColor" }, "fontWeight": { "description": "[Font weight](https://www.w3schools.com/cssref/pr_font_weight.asp). Possible values are `normal`, `bold`, `bolder`, and `lighter`.", "type": "string" }, "textStyle": { "description": "[Text style](https://www.w3schools.com/cssref/pr_font_font-style.asp). Possible values are `normal`, `italic`, and `oblique`.", "type": "string" }, "textDecoration": { "description": "[Text decoration](https://www.w3schools.com/cssref/pr_text_text-decoration.asp). Follows CSS standard. ", "type": "string" }, "fontSize": { "description": "Font size.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentStyleFontSize" }, "fontFamily": { "description": "Font family such as `Arial`, `Times New Roman`. https://www.w3schools.com/cssref/pr_font_font-family.asp", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentTextAnchor": { "id": "GoogleCloudDocumentaiV1beta2DocumentTextAnchor", "description": "Text reference indexing into the Document.text.", "type": "object", "properties": { "textSegments": { "description": "The text segments from the Document.text.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentTextAnchorTextSegment" } }, "content": { "description": "Contains the content of the text span so that users do not have to look it up in the text_segments. It is always populated for formFields.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentTextAnchorTextSegment": { "id": "GoogleCloudDocumentaiV1beta2DocumentTextAnchorTextSegment", "description": "A text segment in the Document.text. The indices may be out of bounds which indicate that the text extends into another document shard for large sharded documents. See ShardInfo.text_offset", "type": "object", "properties": { "startIndex": { "description": "TextSegment start UTF-8 char index in the Document.text.", "type": "string", "format": "int64" }, "endIndex": { "description": "TextSegment half open end UTF-8 char index in the Document.text.", "type": "string", "format": "int64" } } }, "GoogleCloudDocumentaiV1beta2DocumentStyleFontSize": { "id": "GoogleCloudDocumentaiV1beta2DocumentStyleFontSize", "description": "Font size with unit.", "type": "object", "properties": { "size": { "description": "Font size for the text.", "type": "number", "format": "float" }, "unit": { "description": "Unit for the font size. Follows CSS naming (such as `in`, `px`, and `pt`).", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentPage": { "id": "GoogleCloudDocumentaiV1beta2DocumentPage", "description": "A page in a Document.", "type": "object", "properties": { "pageNumber": { "description": "1-based index for current Page in a parent Document. Useful when a page is taken out of a Document for individual processing.", "type": "integer", "format": "int32" }, "image": { "description": "Rendered image for this page. This image is preprocessed to remove any skew, rotation, and distortions such that the annotation bounding boxes can be upright and axis-aligned.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageImage" }, "transforms": { "description": "Transformation matrices that were applied to the original document image to produce Page.image.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageMatrix" } }, "dimension": { "description": "Physical dimension of the page.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDimension" }, "layout": { "description": "Layout for the page.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "blocks": { "description": "A list of visually detected text blocks on the page. A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageBlock" } }, "paragraphs": { "description": "A list of visually detected text paragraphs on the page. A collection of lines that a human would perceive as a paragraph.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageParagraph" } }, "lines": { "description": "A list of visually detected text lines on the page. A collection of tokens that a human would perceive as a line.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLine" } }, "tokens": { "description": "A list of visually detected tokens on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageToken" } }, "visualElements": { "description": "A list of detected non-text visual elements e.g. checkbox, signature etc. on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageVisualElement" } }, "tables": { "description": "A list of visually detected tables on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageTable" } }, "formFields": { "description": "A list of visually detected form fields on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageFormField" } }, "symbols": { "description": "A list of visually detected symbols on the page.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageSymbol" } }, "detectedBarcodes": { "description": "A list of detected barcodes.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedBarcode" } }, "imageQualityScores": { "description": "Image quality scores.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageImageQualityScores" }, "provenance": { "description": "The history of this page.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageImage": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageImage", "description": "Rendered image contents for this page.", "type": "object", "properties": { "content": { "description": "Raw byte content of the image.", "type": "string", "format": "byte" }, "mimeType": { "description": "Encoding [media type (MIME type)](https://www.iana.org/assignments/media-types/media-types.xhtml) for the image.", "type": "string" }, "width": { "description": "Width of the image in pixels.", "type": "integer", "format": "int32" }, "height": { "description": "Height of the image in pixels.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageMatrix": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageMatrix", "description": "Representation for transformation matrix, intended to be compatible and used with OpenCV format for image manipulation.", "type": "object", "properties": { "rows": { "description": "Number of rows in the matrix.", "type": "integer", "format": "int32" }, "cols": { "description": "Number of columns in the matrix.", "type": "integer", "format": "int32" }, "type": { "description": "This encodes information about what data type the matrix uses. For example, 0 (CV_8U) is an unsigned 8-bit image. For the full list of OpenCV primitive data types, please refer to https://docs.opencv.org/4.3.0/d1/d1b/group__core__hal__interface.html", "type": "integer", "format": "int32" }, "data": { "description": "The matrix data.", "type": "string", "format": "byte" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageDimension": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageDimension", "description": "Dimension for the page.", "type": "object", "properties": { "width": { "description": "Page width.", "type": "number", "format": "float" }, "height": { "description": "Page height.", "type": "number", "format": "float" }, "unit": { "description": "Dimension unit.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageLayout": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageLayout", "description": "Visual element describing a layout unit on a page.", "type": "object", "properties": { "textAnchor": { "description": "Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentTextAnchor" }, "confidence": { "description": "Confidence of the current Layout within context of the object this layout is for. e.g. confidence can be for a single token, a table, a visual element, etc. depending on context. Range `[0, 1]`.", "type": "number", "format": "float" }, "boundingPoly": { "description": "The bounding polygon for the Layout.", "$ref": "GoogleCloudDocumentaiV1beta2BoundingPoly" }, "orientation": { "description": "Detected orientation for the Layout.", "type": "string", "enumDescriptions": [ "Unspecified orientation.", "Orientation is aligned with page up.", "Orientation is aligned with page right. Turn the head 90 degrees clockwise from upright to read.", "Orientation is aligned with page down. Turn the head 180 degrees from upright to read.", "Orientation is aligned with page left. Turn the head 90 degrees counterclockwise from upright to read." ], "enum": [ "ORIENTATION_UNSPECIFIED", "PAGE_UP", "PAGE_RIGHT", "PAGE_DOWN", "PAGE_LEFT" ] } } }, "GoogleCloudDocumentaiV1beta2BoundingPoly": { "id": "GoogleCloudDocumentaiV1beta2BoundingPoly", "description": "A bounding polygon for the detected image annotation.", "type": "object", "properties": { "vertices": { "description": "The bounding polygon vertices.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2Vertex" } }, "normalizedVertices": { "description": "The bounding polygon normalized vertices.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2NormalizedVertex" } } } }, "GoogleCloudDocumentaiV1beta2Vertex": { "id": "GoogleCloudDocumentaiV1beta2Vertex", "description": "A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "integer", "format": "int32" }, "y": { "description": "Y coordinate (starts from the top of the image).", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2NormalizedVertex": { "id": "GoogleCloudDocumentaiV1beta2NormalizedVertex", "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.", "type": "object", "properties": { "x": { "description": "X coordinate.", "type": "number", "format": "float" }, "y": { "description": "Y coordinate (starts from the top of the image).", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage", "description": "Detected language for a structural component.", "type": "object", "properties": { "languageCode": { "description": "The [BCP-47 language code](https://www.unicode.org/reports/tr35/#Unicode_locale_identifier), such as `en-US` or `sr-Latn`.", "type": "string" }, "confidence": { "description": "Confidence of detected language. Range `[0, 1]`.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageBlock": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageBlock", "description": "A block has a set of lines (collected into paragraphs) that have a common line-spacing and orientation.", "type": "object", "properties": { "layout": { "description": "Layout for Block.