String s3Uri
The Amazon S3 location of the augmented manifest file.
String split
The purpose of the data you've provided in the augmented manifest. You can either train or test this data. If you don't specify, the default is train.
TRAIN - all of the documents in the manifest will be used for training. If no test documents are provided, Amazon Comprehend will automatically reserve a portion of the training documents for testing.
TEST - all of the documents in the manifest will be used for testing.
List<E> attributeNames
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.
String annotationDataS3Uri
The S3 prefix to the annotation files that are referred in the augmented manifest file.
String sourceDocumentsS3Uri
The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file.
String documentType
The type of augmented manifest. PlainTextDocument or SemiStructuredDocument. If you don't specify, the default is PlainTextDocument.
PLAIN_TEXT_DOCUMENT A document type that represents any unicode text that is encoded in UTF-8.
SEMI_STRUCTURED_DOCUMENT A document type with positional and structural context, like a PDF. For
training with Amazon Comprehend, only PDFs are supported. For inference, Amazon Comprehend support PDFs, DOCX and
TXT.
Integer index
The zero-based index of the document in the input list.
List<E> languages
One or more DominantLanguage objects describing the dominant languages in the document.
List<E> resultList
A list of objects containing the results of the operation. The results are sorted in ascending order by the
Index field and match the order of the documents in the input list. If all of the documents contain
an error, the ResultList is empty.
List<E> errorList
A list containing one object for each document that contained an error. The results are sorted in ascending order
by the Index field and match the order of the documents in the input list. If there are no errors in
the batch, the ErrorList is empty.
List<E> textList
A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
String languageCode
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
List<E> resultList
A list of objects containing the results of the operation. The results are sorted in ascending order by the
Index field and match the order of the documents in the input list. If all of the documents contain
an error, the ResultList is empty.
List<E> errorList
A list containing one object for each document that contained an error. The results are sorted in ascending order
by the Index field and match the order of the documents in the input list. If there are no errors in
the batch, the ErrorList is empty.
List<E> textList
A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
String languageCode
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
List<E> resultList
A list of objects containing the results of the operation. The results are sorted in ascending order by the
Index field and match the order of the documents in the input list. If all of the documents contain
an error, the ResultList is empty.
List<E> errorList
A list containing one object for each document that contained an error. The results are sorted in ascending order
by the Index field and match the order of the documents in the input list. If there are no errors in
the batch, the ErrorList is empty.
Integer index
The zero-based index of the document in the input list.
String sentiment
The sentiment detected in the document.
SentimentScore sentimentScore
The level of confidence that Amazon Comprehend has in the accuracy of its sentiment detection.
List<E> textList
A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
String languageCode
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
List<E> resultList
A list of objects containing the results of the operation. The results are sorted in ascending order by the
Index field and match the order of the documents in the input list. If all of the documents contain
an error, the ResultList is empty.
List<E> errorList
A list containing one object for each document that contained an error. The results are sorted in ascending order
by the Index field and match the order of the documents in the input list. If there are no errors in
the batch, the ErrorList is empty.
List<E> textList
A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size for each document is 5 KB.
String languageCode
The language of the input documents. You can specify any of the following languages supported by Amazon Comprehend: German ("de"), English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), or Portuguese ("pt"). All documents must be in the same language.
List<E> resultList
A list of objects containing the results of the operation. The results are sorted in ascending order by the
Index field and match the order of the documents in the input list. If all of the documents contain
an error, the ResultList is empty.
List<E> errorList
A list containing one object for each document that contained an error. The results are sorted in ascending order
by the Index field and match the order of the documents in the input list. If there are no errors in
the batch, the ErrorList is empty.
List<E> textList
A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. The maximum size of each document is 5 KB.
String languageCode
The language of the input documents. Currently, English is the only supported language.
List<E> resultList
A list of objects containing the results of the operation. The results are sorted in ascending order by the
Index field and match the order of the documents in the input list. If all of the documents contain
an error, the ResultList is empty.
List<E> errorList
List of errors that the operation can return.
String id
Unique identifier for the block.
String blockType
The block represents a line of text or one word of text.
WORD - A word that's detected on a document page. A word is one or more ISO basic Latin script characters that aren't separated by spaces.
LINE - A string of tab-delimited, contiguous words that are detected on a document page
String text
The word or line of text extracted from the block.
Integer page
Page number where the block appears.
Geometry geometry
Co-ordinates of the rectangle or polygon that contains the text.
List<E> relationships
A list of child blocks of the current block. For example, a LINE object has child blocks for each WORD block that's part of the line of text.
String blockId
Unique identifier for the block.
Integer beginOffset
Offset of the start of the block within its parent block.
Integer endOffset
Offset of the end of the block within its parent block.
List<E> childBlocks
List of child blocks within this block.
Float height
The height of the bounding box as a ratio of the overall document page height.
Float left
The left coordinate of the bounding box as a ratio of overall document page width.
Float top
The top coordinate of the bounding box as a ratio of overall document page height.
Float width
The width of the bounding box as a ratio of the overall document page width.
Double accuracy
The fraction of the labels that were correct recognized. It is computed by dividing the number of labels in the test documents that were correctly recognized by the total number of labels in the test documents.
Double precision
A measure of the usefulness of the classifier results in the test data. High precision means that the classifier returned substantially more relevant results than irrelevant ones.
Double recall
A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results.
Double f1Score
A measure of how accurate the classifier results are for the test data. It is derived from the
Precision and Recall values. The F1Score is the harmonic average of the
two scores. The highest score is 1, and the worst score is 0.
Double microPrecision
A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones. Unlike the Precision metric which comes from averaging the precision of all available labels, this is based on the overall score of all precision scores added together.
