aws-sdk-comprehend 1.39.0 → 1.40.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fb841e7f98bf2b40de5e3f385e3585ec64e29b61e921778971208d527886a5c9
-  data.tar.gz: 4e8687f7495e31d6c9a844ba6a29b1867cf91ecfba0b3bdd64be8e3fda8dfa88
+  metadata.gz: c616569ac151be94478678e8f509d8cc0a148201704f390a297716813aacdbb4
+  data.tar.gz: 04544c64f14ae2c12f441c69ddb498c328f6eb5d7bc9753daecc92870a8ef26c
 SHA512:
-  metadata.gz: 24ee5c1f0fa7e826845c22538e65a110fc59a26b171a2fb47ca05ac5ddc050c09adae81ace2c086dca498f1a47cd6910cfd2630d221e8a8bd61ccaf57812060b
-  data.tar.gz: 0eccd1f090108d68ff3f208b0499112eea405e401966f6dff53174e29c71e1892cd530ce3bf9b0bcac977101a626e1f8dca1de1d0f04d909f67cc89640b50e19
+  metadata.gz: 1739c21b0c89d9ab9e466bd9a10beb11ed6cfb01f300361a02c00c0af927745c5e431443ec1c402a3db4308f97ac40ae303f8ad2fbd59cf1cd74f6a0d1d34c62
+  data.tar.gz: ac326f22ea88035afdb8345306e01d5bb828d095463a4761958b6b0bca8d697bf4faebee237eff8f0aa8a0036f62c15b335d1024bd21af2727e5f54b4b8ead56

data/lib/aws-sdk-comprehend.rb

@@ -48,6 +48,6 @@ require_relative 'aws-sdk-comprehend/customizations'
 # @!group service
 module Aws::Comprehend
 
-  GEM_VERSION = '1.39.0'
+  GEM_VERSION = '1.40.0'
 