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta2DocumentProvenance": { "id": "GoogleCloudDocumentaiV1beta2DocumentProvenance", "description": "Structure to identify provenance relationships between annotations in different revisions.", "type": "object", "properties": { "revision": { "description": "The index of the revision that produced this element.", "deprecated": true, "type": "integer", "format": "int32" }, "id": { "description": "The Id of this operation. Needs to be unique within the scope of the revision.", "deprecated": true, "type": "integer", "format": "int32" }, "parents": { "description": "References to the original elements that are replaced.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenanceParent" } }, "type": { "description": "The type of provenance operation.", "type": "string", "enumDescriptions": [ "Operation type unspecified. If no operation is specified a provenance entry is simply used to match against a `parent`.", "Add an element.", "Remove an element identified by `parent`.", "Updates any fields within the given provenance scope of the message. It overwrites the fields rather than replacing them. Use this when you want to update a field value of an entity without also updating all the child properties.", "Currently unused. Replace an element identified by `parent`.", "Deprecated. Request human review for the element identified by `parent`.", "Deprecated. Element is reviewed and approved at human review, confidence will be set to 1.0.", "Deprecated. Element is skipped in the validation process." ], "enumDeprecated": [ false, false, false, false, false, true, true, true ], "enum": [ "OPERATION_TYPE_UNSPECIFIED", "ADD", "REMOVE", "UPDATE", "REPLACE", "EVAL_REQUESTED", "EVAL_APPROVED", "EVAL_SKIPPED" ] } } }, "GoogleCloudDocumentaiV1beta2DocumentProvenanceParent": { "id": "GoogleCloudDocumentaiV1beta2DocumentProvenanceParent", "description": "The parent element the current element is based on. Used for referencing/aligning, removal and replacement operations.", "type": "object", "properties": { "revision": { "description": "The index of the index into current revision's parent_ids list.", "type": "integer", "format": "int32" }, "index": { "description": "The index of the parent item in the corresponding item list (eg. list of entities, properties within entities, etc.) in the parent revision.", "type": "integer", "format": "int32" }, "id": { "description": "The id of the parent provenance.", "deprecated": true, "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageParagraph": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageParagraph", "description": "A collection of lines that a human would perceive as a paragraph.", "type": "object", "properties": { "layout": { "description": "Layout for Paragraph.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageLine": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageLine", "description": "A collection of tokens that a human would perceive as a line. Does not cross column boundaries, can be horizontal, vertical, etc.", "type": "object", "properties": { "layout": { "description": "Layout for Line.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageToken": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageToken", "description": "A detected token.", "type": "object", "properties": { "layout": { "description": "Layout for Token.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "detectedBreak": { "description": "Detected break at the end of a Token.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageTokenDetectedBreak" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" }, "styleInfo": { "description": "Text style attributes.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageTokenStyleInfo" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageTokenDetectedBreak": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageTokenDetectedBreak", "description": "Detected break at the end of a Token.", "type": "object", "properties": { "type": { "description": "Detected break type.", "type": "string", "enumDescriptions": [ "Unspecified break type.", "A single whitespace.", "A wider whitespace.", "A hyphen that indicates that a token has been split across lines." ], "enum": [ "TYPE_UNSPECIFIED", "SPACE", "WIDE_SPACE", "HYPHEN" ] } } }, "GoogleCloudDocumentaiV1beta2DocumentPageTokenStyleInfo": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageTokenStyleInfo", "description": "Font and other text style attributes.", "type": "object", "properties": { "fontSize": { "description": "Font size in points (`1` point is `¹⁄₇₂` inches).", "type": "integer", "format": "int32" }, "pixelFontSize": { "description": "Font size in pixels, equal to _unrounded font_size_ * _resolution_ ÷ `72.0`.", "type": "number", "format": "double" }, "letterSpacing": { "description": "Letter spacing in points.", "type": "number", "format": "double" }, "fontType": { "description": "Name or style of the font.", "type": "string" }, "bold": { "description": "Whether the text is bold (equivalent to font_weight is at least `700`).", "type": "boolean" }, "italic": { "description": "Whether the text is italic.", "type": "boolean" }, "underlined": { "description": "Whether the text is underlined.", "type": "boolean" }, "strikeout": { "description": "Whether the text is strikethrough. This feature is not supported yet.", "type": "boolean" }, "subscript": { "description": "Whether the text is a subscript. This feature is not supported yet.", "type": "boolean" }, "superscript": { "description": "Whether the text is a superscript. This feature is not supported yet.", "type": "boolean" }, "smallcaps": { "description": "Whether the text is in small caps. This feature is not supported yet.", "type": "boolean" }, "fontWeight": { "description": "TrueType weight on a scale `100` (thin) to `1000` (ultra-heavy). Normal is `400`, bold is `700`.", "type": "integer", "format": "int32" }, "handwritten": { "description": "Whether the text is handwritten.", "type": "boolean" }, "textColor": { "description": "Color of the text.", "$ref": "GoogleTypeColor" }, "backgroundColor": { "description": "Color of the background.", "$ref": "GoogleTypeColor" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageVisualElement": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageVisualElement", "description": "Detected non-text visual elements e.g. checkbox, signature etc. on the page.", "type": "object", "properties": { "layout": { "description": "Layout for VisualElement.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "type": { "description": "Type of the VisualElement.", "type": "string" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta2DocumentPageTable": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageTable", "description": "A table representation similar to HTML table structure.", "type": "object", "properties": { "layout": { "description": "Layout for Table.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "headerRows": { "description": "Header rows of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageTableTableRow" } }, "bodyRows": { "description": "Body rows of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageTableTableRow" } }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "provenance": { "description": "The history of this table.", "deprecated": true, "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageTableTableRow": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageTableTableRow", "description": "A row of table cells.", "type": "object", "properties": { "cells": { "description": "Cells that make up this row.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageTableTableCell" } } } }, "GoogleCloudDocumentaiV1beta2DocumentPageTableTableCell": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageTableTableCell", "description": "A cell representation inside the table.", "type": "object", "properties": { "layout": { "description": "Layout for TableCell.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "rowSpan": { "description": "How many rows this cell spans.", "type": "integer", "format": "int32" }, "colSpan": { "description": "How many columns this cell spans.", "type": "integer", "format": "int32" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta2DocumentPageFormField": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageFormField", "description": "A form field detected on the page.", "type": "object", "properties": { "fieldName": { "description": "Layout for the FormField name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "fieldValue": { "description": "Layout for the FormField value.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "nameDetectedLanguages": { "description": "A list of detected languages for name together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "valueDetectedLanguages": { "description": "A list of detected languages for value together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } }, "valueType": { "description": "If the value is non-textual, this field represents the type. Current valid values are: - blank (this indicates the `field_value` is normal text) - `unfilled_checkbox` - `filled_checkbox`", "type": "string" }, "correctedKeyText": { "description": "Created for Labeling UI to export key text. If corrections were made to the text identified by the `field_name.text_anchor`, this field will contain the correction.", "type": "string" }, "correctedValueText": { "description": "Created for Labeling UI to export value text. If corrections were made to the text identified by the `field_value.text_anchor`, this field will contain the correction.", "type": "string" }, "provenance": { "description": "The history of this annotation.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageSymbol": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageSymbol", "description": "A detected symbol.", "type": "object", "properties": { "layout": { "description": "Layout for Symbol.