Double microRecall
A measure of how complete the classifier results are for the test data. High recall means that the classifier returned most of the relevant results. Specifically, this indicates how many of the correct categories in the text that the model can predict. It is a percentage of correct categories in the text that can found. Instead of averaging the recall scores of all labels (as with Recall), micro Recall is based on the overall score of all recall scores added together.
Double microF1Score
A measure of how accurate the classifier results are for the test data. It is a combination of the
Micro Precision and Micro Recall values. The Micro F1Score is the harmonic
mean of the two scores. The highest score is 1, and the worst score is 0.
Double hammingLoss
Indicates the fraction of labels that are incorrectly predicted. Also seen as the fraction of wrong labels compared to the total number of labels. Scores closer to zero are better.
Integer numberOfLabels
The number of labels in the input data.
Integer numberOfTrainedDocuments
The number of documents in the input data that were used to train the classifier. Typically this is 80 to 90 percent of the input documents.
Integer numberOfTestDocuments
The number of documents in the input data that were used to test the classifier. Typically this is 10 to 20 percent of the input documents, up to 10,000 documents.
ClassifierEvaluationMetrics evaluationMetrics
Describes the result metrics for the test data associated with an documentation classifier.
String text
The document text to be analyzed. If you enter text using this parameter, do not use the Bytes
parameter.
String endpointArn
The Amazon Resource Number (ARN) of the endpoint.
For prompt safety classification, Amazon Comprehend provides the endpoint ARN. For more information about prompt safety classifiers, see Prompt safety classification in the Amazon Comprehend Developer Guide
For custom classification, you create an endpoint for your custom model. For more information, see Using Amazon Comprehend endpoints.
ByteBuffer bytes
Use the Bytes parameter to input a text, PDF, Word or image file.
When you classify a document using a custom model, you can also use the Bytes parameter to input an
Amazon Textract DetectDocumentText or AnalyzeDocument output file.
To classify a document using the prompt safety classifier, use the Text parameter for input.
Provide the input document as a sequence of base64-encoded bytes. If your code uses an Amazon Web Services SDK to classify documents, the SDK may encode the document file bytes for you.
The maximum length of this field depends on the input document type. For details, see Inputs for real-time custom analysis in the Comprehend Developer Guide.
If you use the Bytes parameter, do not use the Text parameter.
DocumentReaderConfig documentReaderConfig
Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
List<E> classes
The classes used by the document being analyzed. These are used for models trained in multi-class mode. Individual classes are mutually exclusive and each document is expected to have only a single class assigned to it. For example, an animal can be a dog or a cat, but not both at the same time.
For prompt safety classification, the response includes only two classes (SAFE_PROMPT and UNSAFE_PROMPT), along with a confidence score for each class. The value range of the score is zero to one, where one is the highest confidence.
List<E> labels
The labels used in the document being analyzed. These are used for multi-label trained models. Individual labels represent different categories that are related in some manner and are not mutually exclusive. For example, a movie can be just an action movie, or it can be an action movie, a science fiction movie, and a comedy, all at the same time.
DocumentMetadata documentMetadata
Extraction information about the document. This field is present in the response only if your request includes
the Byte parameter.
List<E> documentType
The document type for each page in the input document. This field is present in the response only if your request
includes the Byte parameter.
List<E> errors
Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.
List<E> warnings
Warnings detected while processing the input document. The response includes a warning if there is a mismatch between the input document type and the model type associated with the endpoint that you specified. The response can also include warnings for individual pages that have a mismatch.
The field is empty if the system generated no warnings.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel of the flywheel to receive the data.
String datasetName
Name of the dataset.
String datasetType
The dataset type. You can specify that the data in a dataset is for training the model or for testing the model.
String description
Description of the dataset.
DatasetInputDataConfig inputDataConfig
Information about the input data configuration. The type of input data varies based on the format of the input and whether the data is for a classifier model or an entity recognition model.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
List<E> tags
Tags for the dataset.
String datasetArn
The ARN of the dataset.
String documentClassifierName
The name of the document classifier.
String versionName
The version name given to the newly created classifier. Version names can have a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same classifier name in the Amazon Web Services account/Amazon Web Services Region.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
List<E> tags
Tags to associate with the document classifier. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
DocumentClassifierInputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
DocumentClassifierOutputDataConfig outputDataConfig
Specifies the location for the output files from a custom classifier job. This parameter is required for a request that creates a native document model.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String languageCode
The language of the input documents. You can specify any of the languages supported by Amazon Comprehend. All documents must be in the same language.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC.
String mode
Indicates the mode in which the classifier will be trained. The classifier can be trained in multi-class (single-label) mode or multi-label mode. Multi-class mode identifies a single class label for each document and multi-label mode identifies one or more class labels for each document. Multiple labels for an individual document are separated by a delimiter. The default delimiter between labels is a pipe (|).
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String modelPolicy
The resource-based policy to attach to your custom document classifier model. You can use this policy to allow another Amazon Web Services account to import your custom model.
Provide your policy as a JSON body that you enter as a UTF-8 encoded string without line breaks. To provide valid JSON, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:
"{\"attribute\": \"value\", \"attribute\": [\"value\"]}"
To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:
'{"attribute": "value", "attribute": ["value"]}'
String documentClassifierArn
The Amazon Resource Name (ARN) that identifies the document classifier.
String endpointName
This is the descriptive suffix that becomes part of the EndpointArn used for all subsequent requests
to this resource.
String modelArn
The Amazon Resource Number (ARN) of the model to which the endpoint will be attached.
Integer desiredInferenceUnits
The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
String clientRequestToken
An idempotency token provided by the customer. If this token matches a previous endpoint creation request, Amazon
Comprehend will not return a ResourceInUseException.
List<E> tags
Tags to associate with the endpoint. A tag is a key-value pair that adds metadata to the endpoint. For example, a tag with "Sales" as the key might be added to an endpoint to indicate its use by the sales department.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel to which the endpoint will be attached.