 end

data/lib/aws-sdk-comprehend/client.rb

@@ -706,8 +706,15 @@ module Aws::Comprehend
     #       },
     #     ],
     #     input_data_config: { # required
-    #       s3_uri: "S3Uri", # required
+    #       data_format: "COMPREHEND_CSV", # accepts COMPREHEND_CSV, AUGMENTED_MANIFEST
+    #       s3_uri: "S3Uri",
     #       label_delimiter: "LabelDelimiter",
+    #       augmented_manifests: [
+    #         {
+    #           s3_uri: "S3Uri", # required
+    #           attribute_names: ["AttributeNamesListItem"], # required
+    #         },
+    #       ],
     #     },
     #     output_data_config: {
     #       s3_uri: "S3Uri",
@@ -873,12 +880,13 @@ module Aws::Comprehend
     #       },
     #     ],
     #     input_data_config: { # required
+    #       data_format: "COMPREHEND_CSV", # accepts COMPREHEND_CSV, AUGMENTED_MANIFEST
     #       entity_types: [ # required
     #         {
     #           type: "EntityTypeName", # required
     #         },
     #       ],
-    #       documents: { # required
+    #       documents: {
     #         s3_uri: "S3Uri", # required
     #       },
     #       annotations: {
@@ -887,6 +895,12 @@ module Aws::Comprehend
     #       entity_list: {
     #         s3_uri: "S3Uri", # required
     #       },
+    #       augmented_manifests: [
+    #         {
+    #           s3_uri: "S3Uri", # required
+    #           attribute_names: ["AttributeNamesListItem"], # required
+    #         },
+    #       ],
     #     },
     #     client_request_token: "ClientRequestTokenString",
     #     language_code: "en", # required, accepts en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW
@@ -1069,8 +1083,13 @@ module Aws::Comprehend
     #   resp.document_classifier_properties.end_time #=> Time
     #   resp.document_classifier_properties.training_start_time #=> Time
     #   resp.document_classifier_properties.training_end_time #=> Time
+    #   resp.document_classifier_properties.input_data_config.data_format #=> String, one of "COMPREHEND_CSV", "AUGMENTED_MANIFEST"
     #   resp.document_classifier_properties.input_data_config.s3_uri #=> String
     #   resp.document_classifier_properties.input_data_config.label_delimiter #=> String
+    #   resp.document_classifier_properties.input_data_config.augmented_manifests #=> Array
+    #   resp.document_classifier_properties.input_data_config.augmented_manifests[0].s3_uri #=> String
+    #   resp.document_classifier_properties.input_data_config.augmented_manifests[0].attribute_names #=> Array
+    #   resp.document_classifier_properties.input_data_config.augmented_manifests[0].attribute_names[0] #=> String
     #   resp.document_classifier_properties.output_data_config.s3_uri #=> String
     #   resp.document_classifier_properties.output_data_config.kms_key_id #=> String
     #   resp.document_classifier_properties.classifier_metadata.number_of_labels #=> Integer
@@ -1256,11 +1275,16 @@ module Aws::Comprehend
     #   resp.entity_recognizer_properties.end_time #=> Time
     #   resp.entity_recognizer_properties.training_start_time #=> Time
     #   resp.entity_recognizer_properties.training_end_time #=> Time
+    #   resp.entity_recognizer_properties.input_data_config.data_format #=> String, one of "COMPREHEND_CSV", "AUGMENTED_MANIFEST"
     #   resp.entity_recognizer_properties.input_data_config.entity_types #=> Array
     #   resp.entity_recognizer_properties.input_data_config.entity_types[0].type #=> String
     #   resp.entity_recognizer_properties.input_data_config.documents.s3_uri #=> String
     #   resp.entity_recognizer_properties.input_data_config.annotations.s3_uri #=> String
     #   resp.entity_recognizer_properties.input_data_config.entity_list.s3_uri #=> String
+    #   resp.entity_recognizer_properties.input_data_config.augmented_manifests #=> Array
+    #   resp.entity_recognizer_properties.input_data_config.augmented_manifests[0].s3_uri #=> String
+    #   resp.entity_recognizer_properties.input_data_config.augmented_manifests[0].attribute_names #=> Array
+    #   resp.entity_recognizer_properties.input_data_config.augmented_manifests[0].attribute_names[0] #=> String
     #   resp.entity_recognizer_properties.recognizer_metadata.number_of_trained_documents #=> Integer
     #   resp.entity_recognizer_properties.recognizer_metadata.number_of_test_documents #=> Integer
     #   resp.entity_recognizer_properties.recognizer_metadata.evaluation_metrics.precision #=> Float
@@ -1835,8 +1859,13 @@ module Aws::Comprehend
     #   resp.document_classifier_properties_list[0].end_time #=> Time
     #   resp.document_classifier_properties_list[0].training_start_time #=> Time
     #   resp.document_classifier_properties_list[0].training_end_time #=> Time
+    #   resp.document_classifier_properties_list[0].input_data_config.data_format #=> String, one of "COMPREHEND_CSV", "AUGMENTED_MANIFEST"
     #   resp.document_classifier_properties_list[0].input_data_config.s3_uri #=> String
     #   resp.document_classifier_properties_list[0].input_data_config.label_delimiter #=> String
+    #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests #=> Array
+    #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests[0].s3_uri #=> String
+    #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests[0].attribute_names #=> Array
+    #   resp.document_classifier_properties_list[0].input_data_config.augmented_manifests[0].attribute_names[0] #=> String
     #   resp.document_classifier_properties_list[0].output_data_config.s3_uri #=> String
     #   resp.document_classifier_properties_list[0].output_data_config.kms_key_id #=> String
     #   resp.document_classifier_properties_list[0].classifier_metadata.number_of_labels #=> Integer
@@ -2104,11 +2133,16 @@ module Aws::Comprehend
     #   resp.entity_recognizer_properties_list[0].end_time #=> Time
     #   resp.entity_recognizer_properties_list[0].training_start_time #=> Time
     #   resp.entity_recognizer_properties_list[0].training_end_time #=> Time
+    #   resp.entity_recognizer_properties_list[0].input_data_config.data_format #=> String, one of "COMPREHEND_CSV", "AUGMENTED_MANIFEST"
     #   resp.entity_recognizer_properties_list[0].input_data_config.entity_types #=> Array
     #   resp.entity_recognizer_properties_list[0].input_data_config.entity_types[0].type #=> String
     #   resp.entity_recognizer_properties_list[0].input_data_config.documents.s3_uri #=> String
     #   resp.entity_recognizer_properties_list[0].input_data_config.annotations.s3_uri #=> String
     #   resp.entity_recognizer_properties_list[0].input_data_config.entity_list.s3_uri #=> String
+    #   resp.entity_recognizer_properties_list[0].input_data_config.augmented_manifests #=> Array
+    #   resp.entity_recognizer_properties_list[0].input_data_config.augmented_manifests[0].s3_uri #=> String
+    #   resp.entity_recognizer_properties_list[0].input_data_config.augmented_manifests[0].attribute_names #=> Array
+    #   resp.entity_recognizer_properties_list[0].input_data_config.augmented_manifests[0].attribute_names[0] #=> String
     #   resp.entity_recognizer_properties_list[0].recognizer_metadata.number_of_trained_documents #=> Integer
     #   resp.entity_recognizer_properties_list[0].recognizer_metadata.number_of_test_documents #=> Integer
     #   resp.entity_recognizer_properties_list[0].recognizer_metadata.evaluation_metrics.precision #=> Float
@@ -3447,7 +3481,7 @@ module Aws::Comprehend
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-comprehend'
-      context[:gem_version] = '1.39.0'
+      context[:gem_version] = '1.40.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-comprehend/client_api.rb