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "detectedLanguages": { "description": "A list of detected languages together with confidence.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedLanguage" } } } }, "GoogleCloudDocumentaiV1beta2DocumentPageDetectedBarcode": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageDetectedBarcode", "description": "A detected barcode.", "type": "object", "properties": { "layout": { "description": "Layout for DetectedBarcode.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageLayout" }, "barcode": { "description": "Detailed barcode information of the DetectedBarcode.", "$ref": "GoogleCloudDocumentaiV1beta2Barcode" } } }, "GoogleCloudDocumentaiV1beta2Barcode": { "id": "GoogleCloudDocumentaiV1beta2Barcode", "description": "Encodes the detailed information of a barcode.", "type": "object", "properties": { "format": { "description": "Format of a barcode. The supported formats are: - `CODE_128`: Code 128 type. - `CODE_39`: Code 39 type. - `CODE_93`: Code 93 type. - `CODABAR`: Codabar type. - `DATA_MATRIX`: 2D Data Matrix type. - `ITF`: ITF type. - `EAN_13`: EAN-13 type. - `EAN_8`: EAN-8 type. - `QR_CODE`: 2D QR code type. - `UPC_A`: UPC-A type. - `UPC_E`: UPC-E type. - `PDF417`: PDF417 type. - `AZTEC`: 2D Aztec code type. - `DATABAR`: GS1 DataBar code type.", "type": "string" }, "valueFormat": { "description": "Value format describes the format of the value that a barcode encodes. The supported formats are: - `CONTACT_INFO`: Contact information. - `EMAIL`: Email address. - `ISBN`: ISBN identifier. - `PHONE`: Phone number. - `PRODUCT`: Product. - `SMS`: SMS message. - `TEXT`: Text string. - `URL`: URL address. - `WIFI`: Wifi information. - `GEO`: Geo-localization. - `CALENDAR_EVENT`: Calendar event. - `DRIVER_LICENSE`: Driver's license.", "type": "string" }, "rawValue": { "description": "Raw value encoded in the barcode. For example: `'MEBKM:TITLE:Google;URL:https://www.google.com;;'`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageImageQualityScores": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageImageQualityScores", "description": "Image quality scores for the page image.", "type": "object", "properties": { "qualityScore": { "description": "The overall quality score. Range `[0, 1]` where `1` is perfect quality.", "type": "number", "format": "float" }, "detectedDefects": { "description": "A list of detected defects.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageImageQualityScoresDetectedDefect" } } } }, "GoogleCloudDocumentaiV1beta2DocumentPageImageQualityScoresDetectedDefect": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageImageQualityScoresDetectedDefect", "description": "Image Quality Defects", "type": "object", "properties": { "type": { "description": "Name of the defect type. Supported values are: - `quality/defect_blurry` - `quality/defect_noisy` - `quality/defect_dark` - `quality/defect_faint` - `quality/defect_text_too_small` - `quality/defect_document_cutoff` - `quality/defect_text_cutoff` - `quality/defect_glare`", "type": "string" }, "confidence": { "description": "Confidence of detected defect. Range `[0, 1]` where `1` indicates strong confidence that the defect exists.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta2DocumentEntity": { "id": "GoogleCloudDocumentaiV1beta2DocumentEntity", "description": "An entity that could be a phrase in the text or a property that belongs to the document. It is a known entity type, such as a person, an organization, or location.", "type": "object", "properties": { "textAnchor": { "description": "Optional. Provenance of the entity. Text anchor indexing into the Document.text.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentTextAnchor" }, "type": { "description": "Required. Entity type from a schema e.g. `Address`.", "type": "string" }, "mentionText": { "description": "Optional. Text value of the entity e.g. `1600 Amphitheatre Pkwy`.", "type": "string" }, "mentionId": { "description": "Optional. Deprecated. Use `id` field instead.", "type": "string" }, "confidence": { "description": "Optional. Confidence of detected Schema entity. Range `[0, 1]`.", "type": "number", "format": "float" }, "pageAnchor": { "description": "Optional. Represents the provenance of this entity wrt. the location on the page where it was found.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageAnchor" }, "id": { "description": "Optional. Canonical id. This will be a unique value in the entity list for this document.", "type": "string" }, "normalizedValue": { "description": "Optional. Normalized entity value. Absent if the extracted value could not be converted or the type (e.g. address) is not supported for certain parsers. This field is also only populated for certain supported document types.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentEntityNormalizedValue" }, "properties": { "description": "Optional. Entities can be nested to form a hierarchical data structure representing the content in the document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentEntity" } }, "provenance": { "description": "Optional. The history of this annotation.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" }, "redacted": { "description": "Optional. Whether the entity will be redacted for de-identification purposes.", "type": "boolean" } } }, "GoogleCloudDocumentaiV1beta2DocumentPageAnchor": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageAnchor", "description": "Referencing the visual context of the entity in the Document.pages. Page anchors can be cross-page, consist of multiple bounding polygons and optionally reference specific layout element types.", "type": "object", "properties": { "pageRefs": { "description": "One or more references to visual page elements", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentPageAnchorPageRef" } } } }, "GoogleCloudDocumentaiV1beta2DocumentPageAnchorPageRef": { "id": "GoogleCloudDocumentaiV1beta2DocumentPageAnchorPageRef", "description": "Represents a weak reference to a page element within a document.", "type": "object", "properties": { "page": { "description": "Required. Index into the Document.pages element, for example using `Document.pages` to locate the related page element. This field is skipped when its value is the default `0`. See https://developers.google.com/protocol-buffers/docs/proto3#json.", "type": "string", "format": "int64" }, "layoutType": { "description": "Optional. The type of the layout element that is being referenced if any.", "type": "string", "enumDescriptions": [ "Layout Unspecified.", "References a Page.blocks element.", "References a Page.paragraphs element.", "References a Page.lines element.", "References a Page.tokens element.", "References a Page.visual_elements element.", "Refrrences a Page.tables element.", "References a Page.form_fields element." ], "enum": [ "LAYOUT_TYPE_UNSPECIFIED", "BLOCK", "PARAGRAPH", "LINE", "TOKEN", "VISUAL_ELEMENT", "TABLE", "FORM_FIELD" ] }, "layoutId": { "description": "Optional. Deprecated. Use PageRef.bounding_poly instead.", "deprecated": true, "type": "string" }, "boundingPoly": { "description": "Optional. Identifies the bounding polygon of a layout element on the page. If `layout_type` is set, the bounding polygon must be exactly the same to the layout element it's referring to.", "$ref": "GoogleCloudDocumentaiV1beta2BoundingPoly" }, "confidence": { "description": "Optional. Confidence of detected page element, if applicable. Range `[0, 1]`.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta2DocumentEntityNormalizedValue": { "id": "GoogleCloudDocumentaiV1beta2DocumentEntityNormalizedValue", "description": "Parsed and normalized entity value.", "type": "object", "properties": { "moneyValue": { "description": "Money value. See also: https://github.com/googleapis/googleapis/blob/master/google/type/money.proto", "$ref": "GoogleTypeMoney" }, "dateValue": { "description": "Date value. Includes year, month, day. See also: https://github.com/googleapis/googleapis/blob/master/google/type/date.proto", "$ref": "GoogleTypeDate" }, "datetimeValue": { "description": "DateTime value. Includes date, time, and timezone. See also: https://github.com/googleapis/googleapis/blob/master/google/type/datetime.proto", "$ref": "GoogleTypeDateTime" }, "addressValue": { "description": "Postal address. See also: https://github.com/googleapis/googleapis/blob/master/google/type/postal_address.proto", "$ref": "GoogleTypePostalAddress" }, "booleanValue": { "description": "Boolean value. Can be used for entities with binary values, or for checkboxes.", "type": "boolean" }, "integerValue": { "description": "Integer value.", "type": "integer", "format": "int32" }, "floatValue": { "description": "Float value.", "type": "number", "format": "float" }, "text": { "description": "Optional. An optional field to store a normalized string. For some entity types, one of respective `structured_value` fields may also be populated. Also not all the types of `structured_value` will be normalized. For example, some processors may not generate `float` or `integer` normalized text by default. Below are sample formats mapped to structured values. - Money/Currency type (`money_value`) is in the ISO 4217 text format. - Date type (`date_value`) is in the ISO 8601 text format. - Datetime type (`datetime_value`) is in the ISO 8601 text format.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentEntityRelation": { "id": "GoogleCloudDocumentaiV1beta2DocumentEntityRelation", "description": "Relationship between Entities.", "type": "object", "properties": { "subjectId": { "description": "Subject entity id.", "type": "string" }, "objectId": { "description": "Object entity id.", "type": "string" }, "relation": { "description": "Relationship description.