String recognizerName
The name given to the newly created recognizer. Recognizer names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The name must be unique in the account/Region.
String versionName
The version name given to the newly created recognizer. Version names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same recognizer name in the account/Region.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
List<E> tags
Tags to associate with the entity recognizer. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
EntityRecognizerInputDataConfig inputDataConfig
Specifies the format and location of the input data. The S3 bucket containing the input data must be located in the same Region as the entity recognizer being created.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String languageCode
You can specify any of the following languages: English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), German ("de"), or Portuguese ("pt"). If you plan to use this entity recognizer with PDF, Word, or image input files, you must specify English as the language. All training documents must be in the same language.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC.
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String modelPolicy
The JSON resource-based policy to attach to your custom entity recognizer model. You can use this policy to allow another Amazon Web Services account to import your custom model.
Provide your JSON as a UTF-8 encoded string without line breaks. To provide valid JSON for your policy, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:
"{\"attribute\": \"value\", \"attribute\": [\"value\"]}"
To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:
'{"attribute": "value", "attribute": ["value"]}'
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the entity recognizer.
String flywheelName
Name for the flywheel.
String activeModelArn
To associate an existing model with the flywheel, specify the Amazon Resource Number (ARN) of the model version.
Do not set TaskConfig or ModelType if you specify an ActiveModelArn.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend the permissions required to access the flywheel data in the data lake.
TaskConfig taskConfig
Configuration about the model associated with the flywheel. You need to set TaskConfig if you are
creating a flywheel for a new model.
String modelType
The model type. You need to set ModelType if you are creating a flywheel for a new model.
String dataLakeS3Uri
Enter the S3 location for the data lake. You can specify a new S3 bucket or a new folder of an existing S3 bucket. The flywheel creates the data lake at this location.
DataSecurityConfig dataSecurityConfig
Data security configurations.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
List<E> tags
The tags to associate with this flywheel.
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String volumeKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt the volume.
String dataLakeKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt the data in the data lake.
VpcConfig vpcConfig
List<E> attributeNames
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.
String s3Uri
The Amazon S3 location of the augmented manifest file.
String annotationDataS3Uri
The S3 prefix to the annotation files that are referred in the augmented manifest file.
String sourceDocumentsS3Uri
The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file.
String documentType
The type of augmented manifest. If you don't specify, the default is PlainTextDocument.
PLAIN_TEXT_DOCUMENT A document type that represents any unicode text that is encoded in UTF-8.
String s3Uri
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 point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix, if the 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.
String labelDelimiter
Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
String s3Uri
Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
String s3Uri
Specifies the Amazon S3 location where the documents for the dataset are located.
String inputFormat
Specifies how the text in an input file should be processed. This is optional, and the default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.
String s3Uri
Specifies the Amazon S3 location where the entity list is located.
DatasetEntityRecognizerAnnotations annotations
The S3 location of the annotation documents for your custom entity recognizer.
DatasetEntityRecognizerDocuments documents
The format and location of the training documents for your custom entity recognizer.
DatasetEntityRecognizerEntityList entityList
The S3 location of the entity list for your custom entity recognizer.
String status
Filter the datasets based on the dataset status.
String datasetType
Filter the datasets based on the dataset type.
Date creationTimeAfter
Filter the datasets to include datasets created after the specified time.
Date creationTimeBefore
Filter the datasets to include datasets created before the specified time.
List<E> augmentedManifests
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.
String dataFormat
COMPREHEND_CSV: The data format is a two-column CSV file, where the first column contains labels and
the second column contains documents.
AUGMENTED_MANIFEST: The data format
DatasetDocumentClassifierInputDataConfig documentClassifierInputDataConfig
The input properties for training a document classifier model.
For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.
DatasetEntityRecognizerInputDataConfig entityRecognizerInputDataConfig
The input properties for training an entity recognizer model.
String datasetArn
The ARN of the dataset.
String datasetName
The name of the dataset.
String datasetType
The dataset type (training data or test data).
String datasetS3Uri
The S3 URI where the dataset is stored.
String description
Description of the dataset.
String status
The dataset status. While the system creates the dataset, the status is CREATING. When the dataset
is ready to use, the status changes to COMPLETED.
String message
A description of the status of the dataset.
Long numberOfDocuments
The number of documents in the dataset.
Date creationTime
Creation time of the dataset.
Date endTime
Time when the data from the dataset becomes available in the data lake.
String documentClassifierArn
The Amazon Resource Name (ARN) that identifies the document classifier.
String endpointArn
The Amazon Resource Number (ARN) of the endpoint being deleted.
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the entity recognizer.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel to delete.
String datasetArn
The ARN of the dataset.
DatasetProperties datasetProperties
The dataset properties.
String jobId
The identifier that Amazon Comprehend generated for the job. The StartDocumentClassificationJob
operation returns this identifier in its response.
DocumentClassificationJobProperties documentClassificationJobProperties
An object that describes the properties associated with the document classification job.
String documentClassifierArn
The Amazon Resource Name (ARN) that identifies the document classifier. The CreateDocumentClassifier
operation returns this identifier in its response.
DocumentClassifierProperties documentClassifierProperties
An object that contains the properties associated with a document classifier.
String jobId
The identifier that Amazon Comprehend generated for the job. The StartDominantLanguageDetectionJob
operation returns this identifier in its response.
DominantLanguageDetectionJobProperties dominantLanguageDetectionJobProperties
An object that contains the properties associated with a dominant language detection job.
String endpointArn
The Amazon Resource Number (ARN) of the endpoint being described.
EndpointProperties endpointProperties
Describes information associated with the specific endpoint.
String jobId
The identifier that Amazon Comprehend generated for the job. The StartEntitiesDetectionJob operation
returns this identifier in its response.
EntitiesDetectionJobProperties entitiesDetectionJobProperties
An object that contains the properties associated with an entities detection job.