@@ -14,6 +14,9 @@ module Aws::Comprehend
     include Seahorse::Model
 
     AnyLengthString = Shapes::StringShape.new(name: 'AnyLengthString')
+    AttributeNamesList = Shapes::ListShape.new(name: 'AttributeNamesList')
+    AttributeNamesListItem = Shapes::StringShape.new(name: 'AttributeNamesListItem')
+    AugmentedManifestsListItem = Shapes::StructureShape.new(name: 'AugmentedManifestsListItem')
     BatchDetectDominantLanguageItemResult = Shapes::StructureShape.new(name: 'BatchDetectDominantLanguageItemResult')
     BatchDetectDominantLanguageRequest = Shapes::StructureShape.new(name: 'BatchDetectDominantLanguageRequest')
     BatchDetectDominantLanguageResponse = Shapes::StructureShape.new(name: 'BatchDetectDominantLanguageResponse')
@@ -94,6 +97,8 @@ module Aws::Comprehend
     DocumentClassificationJobProperties = Shapes::StructureShape.new(name: 'DocumentClassificationJobProperties')
     DocumentClassificationJobPropertiesList = Shapes::ListShape.new(name: 'DocumentClassificationJobPropertiesList')
     DocumentClassifierArn = Shapes::StringShape.new(name: 'DocumentClassifierArn')
+    DocumentClassifierAugmentedManifestsList = Shapes::ListShape.new(name: 'DocumentClassifierAugmentedManifestsList')
+    DocumentClassifierDataFormat = Shapes::StringShape.new(name: 'DocumentClassifierDataFormat')
     DocumentClassifierEndpointArn = Shapes::StringShape.new(name: 'DocumentClassifierEndpointArn')
     DocumentClassifierFilter = Shapes::StructureShape.new(name: 'DocumentClassifierFilter')
     DocumentClassifierInputDataConfig = Shapes::StructureShape.new(name: 'DocumentClassifierInputDataConfig')
@@ -117,6 +122,8 @@ module Aws::Comprehend
     Entity = Shapes::StructureShape.new(name: 'Entity')
     EntityRecognizerAnnotations = Shapes::StructureShape.new(name: 'EntityRecognizerAnnotations')
     EntityRecognizerArn = Shapes::StringShape.new(name: 'EntityRecognizerArn')
+    EntityRecognizerAugmentedManifestsList = Shapes::ListShape.new(name: 'EntityRecognizerAugmentedManifestsList')
+    EntityRecognizerDataFormat = Shapes::StringShape.new(name: 'EntityRecognizerDataFormat')
     EntityRecognizerDocuments = Shapes::StructureShape.new(name: 'EntityRecognizerDocuments')
     EntityRecognizerEndpointArn = Shapes::StringShape.new(name: 'EntityRecognizerEndpointArn')
     EntityRecognizerEntityList = Shapes::StructureShape.new(name: 'EntityRecognizerEntityList')
@@ -272,6 +279,12 @@ module Aws::Comprehend
     UpdateEndpointResponse = Shapes::StructureShape.new(name: 'UpdateEndpointResponse')
     VpcConfig = Shapes::StructureShape.new(name: 'VpcConfig')
 