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentTextChange": { "id": "GoogleCloudDocumentaiV1beta2DocumentTextChange", "description": "This message is used for text changes aka. OCR corrections.", "type": "object", "properties": { "textAnchor": { "description": "Provenance of the correction. Text anchor indexing into the Document.text. There can only be a single `TextAnchor.text_segments` element. If the start and end index of the text segment are the same, the text change is inserted before that index.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentTextAnchor" }, "changedText": { "description": "The text that replaces the text identified in the `text_anchor`.", "type": "string" }, "provenance": { "description": "The history of this annotation.", "deprecated": true, "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentProvenance" } } } }, "GoogleCloudDocumentaiV1beta2DocumentShardInfo": { "id": "GoogleCloudDocumentaiV1beta2DocumentShardInfo", "description": "For a large document, sharding may be performed to produce several document shards. Each document shard contains this field to detail which shard it is.", "type": "object", "properties": { "shardIndex": { "description": "The 0-based index of this shard.", "type": "string", "format": "int64" }, "shardCount": { "description": "Total number of shards.", "type": "string", "format": "int64" }, "textOffset": { "description": "The index of the first character in Document.text in the overall document global text.", "type": "string", "format": "int64" } } }, "GoogleCloudDocumentaiV1beta2DocumentLabel": { "id": "GoogleCloudDocumentaiV1beta2DocumentLabel", "description": "Label attaches schema information and/or other metadata to segments within a Document. Multiple Labels on a single field can denote either different labels, different instances of the same label created at different times, or some combination of both.", "type": "object", "properties": { "automlModel": { "description": "Label is generated AutoML model. This field stores the full resource name of the AutoML model. Format: `projects/{project-id}/locations/{location-id}/models/{model-id}`", "type": "string" }, "name": { "description": "Name of the label. When the label is generated from AutoML Text Classification model, this field represents the name of the category.", "type": "string" }, "confidence": { "description": "Confidence score between 0 and 1 for label assignment.", "type": "number", "format": "float" } } }, "GoogleCloudDocumentaiV1beta2DocumentRevision": { "id": "GoogleCloudDocumentaiV1beta2DocumentRevision", "description": "Contains past or forward revisions of this document.", "type": "object", "properties": { "agent": { "description": "If the change was made by a person specify the name or id of that person.", "type": "string" }, "processor": { "description": "If the annotation was made by processor identify the processor by its resource name.", "type": "string" }, "id": { "description": "Id of the revision, internally generated by doc proto storage. Unique within the context of the document.", "type": "string" }, "parent": { "description": "The revisions that this revision is based on. This can include one or more parent (when documents are merged.) This field represents the index into the `revisions` field.", "deprecated": true, "type": "array", "items": { "type": "integer", "format": "int32" } }, "parentIds": { "description": "The revisions that this revision is based on. Must include all the ids that have anything to do with this revision - eg. there are `provenance.parent.revision` fields that index into this field.", "type": "array", "items": { "type": "string" } }, "createTime": { "description": "The time that the revision was created, internally generated by doc proto storage at the time of create.", "type": "string", "format": "google-datetime" }, "humanReview": { "description": "Human Review information of this revision.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentRevisionHumanReview" } } }, "GoogleCloudDocumentaiV1beta2DocumentRevisionHumanReview": { "id": "GoogleCloudDocumentaiV1beta2DocumentRevisionHumanReview", "description": "Human Review information of the document.", "type": "object", "properties": { "state": { "description": "Human review state. e.g. `requested`, `succeeded`, `rejected`.", "type": "string" }, "stateMessage": { "description": "A message providing more details about the current state of processing. For example, the rejection reason when the state is `rejected`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayout": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayout", "description": "Represents the parsed layout of a document as a collection of blocks that the document is divided into.", "type": "object", "properties": { "blocks": { "description": "List of blocks in the document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlock": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlock", "description": "Represents a block. A block could be one of the various types (text, table, list) supported.", "type": "object", "properties": { "textBlock": { "description": "Block consisting of text content.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock" }, "tableBlock": { "description": "Block consisting of table content/structure.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock" }, "listBlock": { "description": "Block consisting of list content/structure.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock" }, "blockId": { "description": "ID of the block.", "type": "string" }, "pageSpan": { "description": "Page span of the block.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan" } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTextBlock", "description": "Represents a text type block.", "type": "object", "properties": { "text": { "description": "Text content stored in the block.", "type": "string" }, "type": { "description": "Type of the text in the block. Available options are: `paragraph`, `subtitle`, `heading-1`, `heading-2`, `heading-3`, `heading-4`, `heading-5`, `header`, `footer`.", "type": "string" }, "blocks": { "description": "A text block could further have child blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableBlock", "description": "Represents a table type block.", "type": "object", "properties": { "headerRows": { "description": "Header rows at the top of the table.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow" } }, "bodyRows": { "description": "Body rows containing main table content.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow" } }, "caption": { "description": "Table caption/title.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableRow", "description": "Represents a row in a table.", "type": "object", "properties": { "cells": { "description": "A table row is a list of table cells.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell" } } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutTableCell", "description": "Represents a cell in a table row.", "type": "object", "properties": { "blocks": { "description": "A table cell is a list of blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlock" } }, "rowSpan": { "description": "How many rows this cell spans.", "type": "integer", "format": "int32" }, "colSpan": { "description": "How many columns this cell spans.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutListBlock", "description": "Represents a list type block.", "type": "object", "properties": { "listEntries": { "description": "List entries that constitute a list block.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry" } }, "type": { "description": "Type of the list_entries (if exist). Available options are `ordered` and `unordered`.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutListEntry", "description": "Represents an entry in the list.", "type": "object", "properties": { "blocks": { "description": "A list entry is a list of blocks. Repeated blocks support further hierarchies and nested blocks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlock" } } } }, "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan": { "id": "GoogleCloudDocumentaiV1beta2DocumentDocumentLayoutDocumentLayoutBlockLayoutPageSpan", "description": "Represents where the block starts and ends in the document.", "type": "object", "properties": { "pageStart": { "description": "Page where block starts in the document.", "type": "integer", "format": "int32" }, "pageEnd": { "description": "Page where block ends in the document.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2DocumentChunkedDocument": { "id": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocument", "description": "Represents the chunks that the document is divided into.", "type": "object", "properties": { "chunks": { "description": "List of chunks.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunk" } } } }, "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunk": { "id": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunk", "description": "Represents a chunk.", "type": "object", "properties": { "chunkId": { "description": "ID of the chunk.", "type": "string" }, "sourceBlockIds": { "description": "Unused.", "type": "array", "items": { "type": "string" } }, "content": { "description": "Text content of the chunk.", "type": "string" }, "pageSpan": { "description": "Page span of the chunk.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageSpan" }, "pageHeaders": { "description": "Page headers associated with the chunk.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageHeader" } }, "pageFooters": { "description": "Page footers associated with the chunk.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageFooter" } } } }, "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageSpan": { "id": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageSpan", "description": "Represents where the chunk starts and ends in the document.", "type": "object", "properties": { "pageStart": { "description": "Page where chunk starts in the document.", "type": "integer", "format": "int32" }, "pageEnd": { "description": "Page where chunk ends in the document.