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the entity recognizer.
EntityRecognizerProperties entityRecognizerProperties
Describes information associated with an entity recognizer.
String jobId
The identifier of the events detection job.
EventsDetectionJobProperties eventsDetectionJobProperties
An object that contains the properties associated with an event detection job.
FlywheelIterationProperties flywheelIterationProperties
The configuration properties of a flywheel iteration.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel.
FlywheelProperties flywheelProperties
The flywheel properties.
String jobId
The identifier that Amazon Comprehend generated for the job. The StartKeyPhrasesDetectionJob
operation returns this identifier in its response.
KeyPhrasesDetectionJobProperties keyPhrasesDetectionJobProperties
An object that contains the properties associated with a key phrases detection job.
String jobId
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
PiiEntitiesDetectionJobProperties piiEntitiesDetectionJobProperties
String resourceArn
The Amazon Resource Name (ARN) of the custom model version that has the resource policy.
String resourcePolicy
The JSON body of the resource-based policy.
Date creationTime
The time at which the policy was created.
Date lastModifiedTime
The time at which the policy was last modified.
String policyRevisionId
The revision ID of the policy. Each time you modify a policy, Amazon Comprehend assigns a new revision ID, and it deletes the prior version of the policy.
String jobId
The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.
SentimentDetectionJobProperties sentimentDetectionJobProperties
An object that contains the properties associated with a sentiment detection job.
String jobId
The identifier that Amazon Comprehend generated for the job. The StartTargetedSentimentDetectionJob
operation returns this identifier in its response.
TargetedSentimentDetectionJobProperties targetedSentimentDetectionJobProperties
An object that contains the properties associated with a targeted sentiment detection job.
String jobId
The identifier assigned by the user to the detection job.
TopicsDetectionJobProperties topicsDetectionJobProperties
The list of properties for the requested job.
String text
A UTF-8 text string. The string must contain at least 20 characters. The maximum string size is 100 KB.
List<E> languages
Array of languages that Amazon Comprehend detected in the input text. The array is sorted in descending order of the score (the dominant language is always the first element in the array).
For each language, the response returns the RFC 5646 language code and the level of confidence that Amazon Comprehend has in the accuracy of its inference. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
String text
A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter, do not use the
Bytes parameter.
String languageCode
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. If your request includes the endpoint for a custom entity recognition model, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you specify here.
All input documents must be in the same language.
String endpointArn
The Amazon Resource Name of an endpoint that is associated with a custom entity recognition model. Provide an endpoint if you want to detect entities by using your own custom model instead of the default model that is used by Amazon Comprehend.
If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you provide in your request.
For information about endpoints, see Managing endpoints.
ByteBuffer bytes
This field applies only when you use a custom entity recognition model that was trained with PDF annotations. For
other cases, enter your text input in the Text field.
Use the Bytes parameter to input a text, PDF, Word or image file. Using a plain-text file in the
Bytes parameter is equivelent to using the Text parameter (the Entities
field in the response is identical).
You can also use the Bytes parameter to input an Amazon Textract DetectDocumentText or
AnalyzeDocument output file.
Provide the input document as a sequence of base64-encoded bytes. If your code uses an Amazon Web Services SDK to detect entities, the SDK may encode the document file bytes for you.
The maximum length of this field depends on the input document type. For details, see Inputs for real-time custom analysis in the Comprehend Developer Guide.
If you use the Bytes parameter, do not use the Text parameter.
DocumentReaderConfig documentReaderConfig
Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
List<E> entities
A collection of entities identified in the input text. For each entity, the response provides the entity text, entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.
If your request uses a custom entity recognition model, Amazon Comprehend detects the entities that the model is trained to recognize. Otherwise, it detects the default entity types. For a list of default entity types, see Entities in the Comprehend Developer Guide.
DocumentMetadata documentMetadata
Information about the document, discovered during text extraction. This field is present in the response only if
your request used the Byte parameter.
List<E> documentType
The document type for each page in the input document. This field is present in the response only if your request
used the Byte parameter.
List<E> blocks
Information about each block of text in the input document. Blocks are nested. A page block contains a block for each line of text, which contains a block for each word.
The Block content for a Word input document does not include a Geometry field.
The Block field is not present in the response for plain-text inputs.
List<E> errors
Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.
List<E> keyPhrases
A collection of key phrases that Amazon Comprehend identified in the input text. For each key phrase, the response provides the text of the key phrase, where the key phrase begins and ends, and the level of confidence that Amazon Comprehend has in the accuracy of the detection.
String sentiment
The inferred sentiment that Amazon Comprehend has the highest level of confidence in.
SentimentScore sentimentScore
An object that lists the sentiments, and their corresponding confidence levels.
String text
A UTF-8 string. The maximum string size is 5 KB.
String languageCode
The language code of the input documents. You can specify any of the following languages supported by Amazon Comprehend: German ("de"), English ("en"), Spanish ("es"), French ("fr"), Italian ("it"), or Portuguese ("pt").
List<E> syntaxTokens
A collection of syntax tokens describing the text. For each token, the response provides the text, the token type, where the text begins and ends, and the level of confidence that Amazon Comprehend has that the token is correct. For a list of token types, see Syntax in the Comprehend Developer Guide.
List<E> resultList
Results of the content moderation analysis. Each entry in the results list contains a list of toxic content types identified in the text, along with a confidence score for each content type. The results list also includes a toxicity score for each entry in the results list.
String jobName
Filters on the name of the job.
String jobStatus
Filters the list based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the document classification job.
String jobArn
The Amazon Resource Name (ARN) of the document classification job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:document-classification-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned to the document classification job.
String jobStatus
The current status of the document classification job. If the status is FAILED, the
Message field shows the reason for the failure.
String message
A description of the status of the job.