+    AttributeNamesList.member = Shapes::ShapeRef.new(shape: AttributeNamesListItem)
+
+    AugmentedManifestsListItem.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, required: true, location_name: "S3Uri"))
+    AugmentedManifestsListItem.add_member(:attribute_names, Shapes::ShapeRef.new(shape: AttributeNamesList, required: true, location_name: "AttributeNames"))
+    AugmentedManifestsListItem.struct_class = Types::AugmentedManifestsListItem
+
     BatchDetectDominantLanguageItemResult.add_member(:index, Shapes::ShapeRef.new(shape: Integer, location_name: "Index"))
     BatchDetectDominantLanguageItemResult.add_member(:languages, Shapes::ShapeRef.new(shape: ListOfDominantLanguages, location_name: "Languages"))
     BatchDetectDominantLanguageItemResult.struct_class = Types::BatchDetectDominantLanguageItemResult
@@ -553,13 +566,17 @@ module Aws::Comprehend
 
     DocumentClassificationJobPropertiesList.member = Shapes::ShapeRef.new(shape: DocumentClassificationJobProperties)
 
+    DocumentClassifierAugmentedManifestsList.member = Shapes::ShapeRef.new(shape: AugmentedManifestsListItem)
+
     DocumentClassifierFilter.add_member(:status, Shapes::ShapeRef.new(shape: ModelStatus, location_name: "Status"))
     DocumentClassifierFilter.add_member(:submit_time_before, Shapes::ShapeRef.new(shape: Timestamp, location_name: "SubmitTimeBefore"))
     DocumentClassifierFilter.add_member(:submit_time_after, Shapes::ShapeRef.new(shape: Timestamp, location_name: "SubmitTimeAfter"))
     DocumentClassifierFilter.struct_class = Types::DocumentClassifierFilter
 
-    DocumentClassifierInputDataConfig.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, required: true, location_name: "S3Uri"))
+    DocumentClassifierInputDataConfig.add_member(:data_format, Shapes::ShapeRef.new(shape: DocumentClassifierDataFormat, location_name: "DataFormat"))
+    DocumentClassifierInputDataConfig.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, location_name: "S3Uri"))
     DocumentClassifierInputDataConfig.add_member(:label_delimiter, Shapes::ShapeRef.new(shape: LabelDelimiter, location_name: "LabelDelimiter"))
+    DocumentClassifierInputDataConfig.add_member(:augmented_manifests, Shapes::ShapeRef.new(shape: DocumentClassifierAugmentedManifestsList, location_name: "AugmentedManifests"))
     DocumentClassifierInputDataConfig.struct_class = Types::DocumentClassifierInputDataConfig
 
     DocumentClassifierOutputDataConfig.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, location_name: "S3Uri"))
@@ -665,6 +682,8 @@ module Aws::Comprehend
     EntityRecognizerAnnotations.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, required: true, location_name: "S3Uri"))
     EntityRecognizerAnnotations.struct_class = Types::EntityRecognizerAnnotations
 
+    EntityRecognizerAugmentedManifestsList.member = Shapes::ShapeRef.new(shape: AugmentedManifestsListItem)
+
     EntityRecognizerDocuments.add_member(:s3_uri, Shapes::ShapeRef.new(shape: S3Uri, required: true, location_name: "S3Uri"))
     EntityRecognizerDocuments.struct_class = Types::EntityRecognizerDocuments
 
@@ -681,10 +700,12 @@ module Aws::Comprehend
     EntityRecognizerFilter.add_member(:submit_time_after, Shapes::ShapeRef.new(shape: Timestamp, location_name: "SubmitTimeAfter"))
     EntityRecognizerFilter.struct_class = Types::EntityRecognizerFilter
 