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageHeader": { "id": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageHeader", "description": "Represents the page header associated with the chunk.", "type": "object", "properties": { "text": { "description": "Header in text format.", "type": "string" }, "pageSpan": { "description": "Page span of the header.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageSpan" } } }, "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageFooter": { "id": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageFooter", "description": "Represents the page footer associated with the chunk.", "type": "object", "properties": { "text": { "description": "Footer in text format.", "type": "string" }, "pageSpan": { "description": "Page span of the footer.", "$ref": "GoogleCloudDocumentaiV1beta2DocumentChunkedDocumentChunkChunkPageSpan" } } }, "GoogleCloudDocumentaiV1beta2OperationMetadata": { "id": "GoogleCloudDocumentaiV1beta2OperationMetadata", "description": "Contains metadata for the BatchProcessDocuments operation.", "type": "object", "properties": { "state": { "description": "The state of the current batch processing.", "type": "string", "enumDescriptions": [ "The default value. This value is used if the state is omitted.", "Request is received.", "Request operation is waiting for scheduling.", "Request is being processed.", "The batch processing completed successfully.", "The batch processing was cancelled.", "The batch processing has failed." ], "enum": [ "STATE_UNSPECIFIED", "ACCEPTED", "WAITING", "RUNNING", "SUCCEEDED", "CANCELLED", "FAILED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" } } }, "GoogleCloudDocumentaiV1beta3BatchProcessResponse": { "id": "GoogleCloudDocumentaiV1beta3BatchProcessResponse", "description": "Response message for BatchProcessDocuments.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3BatchProcessMetadata": { "id": "GoogleCloudDocumentaiV1beta3BatchProcessMetadata", "description": "The long-running operation metadata for BatchProcessDocuments.", "type": "object", "properties": { "state": { "description": "The state of the current batch processing.", "type": "string", "enumDescriptions": [ "The default value. This value is used if the state is omitted.", "Request operation is waiting for scheduling.", "Request is being processed.", "The batch processing completed successfully.", "The batch processing was being cancelled.", "The batch processing was cancelled.", "The batch processing has failed." ], "enum": [ "STATE_UNSPECIFIED", "WAITING", "RUNNING", "SUCCEEDED", "CANCELLING", "CANCELLED", "FAILED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing. For example, the error message if the operation is failed.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" }, "individualProcessStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3BatchProcessMetadataIndividualProcessStatus" } } } }, "GoogleCloudDocumentaiV1beta3BatchProcessMetadataIndividualProcessStatus": { "id": "GoogleCloudDocumentaiV1beta3BatchProcessMetadataIndividualProcessStatus", "description": "The status of a each individual document in the batch process.", "type": "object", "properties": { "inputGcsSource": { "description": "The source of the document, same as the input_gcs_source field in the request when the batch process started.", "type": "string" }, "status": { "description": "The status processing the document.", "$ref": "GoogleRpcStatus" }, "outputGcsDestination": { "description": "The Cloud Storage output destination (in the request as DocumentOutputConfig.GcsOutputConfig.gcs_uri) of the processed document if it was successful, otherwise empty.", "type": "string" }, "humanReviewOperation": { "description": "The name of the operation triggered by the processed document. If the human review process isn't triggered, this field will be empty. It has the same response type and metadata as the long-running operation returned by the ReviewDocument method.", "deprecated": true, "type": "string" }, "humanReviewStatus": { "description": "The status of human review on the processed document.", "$ref": "GoogleCloudDocumentaiV1beta3HumanReviewStatus" } } }, "GoogleCloudDocumentaiV1beta3DeleteProcessorMetadata": { "id": "GoogleCloudDocumentaiV1beta3DeleteProcessorMetadata", "description": "The long-running operation metadata for the DeleteProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3CommonOperationMetadata": { "id": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata", "description": "The common metadata for long running operations.", "type": "object", "properties": { "state": { "description": "The state of the operation.", "type": "string", "enumDescriptions": [ "Unspecified state.", "Operation is still running.", "Operation is being cancelled.", "Operation succeeded.", "Operation failed.", "Operation is cancelled." ], "enum": [ "STATE_UNSPECIFIED", "RUNNING", "CANCELLING", "SUCCEEDED", "FAILED", "CANCELLED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing.", "type": "string" }, "resource": { "description": "A related resource to this operation.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" } } }, "GoogleCloudDocumentaiV1beta3EnableProcessorResponse": { "id": "GoogleCloudDocumentaiV1beta3EnableProcessorResponse", "description": "Response message for the EnableProcessor method. Intentionally empty proto for adding fields in future.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3EnableProcessorMetadata": { "id": "GoogleCloudDocumentaiV1beta3EnableProcessorMetadata", "description": "The long-running operation metadata for the EnableProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3DisableProcessorResponse": { "id": "GoogleCloudDocumentaiV1beta3DisableProcessorResponse", "description": "Response message for the DisableProcessor method. Intentionally empty proto for adding fields in future.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3DisableProcessorMetadata": { "id": "GoogleCloudDocumentaiV1beta3DisableProcessorMetadata", "description": "The long-running operation metadata for the DisableProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3ReviewDocumentResponse": { "id": "GoogleCloudDocumentaiV1beta3ReviewDocumentResponse", "description": "Response message for the ReviewDocument method.", "type": "object", "properties": { "gcsDestination": { "description": "The Cloud Storage uri for the human reviewed document if the review is succeeded.", "type": "string" }, "state": { "description": "The state of the review operation.", "type": "string", "enumDescriptions": [ "The default value. This value is used if the state is omitted.", "The review operation is rejected by the reviewer.", "The review operation is succeeded." ], "enum": [ "STATE_UNSPECIFIED", "REJECTED", "SUCCEEDED" ] }, "rejectionReason": { "description": "The reason why the review is rejected by reviewer.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ReviewDocumentOperationMetadata": { "id": "GoogleCloudDocumentaiV1beta3ReviewDocumentOperationMetadata", "description": "The long-running operation metadata for the ReviewDocument method.", "type": "object", "properties": { "state": { "description": "Used only when Operation.done is false.", "type": "string", "enumDescriptions": [ "Unspecified state.", "Operation is still running.", "Operation is being cancelled.", "Operation succeeded.", "Operation failed.", "Operation is cancelled." ], "enum": [ "STATE_UNSPECIFIED", "RUNNING", "CANCELLING", "SUCCEEDED", "FAILED", "CANCELLED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing. For example, the error message if the operation is failed.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" }, "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" }, "questionId": { "description": "The Crowd Compute question ID.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3DeleteProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3DeleteProcessorVersionMetadata", "description": "The long-running operation metadata for the DeleteProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3DeployProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3DeployProcessorVersionMetadata", "description": "The long-running operation metadata for the DeployProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3DeployProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1beta3DeployProcessorVersionResponse", "description": "Response message for the DeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionMetadata", "description": "The long-running operation metadata for the UndeployProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1beta3UndeployProcessorVersionResponse", "description": "Response message for the UndeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionMetadata", "description": "The long-running operation metadata for the SetDefaultProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1beta3SetDefaultProcessorVersionResponse", "description": "Response message for the SetDefaultProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionMetadata", "description": "The metadata that represents a processor version being created.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" }, "trainingDatasetValidation": { "description": "The training dataset validation information.", "$ref": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionMetadataDatasetValidation" }, "testDatasetValidation": { "description": "The test dataset validation information.", "$ref": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionMetadataDatasetValidation" } } }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionMetadataDatasetValidation": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionMetadataDatasetValidation", "description": "The dataset validation information. This includes any and all errors with documents and the dataset.", "type": "object", "properties": { "documentErrorCount": { "description": "The total number of document errors.", "type": "integer", "format": "int32" }, "datasetErrorCount": { "description": "The total number of dataset errors.", "type": "integer", "format": "int32" }, "documentErrors": { "description": "Error information pertaining to specific documents. A maximum of 10 document errors will be returned. Any document with errors will not be used throughout training.", "type": "array", "items": { "$ref": "GoogleRpcStatus" } }, "datasetErrors": { "description": "Error information for the dataset as a whole. A maximum of 10 dataset errors will be returned. A single dataset error is terminal for training.", "type": "array", "items": { "$ref": "GoogleRpcStatus" } } } }, "GoogleCloudDocumentaiV1beta3TrainProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1beta3TrainProcessorVersionResponse", "description": "The response for TrainProcessorVersion.", "type": "object", "properties": { "processorVersion": { "description": "The resource name of the processor version produced by training.