Date submitTime
The time that the document classification job was submitted for processing.
Date endTime
The time that the document classification job completed.
String documentClassifierArn
The Amazon Resource Name (ARN) that identifies the document classifier.
InputDataConfig inputDataConfig
The input data configuration that you supplied when you created the document classification job.
OutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the document classification job.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. For more information, see Amazon VPC.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel
String status
Filters the list of classifiers based on status.
String documentClassifierName
The name that you assigned to the document classifier
Date submitTimeBefore
Filters the list of classifiers based on the time that the classifier was submitted for processing. Returns only classifiers submitted before the specified time. Classifiers are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of classifiers based on the time that the classifier was submitted for processing. Returns only classifiers submitted after the specified time. Classifiers are returned in descending order, newest to oldest.
String dataFormat
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.
String s3Uri
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 point to a single input file or it can provide the prefix for a collection of input files.
For example, if you use the URI S3://bucketName/prefix, if the 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.
String testS3Uri
This specifies the Amazon S3 location that contains the test annotations for the document classifier. The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling.
String labelDelimiter
Indicates the delimiter used to separate each label for training a multi-label classifier. The default delimiter between labels is a pipe (|). You can use a different character as a delimiter (if it's an allowed character) by specifying it under Delimiter for labels. If the training documents use a delimiter other than the default or the delimiter you specify, the labels on that line will be combined to make a single unique label, such as LABELLABELLABEL.
List<E> augmentedManifests
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.
String documentType
The type of input documents for training the model. Provide plain-text documents to create a plain-text model, and provide semi-structured documents to create a native document model.
DocumentClassifierDocuments documents
The S3 location of the training documents. This parameter is required in a request to create a native document model.
DocumentReaderConfig documentReaderConfig
String s3Uri
When you use the OutputDataConfig object while creating a custom classifier, you specify the Amazon
S3 location where you want to write the confusion matrix and other output files. The URI must be in the same
Region as the API endpoint that you are calling. The location is used as the prefix for the actual location of
this output file.
When the custom classifier job is finished, the service creates the output file in a directory specific to the
job. The S3Uri field contains the location of the output file, called output.tar.gz. It
is a compressed archive that contains the confusion matrix.
String kmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. The KmsKeyId can be one of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
ARN of a KMS Key Alias: "arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
String flywheelStatsS3Prefix
The Amazon S3 prefix for the data lake location of the flywheel statistics.
String documentClassifierArn
The Amazon Resource Name (ARN) that identifies the document classifier.
String languageCode
The language code for the language of the documents that the classifier was trained on.
String status
The status of the document classifier. If the status is TRAINED the classifier is ready to use. If
the status is TRAINED_WITH_WARNINGS the classifier training succeeded, but you should review the
warnings returned in the CreateDocumentClassifier response.
If the status is FAILED you can see additional information about why the classifier wasn't trained
in the Message field.
String message
Additional information about the status of the classifier.
Date submitTime
The time that the document classifier was submitted for training.
Date endTime
The time that training the document classifier completed.
Date trainingStartTime
Indicates the time when the training starts on documentation classifiers. You are billed for the time interval between this time and the value of TrainingEndTime.
Date trainingEndTime
The time that training of the document classifier was completed. Indicates the time when the training completes on documentation classifiers. You are billed for the time interval between this time and the value of TrainingStartTime.
DocumentClassifierInputDataConfig inputDataConfig
The input data configuration that you supplied when you created the document classifier for training.
DocumentClassifierOutputDataConfig outputDataConfig
Provides output results configuration parameters for custom classifier jobs.
ClassifierMetadata classifierMetadata
Information about the document classifier, including the number of documents used for training the classifier, the number of documents used for test the classifier, and an accuracy rating.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom classifier. For more information, see Amazon VPC.
String mode
Indicates the mode in which the specific classifier was trained. This also indicates the format of input documents and the format of the confusion matrix. Each classifier can only be trained in one mode and this cannot be changed once the classifier is trained.
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String versionName
The version name that you assigned to the document classifier.
String sourceModelArn
The Amazon Resource Name (ARN) of the source model. This model was imported from a different Amazon Web Services account to create the document classifier model in your Amazon Web Services account.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel
String documentClassifierName
The name that you assigned the document classifier.
Integer numberOfVersions
The number of versions you created.
Date latestVersionCreatedAt
The time that the latest document classifier version was submitted for processing.
String latestVersionName
The version name you assigned to the latest document classifier version.
String latestVersionStatus
Provides the status of the latest document classifier version.
String documentReadAction
This field defines the Amazon Textract API operation that Amazon Comprehend uses to extract text from PDF files and image files. Enter one of the following values:
TEXTRACT_DETECT_DOCUMENT_TEXT - The Amazon Comprehend service uses the
DetectDocumentText API operation.
TEXTRACT_ANALYZE_DOCUMENT - The Amazon Comprehend service uses the AnalyzeDocument API
operation.
String documentReadMode
Determines the text extraction actions for PDF files. Enter one of the following values:
SERVICE_DEFAULT - use the Amazon Comprehend service defaults for PDF files.
FORCE_DOCUMENT_READ_ACTION - Amazon Comprehend uses the Textract API specified by DocumentReadAction
for all PDF files, including digital PDF files.
List<E> featureTypes
Specifies the type of Amazon Textract features to apply. If you chose TEXTRACT_ANALYZE_DOCUMENT as
the read action, you must specify one or both of the following values:
TABLES - Returns additional information about any tables that are detected in the input document.
FORMS - Returns additional information about any forms that are detected in the input document.
String languageCode
The RFC 5646 language code for the dominant language. For more information about RFC 5646, see Tags for Identifying Languages on the IETF Tools web site.
Float score
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
String jobName
Filters on the name of the job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the dominant language detection job.