+    EntityRecognizerInputDataConfig.add_member(:data_format, Shapes::ShapeRef.new(shape: EntityRecognizerDataFormat, location_name: "DataFormat"))
     EntityRecognizerInputDataConfig.add_member(:entity_types, Shapes::ShapeRef.new(shape: EntityTypesList, required: true, location_name: "EntityTypes"))
-    EntityRecognizerInputDataConfig.add_member(:documents, Shapes::ShapeRef.new(shape: EntityRecognizerDocuments, required: true, location_name: "Documents"))
+    EntityRecognizerInputDataConfig.add_member(:documents, Shapes::ShapeRef.new(shape: EntityRecognizerDocuments, location_name: "Documents"))
     EntityRecognizerInputDataConfig.add_member(:annotations, Shapes::ShapeRef.new(shape: EntityRecognizerAnnotations, location_name: "Annotations"))
     EntityRecognizerInputDataConfig.add_member(:entity_list, Shapes::ShapeRef.new(shape: EntityRecognizerEntityList, location_name: "EntityList"))
+    EntityRecognizerInputDataConfig.add_member(:augmented_manifests, Shapes::ShapeRef.new(shape: EntityRecognizerAugmentedManifestsList, location_name: "AugmentedManifests"))
     EntityRecognizerInputDataConfig.struct_class = Types::EntityRecognizerInputDataConfig
 
     EntityRecognizerMetadata.add_member(:number_of_trained_documents, Shapes::ShapeRef.new(shape: Integer, location_name: "NumberOfTrainedDocuments"))