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionMetadata", "description": "Metadata of the EvaluateProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1beta3EvaluateProcessorVersionResponse", "description": "Response of the EvaluateProcessorVersion method.", "type": "object", "properties": { "evaluation": { "description": "The resource name of the created evaluation.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3ImportProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiV1beta3ImportProcessorVersionMetadata", "description": "The long-running operation metadata for the ImportProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata for the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3ImportProcessorVersionResponse": { "id": "GoogleCloudDocumentaiV1beta3ImportProcessorVersionResponse", "description": "The response message for the ImportProcessorVersion method.", "type": "object", "properties": { "processorVersion": { "description": "The destination processor version name.", "type": "string" } } }, "GoogleCloudDocumentaiV1beta3UpdateDatasetOperationMetadata": { "id": "GoogleCloudDocumentaiV1beta3UpdateDatasetOperationMetadata", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadata": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadata", "description": "Metadata of the import document operation.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" }, "individualImportStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadataIndividualImportStatus" } }, "importConfigValidationResults": { "description": "Validation statuses of the batch documents import config.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadataImportConfigValidationResult" } }, "totalDocumentCount": { "description": "Total number of the documents that are qualified for importing.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadataIndividualImportStatus": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadataIndividualImportStatus", "description": "The status of each individual document in the import process.", "type": "object", "properties": { "inputGcsSource": { "description": "The source Cloud Storage URI of the document.", "type": "string" }, "status": { "description": "The status of the importing of the document.", "$ref": "GoogleRpcStatus" }, "outputDocumentId": { "description": "The document id of imported document if it was successful, otherwise empty.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentId" } } }, "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadataImportConfigValidationResult": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsMetadataImportConfigValidationResult", "description": "The validation status of each import config. Status is set to an error if there are no documents to import in the `import_config`, or `OK` if the operation will try to proceed with at least one document.", "type": "object", "properties": { "inputGcsSource": { "description": "The source Cloud Storage URI specified in the import config.", "type": "string" }, "status": { "description": "The validation status of import config.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiV1beta3ImportDocumentsResponse": { "id": "GoogleCloudDocumentaiV1beta3ImportDocumentsResponse", "description": "Response of the import document operation.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsMetadata": { "id": "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsMetadata", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiV1beta3CommonOperationMetadata" }, "individualBatchDeleteStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsMetadataIndividualBatchDeleteStatus" } }, "totalDocumentCount": { "description": "Total number of documents deleting from dataset.", "type": "integer", "format": "int32" }, "errorDocumentCount": { "description": "Total number of documents that failed to be deleted in storage.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsMetadataIndividualBatchDeleteStatus": { "id": "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsMetadataIndividualBatchDeleteStatus", "description": "The status of each individual document in the batch delete process.", "type": "object", "properties": { "documentId": { "description": "The document id of the document.", "$ref": "GoogleCloudDocumentaiV1beta3DocumentId" }, "status": { "description": "The status of deleting the document in storage.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsResponse": { "id": "GoogleCloudDocumentaiV1beta3BatchDeleteDocumentsResponse", "description": "Response of the delete documents operation.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3DeleteProcessorMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3DeleteProcessorMetadata", "description": "The long-running operation metadata for the DeleteProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata", "description": "The common metadata for long running operations.", "type": "object", "properties": { "state": { "description": "The state of the operation.", "type": "string", "enumDescriptions": [ "Unspecified state.", "Operation is still running.", "Operation is being cancelled.", "Operation succeeded.", "Operation failed.", "Operation is cancelled." ], "enum": [ "STATE_UNSPECIFIED", "RUNNING", "CANCELLING", "SUCCEEDED", "FAILED", "CANCELLED" ] }, "stateMessage": { "description": "A message providing more details about the current state of processing.", "type": "string" }, "resource": { "description": "A related resource to this operation.", "type": "string" }, "createTime": { "description": "The creation time of the operation.", "type": "string", "format": "google-datetime" }, "updateTime": { "description": "The last update time of the operation.", "type": "string", "format": "google-datetime" } } }, "GoogleCloudDocumentaiUiv1beta3EnableProcessorResponse": { "id": "GoogleCloudDocumentaiUiv1beta3EnableProcessorResponse", "description": "Response message for the EnableProcessor method. Intentionally empty proto for adding fields in future.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3EnableProcessorMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3EnableProcessorMetadata", "description": "The long-running operation metadata for the EnableProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3DisableProcessorResponse": { "id": "GoogleCloudDocumentaiUiv1beta3DisableProcessorResponse", "description": "Response message for the DisableProcessor method. Intentionally empty proto for adding fields in future.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3DisableProcessorMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3DisableProcessorMetadata", "description": "The long-running operation metadata for the DisableProcessor method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionMetadata", "description": "The metadata that represents a processor version being created.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "trainingDatasetValidation": { "description": "The training dataset validation information.", "$ref": "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionMetadataDatasetValidation" }, "testDatasetValidation": { "description": "The test dataset validation information.", "$ref": "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionMetadataDatasetValidation" } } }, "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionMetadataDatasetValidation": { "id": "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionMetadataDatasetValidation", "description": "The dataset validation information. This includes any and all errors with documents and the dataset.", "type": "object", "properties": { "documentErrorCount": { "description": "The total number of document errors.", "type": "integer", "format": "int32" }, "datasetErrorCount": { "description": "The total number of dataset errors.", "type": "integer", "format": "int32" }, "documentErrors": { "description": "Error information pertaining to specific documents. A maximum of 10 document errors will be returned. Any document with errors will not be used throughout training.", "type": "array", "items": { "$ref": "GoogleRpcStatus" } }, "datasetErrors": { "description": "Error information for the dataset as a whole. A maximum of 10 dataset errors will be returned. A single dataset error is terminal for training.", "type": "array", "items": { "$ref": "GoogleRpcStatus" } } } }, "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3TrainProcessorVersionResponse", "description": "The response for TrainProcessorVersion.", "type": "object", "properties": { "processorVersion": { "description": "The resource name of the processor version produced by training.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3CreateLabelerPoolOperationMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3CreateLabelerPoolOperationMetadata", "description": "The long-running operation metadata for the CreateLabelerPool method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3UpdateLabelerPoolOperationMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3UpdateLabelerPoolOperationMetadata", "description": "The long-running operation metadata for UpdateLabelerPool.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3DeleteLabelerPoolOperationMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3DeleteLabelerPoolOperationMetadata", "description": "The long-running operation metadata for DeleteLabelerPool.