String jobArn
The Amazon Resource Name (ARN) of the dominant language detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:dominant-language-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned to the dominant language detection job.
String jobStatus
The current status of the dominant language detection job. If the status is FAILED, the
Message field shows the reason for the failure.
String message
A description for the status of a job.
Date submitTime
The time that the dominant language detection job was submitted for processing.
Date endTime
The time that the dominant language detection job completed.
InputDataConfig inputDataConfig
The input data configuration that you supplied when you created the dominant language detection job.
OutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the dominant language detection job.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. For more information, see Amazon VPC.
String modelArn
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
String status
Specifies the status of the endpoint being returned. Possible values are: Creating, Ready, Updating, Deleting, Failed.
Date creationTimeBefore
Specifies a date before which the returned endpoint or endpoints were created.
Date creationTimeAfter
Specifies a date after which the returned endpoint or endpoints were created.
String endpointArn
The Amazon Resource Number (ARN) of the endpoint.
String status
Specifies the status of the endpoint. Because the endpoint updates and creation are asynchronous, so customers
will need to wait for the endpoint to be Ready status before making inference requests.
String message
Specifies a reason for failure in cases of Failed status.
String modelArn
The Amazon Resource Number (ARN) of the model to which the endpoint is attached.
String desiredModelArn
ARN of the new model to use for updating an existing endpoint. This ARN is going to be different from the model ARN when the update is in progress
Integer desiredInferenceUnits
The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
Integer currentInferenceUnits
The number of inference units currently used by the model using this endpoint.
Date creationTime
The creation date and time of the endpoint.
Date lastModifiedTime
The date and time that the endpoint was last modified.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).
String desiredDataAccessRoleArn
Data access role ARN to use in case the new model is encrypted with a customer KMS key.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel
String jobName
Filters on the name of the job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the entities detection job.
String jobArn
The Amazon Resource Name (ARN) of the entities detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:entities-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned the entities detection job.
String jobStatus
The current status of the entities detection job. If the status is FAILED, the Message
field shows the reason for the failure.
String message
A description of the status of a job.
Date submitTime
The time that the entities detection job was submitted for processing.
Date endTime
The time that the entities detection job completed
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the entity recognizer.
InputDataConfig inputDataConfig
The input data configuration that you supplied when you created the entities detection job.
OutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the entities detection job.
String languageCode
The language code of the input documents.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC.
String flywheelArn
The Amazon Resource Name (ARN) of the flywheel associated with this job.
Float score
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
String type
The entity type. For entity detection using the built-in model, this field contains one of the standard entity types listed below.
For custom entity detection, this field contains one of the entity types that you specified when you trained your custom model.
String text
The text of the entity.
Integer beginOffset
The zero-based offset from the beginning of the source text to the first character in the entity.
This field is empty for non-text input.
Integer endOffset
The zero-based offset from the beginning of the source text to the last character in the entity.
This field is empty for non-text input.
List<E> blockReferences
A reference to each block for this entity. This field is empty for plain-text input.
String s3Uri
Specifies the Amazon S3 location where the annotations for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
String testS3Uri
Specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
String s3Uri
Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling.
String testS3Uri
Specifies the Amazon S3 location where the test documents for an entity recognizer are located. The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling.
String inputFormat
Specifies how the text in an input file should be processed. This is optional, and the default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.
String s3Uri
Specifies the Amazon S3 location where the entity list is located. The URI must be in the same Region as the API endpoint that you are calling.
Double precision
A measure of the usefulness of the recognizer results in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
Double recall
A measure of how complete the recognizer results are for the test data. High recall means that the recognizer returned most of the relevant results.
Double f1Score
A measure of how accurate the recognizer results are for the test data. It is derived from the
Precision and Recall values. The F1Score is the harmonic average of the
two scores. For plain text entity recognizer models, the range is 0 to 100, where 100 is the best score. For
PDF/Word entity recognizer models, the range is 0 to 1, where 1 is the best score.
String status
The status of an entity recognizer.
String recognizerName
The name that you assigned the entity recognizer.
Date submitTimeBefore
Filters the list of entities based on the time that the list was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
Date submitTimeAfter
Filters the list of entities based on the time that the list was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
String dataFormat
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.
List<E> entityTypes
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).
EntityRecognizerDocuments documents
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.
EntityRecognizerAnnotations annotations
The S3 location of the CSV file that annotates your training documents.
EntityRecognizerEntityList entityList
The S3 location of the CSV file that has the entity list for your custom entity recognizer.
List<E> augmentedManifests
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.
Integer numberOfTrainedDocuments
The number of documents in the input data that were used to train the entity recognizer. Typically this is 80 to 90 percent of the input documents.
Integer numberOfTestDocuments
The number of documents in the input data that were used to test the entity recognizer. Typically this is 10 to 20 percent of the input documents.
EntityRecognizerEvaluationMetrics evaluationMetrics
Detailed information about the accuracy of an entity recognizer.
List<E> entityTypes
Entity types from the metadata of an entity recognizer.
String type
Type of entity from the list of entity types in the metadata of an entity recognizer.
EntityTypesEvaluationMetrics evaluationMetrics
Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.
Integer numberOfTrainMentions
Indicates the number of times the given entity type was seen in the training data.
String flywheelStatsS3Prefix
The Amazon S3 prefix for the data lake location of the flywheel statistics.
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the entity recognizer.
String languageCode
The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.
String status
Provides the status of the entity recognizer.
String message
A description of the status of the recognizer.
Date submitTime
The time that the recognizer was submitted for processing.
Date endTime
The time that the recognizer creation completed.
Date trainingStartTime
The time that training of the entity recognizer started.
Date trainingEndTime
The time that training of the entity recognizer was completed.
EntityRecognizerInputDataConfig inputDataConfig
The input data properties of an entity recognizer.