data/lib/aws-sdk-comprehend/types.rb

@@ -10,6 +10,47 @@
 module Aws::Comprehend
   module Types
 
+    # An augmented manifest file that provides training data for your custom
+    # model. An augmented manifest file is a labeled dataset that is
+    # produced by Amazon SageMaker Ground Truth.
+    #
+    # @note When making an API call, you may pass AugmentedManifestsListItem
+    #   data as a hash:
+    #
+    #       {
+    #         s3_uri: "S3Uri", # required
+    #         attribute_names: ["AttributeNamesListItem"], # required
+    #       }
+    #
+    # @!attribute [rw] s3_uri
+    #   The Amazon S3 location of the augmented manifest file.
+    #   @return [String]
+    #
+    # @!attribute [rw] attribute_names
+    #   The JSON attribute that contains the annotations for your training
+    #   documents. The number of attribute names that you specify depends on
+    #   whether your augmented manifest file is the output of a single
+    #   labeling job or a chained labeling job.
+    #
+    #   If your file is the output of a single labeling job, specify the
+    #   LabelAttributeName key that was used when the job was created in
+    #   Ground Truth.
+    #
+    #   If your file is the output of a chained labeling job, specify the
+    #   LabelAttributeName key for one or more jobs in the chain. Each
+    #   LabelAttributeName key provides the annotations from an individual
+    #   job.
+    #   @return [Array<String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/AugmentedManifestsListItem AWS API Documentation
+    #
+    class AugmentedManifestsListItem < Struct.new(
+      :s3_uri,
+      :attribute_names)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # The result of calling the operation. The operation returns one object
     # for each document that is successfully processed by the operation.
     #
@@ -604,8 +645,15 @@ module Aws::Comprehend
     #           },
     #         ],
     #         input_data_config: { # required
-    #           s3_uri: "S3Uri", # required
+    #           data_format: "COMPREHEND_CSV", # accepts COMPREHEND_CSV, AUGMENTED_MANIFEST
+    #           s3_uri: "S3Uri",
     #           label_delimiter: "LabelDelimiter",
+    #           augmented_manifests: [
+    #             {
+    #               s3_uri: "S3Uri", # required
+    #               attribute_names: ["AttributeNamesListItem"], # required
+    #             },
+    #           ],
     #         },
     #         output_data_config: {
     #           s3_uri: "S3Uri",
@@ -810,12 +858,13 @@ module Aws::Comprehend
     #           },
     #         ],
     #         input_data_config: { # required
+    #           data_format: "COMPREHEND_CSV", # accepts COMPREHEND_CSV, AUGMENTED_MANIFEST
     #           entity_types: [ # required
     #             {
     #               type: "EntityTypeName", # required
     #             },
     #           ],
-    #           documents: { # required
+    #           documents: {
     #             s3_uri: "S3Uri", # required
     #           },
     #           annotations: {
@@ -824,6 +873,12 @@ module Aws::Comprehend
     #           entity_list: {
     #             s3_uri: "S3Uri", # required
     #           },
+    #           augmented_manifests: [
+    #             {
+    #               s3_uri: "S3Uri", # required
+    #               attribute_names: ["AttributeNamesListItem"], # required
+    #             },
+    #           ],
     #         },
     #         client_request_token: "ClientRequestTokenString",
     #         language_code: "en", # required, accepts en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW
@@ -1813,10 +1868,37 @@ module Aws::Comprehend
     #   data as a hash:
     #
     #       {
-    #         s3_uri: "S3Uri", # required
+    #         data_format: "COMPREHEND_CSV", # accepts COMPREHEND_CSV, AUGMENTED_MANIFEST
+    #         s3_uri: "S3Uri",
     #         label_delimiter: "LabelDelimiter",
+    #         augmented_manifests: [
+    #           {
+    #             s3_uri: "S3Uri", # required
+    #             attribute_names: ["AttributeNamesListItem"], # required
+    #           },
+    #         ],
     #       }
     #
+    # @!attribute [rw] data_format
+    #   The format of your training data:
+    #
+    #   * `COMPREHEND_CSV`\: A two-column CSV file, where labels are
+    #     provided in the first column, and documents are provided in the
+    #     second. If you use this value, you must provide the `S3Uri`
+    #     parameter in your request.
+    #
+    #   * `AUGMENTED_MANIFEST`\: A labeled dataset that is produced by
+    #     Amazon SageMaker Ground Truth. This file is in JSON lines format.
+    #     Each line is a complete JSON object that contains a training
+    #     document and its associated labels.
+    #
+    #     If you use this value, you must provide the `AugmentedManifests`
+    #     parameter in your request.
+    #
+    #   If you don't specify a value, Amazon Comprehend uses
+    #   `COMPREHEND_CSV` as the default.
+    #   @return [String]
+    #
     # @!attribute [rw] s3_uri
     #   The Amazon S3 URI for the input data. The S3 bucket must be in the
     #   same region as the API endpoint that you are calling. The URI can
@@ -1827,6 +1909,9 @@ module Aws::Comprehend
     #   prefix is a single file, Amazon Comprehend uses that file as input.
     #   If more than one file begins with the prefix, Amazon Comprehend uses
     #   all of them as input.
+    #
+    #   This parameter is required if you set `DataFormat` to
+    #   `COMPREHEND_CSV`.
     #   @return [String]
     #
     # @!attribute [rw] label_delimiter
@@ -1839,11 +1924,22 @@ module Aws::Comprehend
     #   be combined to make a single unique label, such as LABELLABELLABEL.
     #   @return [String]
     #
+    # @!attribute [rw] augmented_manifests
+    #   A list of augmented manifest files that provide training data for
+    #   your custom model. An augmented manifest file is a labeled dataset
+    #   that is produced by Amazon SageMaker Ground Truth.
+    #
+    #   This parameter is required if you set `DataFormat` to
+    #   `AUGMENTED_MANIFEST`.
+    #   @return [Array<Types::AugmentedManifestsListItem>]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/DocumentClassifierInputDataConfig AWS API Documentation