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3UpdateHumanReviewConfigMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3UpdateHumanReviewConfigMetadata", "description": "The long-running operation metadata for updating the human review configuration.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3DeleteProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3DeleteProcessorVersionMetadata", "description": "The long-running operation metadata for the DeleteProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3DeployProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3DeployProcessorVersionMetadata", "description": "The long-running operation metadata for the DeployProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3DeployProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3DeployProcessorVersionResponse", "description": "Response message for the DeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3UndeployProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3UndeployProcessorVersionMetadata", "description": "The long-running operation metadata for the UndeployProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3UndeployProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3UndeployProcessorVersionResponse", "description": "Response message for the UndeployProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3EvaluateProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3EvaluateProcessorVersionMetadata", "description": "Metadata of the EvaluateProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3EvaluateProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3EvaluateProcessorVersionResponse", "description": "Response of the EvaluateProcessorVersion method.", "type": "object", "properties": { "evaluation": { "description": "The resource name of the created evaluation.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3SetDefaultProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3SetDefaultProcessorVersionMetadata", "description": "The long-running operation metadata for the SetDefaultProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3SetDefaultProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3SetDefaultProcessorVersionResponse", "description": "Response message for the SetDefaultProcessorVersion method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3ExportProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3ExportProcessorVersionMetadata", "description": "Metadata message associated with the ExportProcessorVersion operation.", "type": "object", "properties": { "commonMetadata": { "description": "The common metadata about the operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3ExportProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3ExportProcessorVersionResponse", "description": "Response message associated with the ExportProcessorVersion operation.", "type": "object", "properties": { "gcsUri": { "description": "The Cloud Storage URI containing the output artifacts.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3ImportProcessorVersionMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3ImportProcessorVersionMetadata", "description": "The long-running operation metadata for the ImportProcessorVersion method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata for the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3ImportProcessorVersionResponse": { "id": "GoogleCloudDocumentaiUiv1beta3ImportProcessorVersionResponse", "description": "The response message for the ImportProcessorVersion method.", "type": "object", "properties": { "processorVersion": { "description": "The destination processor version name.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3UpdateDatasetOperationMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3UpdateDatasetOperationMetadata", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } }, "GoogleCloudDocumentaiUiv1beta3ImportDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3ImportDocumentsResponse", "description": "Response of the import document operation.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadata", "description": "Metadata of the import document operation.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualImportStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadataIndividualImportStatus" } }, "importConfigValidationResults": { "description": "Validation statuses of the batch documents import config.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadataImportConfigValidationResult" } }, "totalDocumentCount": { "description": "Total number of the documents that are qualified for importing.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadataIndividualImportStatus": { "id": "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadataIndividualImportStatus", "description": "The status of each individual document in the import process.", "type": "object", "properties": { "inputGcsSource": { "description": "The source Cloud Storage URI of the document.", "type": "string" }, "status": { "description": "The status of the importing of the document.", "$ref": "GoogleRpcStatus" }, "outputGcsDestination": { "description": "The output_gcs_destination of the processed document if it was successful, otherwise empty.", "type": "string" }, "outputDocumentId": { "description": "The document id of imported document if it was successful, otherwise empty.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" } } }, "GoogleCloudDocumentaiUiv1beta3DocumentId": { "id": "GoogleCloudDocumentaiUiv1beta3DocumentId", "description": "Document Identifier.", "type": "object", "properties": { "gcsManagedDocId": { "description": "A document id within user-managed Cloud Storage.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentIdGCSManagedDocumentId" }, "unmanagedDocId": { "description": "A document id within unmanaged dataset.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentIdUnmanagedDocumentId" }, "revisionRef": { "description": "Points to a specific revision of the document if set.", "$ref": "GoogleCloudDocumentaiUiv1beta3RevisionRef" } } }, "GoogleCloudDocumentaiUiv1beta3DocumentIdGCSManagedDocumentId": { "id": "GoogleCloudDocumentaiUiv1beta3DocumentIdGCSManagedDocumentId", "description": "Identifies a document uniquely within the scope of a dataset in the user-managed Cloud Storage option.", "type": "object", "properties": { "gcsUri": { "description": "Required. The Cloud Storage URI where the actual document is stored.", "type": "string" }, "cwDocId": { "description": "Id of the document (indexed) managed by Content Warehouse.", "deprecated": true, "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3DocumentIdUnmanagedDocumentId": { "id": "GoogleCloudDocumentaiUiv1beta3DocumentIdUnmanagedDocumentId", "description": "Identifies a document uniquely within the scope of a dataset in unmanaged option.", "type": "object", "properties": { "docId": { "description": "Required. The id of the document.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3RevisionRef": { "id": "GoogleCloudDocumentaiUiv1beta3RevisionRef", "description": "The revision reference specifies which revision on the document to read.", "type": "object", "properties": { "revisionCase": { "description": "Reads the revision by the predefined case.", "type": "string", "enumDescriptions": [ "Unspecified case, fall back to read the `LATEST_HUMAN_REVIEW`.", "The latest revision made by a human.", "The latest revision based on timestamp.", "The first (OCR) revision." ], "enum": [ "REVISION_CASE_UNSPECIFIED", "LATEST_HUMAN_REVIEW", "LATEST_TIMESTAMP", "BASE_OCR_REVISION" ] }, "revisionId": { "description": "Reads the revision given by the id.", "type": "string" }, "latestProcessorVersion": { "description": "Reads the revision generated by the processor version. The format takes the full resource name of processor version. `projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}`", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadataImportConfigValidationResult": { "id": "GoogleCloudDocumentaiUiv1beta3ImportDocumentsMetadataImportConfigValidationResult", "description": "The validation status of each import config. Status is set to an error if there are no documents to import in the `import_config`, or `OK` if the operation will try to proceed with at least one document.", "type": "object", "properties": { "inputGcsSource": { "description": "The source Cloud Storage URI specified in the import config.", "type": "string" }, "status": { "description": "The validation status of import config.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsResponse", "description": "Response of the batch move documents operation.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsMetadata", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualBatchMoveStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsMetadataIndividualBatchMoveStatus" } }, "destDatasetType": { "description": "The destination dataset split type.", "deprecated": true, "type": "string", "enumDescriptions": [ "Default value if the enum is not set.", "Identifies the train documents.", "Identifies the test documents.", "Identifies the unassigned documents." ], "enum": [ "DATASET_SPLIT_TYPE_UNSPECIFIED", "DATASET_SPLIT_TRAIN", "DATASET_SPLIT_TEST", "DATASET_SPLIT_UNASSIGNED" ] }, "destSplitType": { "description": "The destination dataset split type.", "type": "string", "enumDescriptions": [ "Default value if the enum is not set.", "Identifies the train documents.", "Identifies the test documents.", "Identifies the unassigned documents." ], "enum": [ "DATASET_SPLIT_TYPE_UNSPECIFIED", "DATASET_SPLIT_TRAIN", "DATASET_SPLIT_TEST", "DATASET_SPLIT_UNASSIGNED" ] } } }, "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsMetadataIndividualBatchMoveStatus": { "id": "GoogleCloudDocumentaiUiv1beta3BatchMoveDocumentsMetadataIndividualBatchMoveStatus", "description": "The status of each individual document in the batch move process.", "type": "object", "properties": { "documentId": { "description": "The document id of the document.