EntityRecognizerMetadata recognizerMetadata
Provides information about an entity recognizer.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your custom entity recognizer. For more information, see Amazon VPC.
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String versionName
The version name you assigned to the entity recognizer.
String sourceModelArn
The Amazon Resource Name (ARN) of the source model. This model was imported from a different Amazon Web Services account to create the entity recognizer model in your Amazon Web Services account.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel
EntityRecognizerOutputDataConfig outputDataConfig
Output data configuration.
String recognizerName
The name that you assigned the entity recognizer.
Integer numberOfVersions
The number of versions you created.
Date latestVersionCreatedAt
The time that the latest entity recognizer version was submitted for processing.
String latestVersionName
The version name you assigned to the latest entity recognizer version.
String latestVersionStatus
Provides the status of the latest entity recognizer version.
Double precision
A measure of the usefulness of the recognizer results for a specific entity type in the test data. High precision means that the recognizer returned substantially more relevant results than irrelevant ones.
Double recall
A measure of how complete the recognizer results are for a specific entity type in the test data. High recall means that the recognizer returned most of the relevant results.
Double f1Score
A measure of how accurate the recognizer results are for a specific entity type in the test data. It is derived
from the Precision and Recall values. The F1Score is the harmonic average
of the two scores. The highest score is 1, and the worst score is 0.
String type
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), and , (comma).
String jobName
Filters on the name of the events detection job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the events detection job.
String jobArn
The Amazon Resource Name (ARN) of the events detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:events-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:events-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name you assigned the events detection job.
String jobStatus
The current status of the events detection job.
String message
A description of the status of the events detection job.
Date submitTime
The time that the events detection job was submitted for processing.
Date endTime
The time that the events detection job completed.
InputDataConfig inputDataConfig
The input data configuration that you supplied when you created the events detection job.
OutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the events detection job.
String languageCode
The language code of the input documents.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
List<E> targetEventTypes
The types of events that are detected by the job.
String status
Filter the flywheels based on the flywheel status.
Date creationTimeAfter
Filter the flywheels to include flywheels created after the specified time.
Date creationTimeBefore
Filter the flywheels to include flywheels created before the specified time.
String flywheelArn
String flywheelIterationId
Date creationTime
The creation start time of the flywheel iteration.
Date endTime
The completion time of this flywheel iteration.
String status
The status of the flywheel iteration.
String message
A description of the status of the flywheel iteration.
String evaluatedModelArn
The ARN of the evaluated model associated with this flywheel iteration.
FlywheelModelEvaluationMetrics evaluatedModelMetrics
String trainedModelArn
The ARN of the trained model associated with this flywheel iteration.
FlywheelModelEvaluationMetrics trainedModelMetrics
The metrics associated with the trained model.
String evaluationManifestS3Prefix
Double averageF1Score
The average F1 score from the evaluation metrics.
Double averagePrecision
Average precision metric for the model.
Double averageRecall
Average recall metric for the model.
Double averageAccuracy
Average accuracy metric for the model.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel.
String activeModelArn
The Amazon Resource Number (ARN) of the active model version.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to access the flywheel data.
TaskConfig taskConfig
Configuration about the model associated with a flywheel.
String dataLakeS3Uri
Amazon S3 URI of the data lake location.
DataSecurityConfig dataSecurityConfig
Data security configuration.
String status
The status of the flywheel.
String modelType
Model type of the flywheel's model.
String message
A description of the status of the flywheel.
Date creationTime
Creation time of the flywheel.
Date lastModifiedTime
Last modified time for the flywheel.
String latestFlywheelIteration
The most recent flywheel iteration.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel
String activeModelArn
ARN of the active model version for the flywheel.
String dataLakeS3Uri
Amazon S3 URI of the data lake location.
String status
The status of the flywheel.
String modelType
Model type of the flywheel's model.
String message
A description of the status of the flywheel.
Date creationTime
Creation time of the flywheel.
Date lastModifiedTime
Last modified time for the flywheel.
String latestFlywheelIteration
The most recent flywheel iteration.
BoundingBox boundingBox
An axis-aligned coarse representation of the location of the recognized item on the document page.
List<E> polygon
Within the bounding box, a fine-grained polygon around the recognized item.
String sourceModelArn
The Amazon Resource Name (ARN) of the custom model to import.
String modelName
The name to assign to the custom model that is created in Amazon Comprehend by this import.
String versionName
The version name given to the custom model that is created by this import. Version names can have a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same classifier name in the account/Region.
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to use Amazon Key Management Service (KMS) to encrypt or decrypt the custom model.
List<E> tags
Tags to associate with the custom model that is created by this import. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String modelArn
The Amazon Resource Name (ARN) of the custom model being imported.
String s3Uri
The Amazon S3 URI for the input data. The URI must be in same Region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of data files.
For example, if you use the URI S3://bucketName/prefix, if the 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.
String inputFormat
Specifies how the text in an input file should be processed:
ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are
processing large documents, such as newspaper articles or scientific papers.
ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you
are processing many short documents, such as text messages.
DocumentReaderConfig documentReaderConfig
Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
String reason
Reason codes include the following values:
DOCUMENT_SIZE_EXCEEDED - Document size is too large. Check the size of your file and resubmit the request.
UNSUPPORTED_DOC_TYPE - Document type is not supported. Check the file type and resubmit the request.
PAGE_LIMIT_EXCEEDED - Too many pages in the document. Check the number of pages in your file and resubmit the request.
TEXTRACT_ACCESS_DENIED - Access denied to Amazon Textract. Verify that your account has permission to use Amazon Textract API operations and resubmit the request.
NOT_TEXTRACT_JSON - Document is not Amazon Textract JSON format. Verify the format and resubmit the request.
MISMATCHED_TOTAL_PAGE_COUNT - Check the number of pages in your file and resubmit the request.
INVALID_DOCUMENT - Invalid document. Check the file and resubmit the request.