     #
     class DocumentClassifierInputDataConfig < Struct.new(
+      :data_format,
       :s3_uri,
-      :label_delimiter)
+      :label_delimiter,
+      :augmented_manifests)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -2626,12 +2722,13 @@ module Aws::Comprehend
     #   data as a hash:
     #
     #       {
+    #         data_format: "COMPREHEND_CSV", # accepts COMPREHEND_CSV, AUGMENTED_MANIFEST
     #         entity_types: [ # required
     #           {
     #             type: "EntityTypeName", # required
     #           },
     #         ],
-    #         documents: { # required
+    #         documents: {
     #           s3_uri: "S3Uri", # required
     #         },
     #         annotations: {
@@ -2640,33 +2737,89 @@ module Aws::Comprehend
     #         entity_list: {
     #           s3_uri: "S3Uri", # required
     #         },
+    #         augmented_manifests: [
+    #           {
+    #             s3_uri: "S3Uri", # required
+    #             attribute_names: ["AttributeNamesListItem"], # required
+    #           },
+    #         ],
     #       }
     #
+    # @!attribute [rw] data_format
+    #   The format of your training data:
+    #
+    #   * `COMPREHEND_CSV`\: A CSV file that supplements your training
+    #     documents. The CSV file contains information about the custom
+    #     entities that your trained model will detect. The required format
+    #     of the file depends on whether you are providing annotations or an
+    #     entity list.
+    #
+    #     If you use this value, you must provide your CSV file by using
+    #     either the `Annotations` or `EntityList` parameters. You must
+    #     provide your training documents by using the `Documents`
+    #     parameter.
+    #
+    #   * `AUGMENTED_MANIFEST`\: A labeled dataset that is produced by
+    #     Amazon SageMaker Ground Truth. This file is in JSON lines format.
+    #     Each line is a complete JSON object that contains a training
+    #     document and its labels. Each label annotates a named entity in
+    #     the training document.
+    #
+    #     If you use this value, you must provide the `AugmentedManifests`
+    #     parameter in your request.
+    #
+    #   If you don't specify a value, Amazon Comprehend uses
+    #   `COMPREHEND_CSV` as the default.
+    #   @return [String]
+    #
     # @!attribute [rw] entity_types
-    #   The entity types in the input data for an entity recognizer. A
-    #   maximum of 25 entity types can be used at one time to train an
-    #   entity recognizer.
+    #   The entity types in the labeled training data that Amazon Comprehend
+    #   uses to train the custom entity recognizer. Any entity types that
+    #   you don't specify are ignored.
+    #
+    #   A maximum of 25 entity types can be used at one time to train an
+    #   entity recognizer. Entity types must not contain the following
+    #   invalid characters: \\n (line break), \\\\n (escaped line break),
+    #   \\r (carriage return), \\\\r (escaped carriage return), \\t (tab),
+    #   \\\\t (escaped tab), space, and , (comma).
     #   @return [Array<Types::EntityTypesListItem>]
     #
     # @!attribute [rw] documents
-    #   S3 location of the documents folder for an entity recognizer
+    #   The S3 location of the folder that contains the training documents
+    #   for your custom entity recognizer.
+    #
+    #   This parameter is required if you set `DataFormat` to
+    #   `COMPREHEND_CSV`.
     #   @return [Types::EntityRecognizerDocuments]
     #
     # @!attribute [rw] annotations
-    #   S3 location of the annotations file for an entity recognizer.
+    #   The S3 location of the CSV file that annotates your training
+    #   documents.
     #   @return [Types::EntityRecognizerAnnotations]
     #
     # @!attribute [rw] entity_list
-    #   S3 location of the entity list for an entity recognizer.
+    #   The S3 location of the CSV file that has the entity list for your
+    #   custom entity recognizer.
     #   @return [Types::EntityRecognizerEntityList]
     #
+    # @!attribute [rw] augmented_manifests
+    #   A list of augmented manifest files that provide training data for
+    #   your custom model. An augmented manifest file is a labeled dataset
+    #   that is produced by Amazon SageMaker Ground Truth.
+    #
+    #   This parameter is required if you set `DataFormat` to
+    #   `AUGMENTED_MANIFEST`.
+    #   @return [Array<Types::AugmentedManifestsListItem>]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/EntityRecognizerInputDataConfig AWS API Documentation
     #
     class EntityRecognizerInputDataConfig < Struct.new(
+      :data_format,
       :entity_types,
       :documents,
       :annotations,
-      :entity_list)
+      :entity_list,
+      :augmented_manifests)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -2858,7 +3011,8 @@ module Aws::Comprehend
       include Aws::Structure
     end
 
-    # Information about an individual item on a list of entity types.
+    # An entity type within a labeled training dataset that Amazon
+    # Comprehend uses to train a custom entity recognizer.
     #
     # @note When making an API call, you may pass EntityTypesListItem
     #   data as a hash:
@@ -2868,7 +3022,13 @@ module Aws::Comprehend
     #       }
     #
     # @!attribute [rw] type
-    #   Entity type of an item on an entity type list.
+    #   An entity type within a labeled training dataset that Amazon
+    #   Comprehend uses to train a custom entity recognizer.
+    #
+    #   Entity types must not contain the following invalid characters: \\n
+    #   (line break), \\\\n (escaped line break, \\r (carriage return),
+    #   \\\\r (escaped carriage return), \\t (tab), \\\\t (escaped tab),
+    #   space, and , (comma).
     #   @return [String]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/comprehend-2017-11-27/EntityTypesListItem AWS API Documentation

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-comprehend
 version: !ruby/object:Gem::Version
-  version: 1.39.0
+  version: 1.40.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-09-17 00:00:00.000000000 Z
+date: 2020-09-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core