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" }, "status": { "description": "The status of moving the document.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsResponse", "description": "Response of the batch update documents operation.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsMetadata", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualBatchUpdateStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsMetadataIndividualBatchUpdateStatus" } } } }, "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsMetadataIndividualBatchUpdateStatus": { "id": "GoogleCloudDocumentaiUiv1beta3BatchUpdateDocumentsMetadataIndividualBatchUpdateStatus", "description": "The status of each individual document in the batch update process.", "type": "object", "properties": { "documentId": { "description": "The document id of the document.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" }, "status": { "description": "The status of updating the document in storage.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsResponse", "description": "Response of the delete documents operation.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsMetadata", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualBatchDeleteStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsMetadataIndividualBatchDeleteStatus" } }, "totalDocumentCount": { "description": "Total number of documents deleting from dataset.", "type": "integer", "format": "int32" }, "errorDocumentCount": { "description": "Total number of documents that failed to be deleted in storage.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsMetadataIndividualBatchDeleteStatus": { "id": "GoogleCloudDocumentaiUiv1beta3BatchDeleteDocumentsMetadataIndividualBatchDeleteStatus", "description": "The status of each individual document in the batch delete process.", "type": "object", "properties": { "documentId": { "description": "The document id of the document.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" }, "status": { "description": "The status of deleting the document in storage.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3ResyncDatasetResponse": { "id": "GoogleCloudDocumentaiUiv1beta3ResyncDatasetResponse", "description": "The response proto of ResyncDataset method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadata", "description": "The metadata proto of `ResyncDataset` method.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualDocumentResyncStatuses": { "description": "The list of document resync statuses. The same document could have multiple `individual_document_resync_statuses` if it has multiple inconsistencies.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadataIndividualDocumentResyncStatus" } }, "datasetResyncStatuses": { "description": "The list of dataset resync statuses. Not checked when ResyncDatasetRequest.dataset_documents is specified.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadataDatasetResyncStatus" } } } }, "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadataIndividualDocumentResyncStatus": { "id": "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadataIndividualDocumentResyncStatus", "description": "Resync status for each document per inconsistency type.", "type": "object", "properties": { "documentId": { "description": "The document identifier.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" }, "documentInconsistencyType": { "description": "The type of document inconsistency.", "type": "string", "enumDescriptions": [ "Default value.", "The document proto is invalid.", "Indexed docproto metadata is mismatched.", "The page image or thumbnails are missing." ], "enum": [ "DOCUMENT_INCONSISTENCY_TYPE_UNSPECIFIED", "DOCUMENT_INCONSISTENCY_TYPE_INVALID_DOCPROTO", "DOCUMENT_INCONSISTENCY_TYPE_MISMATCHED_METADATA", "DOCUMENT_INCONSISTENCY_TYPE_NO_PAGE_IMAGE" ] }, "status": { "description": "The status of resyncing the document with regards to the detected inconsistency. Empty if ResyncDatasetRequest.validate_only is `true`.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadataDatasetResyncStatus": { "id": "GoogleCloudDocumentaiUiv1beta3ResyncDatasetMetadataDatasetResyncStatus", "description": "Resync status against inconsistency types on the dataset level.", "type": "object", "properties": { "datasetInconsistencyType": { "description": "The type of the inconsistency of the dataset.", "type": "string", "enumDescriptions": [ "Default value.", "The marker file under the dataset folder is not found." ], "enum": [ "DATASET_INCONSISTENCY_TYPE_UNSPECIFIED", "DATASET_INCONSISTENCY_TYPE_NO_STORAGE_MARKER" ] }, "status": { "description": "The status of resyncing the dataset with regards to the detected inconsistency. Empty if ResyncDatasetRequest.validate_only is `true`.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3ExportDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3ExportDocumentsResponse", "description": "The response proto of ExportDocuments method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadata", "description": "Metadata of the batch export documents operation.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualExportStatuses": { "description": "The list of response details of each document.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadataIndividualExportStatus" } }, "splitExportStats": { "description": "The list of statistics for each dataset split type.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadataSplitExportStat" } } } }, "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadataIndividualExportStatus": { "id": "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadataIndividualExportStatus", "description": "The status of each individual document in the export process.", "type": "object", "properties": { "documentId": { "description": "The path to source docproto of the document.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" }, "status": { "description": "The status of the exporting of the document.", "$ref": "GoogleRpcStatus" }, "outputGcsDestination": { "description": "The output_gcs_destination of the exported document if it was successful, otherwise empty.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadataSplitExportStat": { "id": "GoogleCloudDocumentaiUiv1beta3ExportDocumentsMetadataSplitExportStat", "description": "The statistic representing a dataset split type for this export.", "type": "object", "properties": { "splitType": { "description": "The dataset split type.", "type": "string", "enumDescriptions": [ "Default value if the enum is not set.", "Identifies the train documents.", "Identifies the test documents.", "Identifies the unassigned documents." ], "enum": [ "DATASET_SPLIT_TYPE_UNSPECIFIED", "DATASET_SPLIT_TRAIN", "DATASET_SPLIT_TEST", "DATASET_SPLIT_UNASSIGNED" ] }, "totalDocumentCount": { "description": "Total number of documents with the given dataset split type to be exported.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsResponse", "description": "The response proto of AutoLabelDocuments method.", "type": "object", "properties": {} }, "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsMetadata", "description": "Metadata of the auto-labeling documents operation.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" }, "individualAutoLabelStatuses": { "description": "The list of individual auto-labeling statuses of the dataset documents.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsMetadataIndividualAutoLabelStatus" } }, "totalDocumentCount": { "description": "Total number of the auto-labeling documents.", "type": "integer", "format": "int32" } } }, "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsMetadataIndividualAutoLabelStatus": { "id": "GoogleCloudDocumentaiUiv1beta3AutoLabelDocumentsMetadataIndividualAutoLabelStatus", "description": "The status of individual documents in the auto-labeling process.", "type": "object", "properties": { "status": { "description": "The status of the document auto-labeling.", "$ref": "GoogleRpcStatus" }, "documentId": { "description": "The document id of the auto-labeled document. This will replace the gcs_uri.", "$ref": "GoogleCloudDocumentaiUiv1beta3DocumentId" } } }, "GoogleCloudDocumentaiUiv1beta3SampleDocumentsResponse": { "id": "GoogleCloudDocumentaiUiv1beta3SampleDocumentsResponse", "description": "Response of the sample documents operation.", "type": "object", "properties": { "selectedDocuments": { "description": "The result of the sampling process.", "type": "array", "items": { "$ref": "GoogleCloudDocumentaiUiv1beta3SampleDocumentsResponseSelectedDocument" } }, "sampleTestStatus": { "description": "The status of sampling documents in test split.", "$ref": "GoogleRpcStatus" }, "sampleTrainingStatus": { "description": "The status of sampling documents in training split.", "$ref": "GoogleRpcStatus" } } }, "GoogleCloudDocumentaiUiv1beta3SampleDocumentsResponseSelectedDocument": { "id": "GoogleCloudDocumentaiUiv1beta3SampleDocumentsResponseSelectedDocument", "type": "object", "properties": { "documentId": { "description": "An internal identifier for document.", "type": "string" } } }, "GoogleCloudDocumentaiUiv1beta3SampleDocumentsMetadata": { "id": "GoogleCloudDocumentaiUiv1beta3SampleDocumentsMetadata", "description": "Metadata of the sample documents operation.", "type": "object", "properties": { "commonMetadata": { "description": "The basic metadata of the long-running operation.", "$ref": "GoogleCloudDocumentaiUiv1beta3CommonOperationMetadata" } } } }, "version_module": true, "rootUrl": "https://documentai.googleapis.com/", "description": "Service to parse structured information from unstructured or semi-structured documents using state-of-the-art Google AI such as natural language, computer vision, translation, and AutoML.", "icons": { "x16": "http://www.google.com/images/icons/product/search-16.gif", "x32": "http://www.google.com/images/icons/product/search-32.gif" }, "documentationLink": "https://cloud.google.com/document-ai/docs/", "version": "v1beta3", "name": "documentai" }