String reason
InvalidRequestDetail detail
Float score
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
String text
The text of a key noun phrase.
Integer beginOffset
The zero-based offset from the beginning of the source text to the first character in the key phrase.
Integer endOffset
The zero-based offset from the beginning of the source text to the last character in the key phrase.
String jobName
Filters on the name of the job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the key phrases detection job.
String jobArn
The Amazon Resource Name (ARN) of the key phrases detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:key-phrases-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned the key phrases detection job.
String jobStatus
The current status of the key phrases detection job. If the status is FAILED, the
Message field shows the reason for the failure.
String message
A description of the status of a job.
Date submitTime
The time that the key phrases detection job was submitted for processing.
Date endTime
The time that the key phrases detection job completed.
InputDataConfig inputDataConfig
The input data configuration that you supplied when you created the key phrases detection job.
OutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the key phrases detection job.
String languageCode
The language code of the input documents.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. For more information, see Amazon VPC.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel.
DatasetFilter filter
Filters the datasets to be returned in the response.
String nextToken
Identifies the next page of results to return.
Integer maxResults
Maximum number of results to return in a response. The default is 100.
DocumentClassificationJobFilter filter
Filters the jobs that are returned. You can filter jobs on their names, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
DocumentClassifierFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
DominantLanguageDetectionJobFilter filter
Filters that jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
EndpointFilter filter
Filters the endpoints that are returned. You can filter endpoints on their name, model, status, or the date and time that they were created. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
EntitiesDetectionJobFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
EntityRecognizerFilter filter
Filters the list of entities returned. You can filter on Status, SubmitTimeBefore, or
SubmitTimeAfter. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return on each page. The default is 100.
EventsDetectionJobFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page.
String flywheelArn
The ARN of the flywheel.
FlywheelIterationFilter filter
Filter the flywheel iteration history based on creation time.
String nextToken
Next token
Integer maxResults
Maximum number of iteration history results to return
FlywheelFilter filter
Filters the flywheels that are returned. You can filter flywheels on their status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
Maximum number of results to return in a response. The default is 100.
KeyPhrasesDetectionJobFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
PiiEntitiesDetectionJobFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page.
SentimentDetectionJobFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
String resourceArn
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.
String resourceArn
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.
List<E> tags
Tags associated with the Amazon Comprehend resource being queried. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
TargetedSentimentDetectionJobFilter filter
Filters the jobs that are returned. You can filter jobs on their name, status, or the date and time that they were submitted. You can only set one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
TopicsDetectionJobFilter filter
Filters the jobs that are returned. Jobs can be filtered on their name, status, or the date and time that they were submitted. You can set only one filter at a time.
String nextToken
Identifies the next page of results to return.
Integer maxResults
The maximum number of results to return in each page. The default is 100.
String sentiment
The sentiment of the mention.
SentimentScore sentimentScore
String s3Uri
When you use the OutputDataConfig object with asynchronous operations, you specify the Amazon S3
location where you want to write the output data. The URI must be in the same Region as the API endpoint that you
are calling. The location is used as the prefix for the actual location of the output file.
When the topic detection job is finished, the service creates an output file in a directory specific to the job.
The S3Uri field contains the location of the output file, called output.tar.gz. It is a
compressed archive that contains the ouput of the operation.
For a PII entity detection job, the output file is plain text, not a compressed archive. The output file name is
the same as the input file, with .out appended at the end.
String kmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. Specify the Key Id of a symmetric key, because you cannot use an asymmetric key for uploading data to S3.
The KmsKeyId can be one of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS Key Alias: "alias/ExampleAlias"
ARN of a KMS Key Alias: "arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
String jobName
Filters on the name of the job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the PII entities detection job.
String jobArn
The Amazon Resource Name (ARN) of the PII entities detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:pii-entities-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned the PII entities detection job.
String jobStatus
The current status of the PII entities detection job. If the status is FAILED, the
Message field shows the reason for the failure.
String message
A description of the status of a job.
Date submitTime
The time that the PII entities detection job was submitted for processing.
Date endTime
The time that the PII entities detection job completed.
InputDataConfig inputDataConfig
The input properties for a PII entities detection job.
PiiOutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the PII entities detection job.
RedactionConfig redactionConfig
Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION. In that
case, you must provide a RedactionConfig definition that includes the PiiEntityTypes
parameter.
String languageCode
The language code of the input documents.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String mode
Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
Float score
The level of confidence that Amazon Comprehend has in the accuracy of the detection.
String type
The entity's type.
Integer beginOffset
The zero-based offset from the beginning of the source text to the first character in the entity.
Integer endOffset
The zero-based offset from the beginning of the source text to the last character in the entity.
String s3Uri
When you use the PiiOutputDataConfig object with asynchronous operations, you specify the Amazon S3
location where you want to write the output data.
For a PII entity detection job, the output file is plain text, not a compressed archive. The output file name is
the same as the input file, with .out appended at the end.
String kmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job.
String resourceArn
The Amazon Resource Name (ARN) of the custom model to attach the policy to.
String resourcePolicy
The JSON resource-based policy to attach to your custom model. Provide your JSON as a UTF-8 encoded string without line breaks. To provide valid JSON for your policy, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:
"{\"attribute\": \"value\", \"attribute\": [\"value\"]}"
To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:
'{"attribute": "value", "attribute": ["value"]}'
String policyRevisionId
The revision ID that Amazon Comprehend assigned to the policy that you are updating. If you are creating a new policy that has no prior version, don't use this parameter. Amazon Comprehend creates the revision ID for you.
String policyRevisionId
The revision ID of the policy. Each time you modify a policy, Amazon Comprehend assigns a new revision ID, and it deletes the prior version of the policy.
List<E> piiEntityTypes
An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.
String maskMode
Specifies whether the PII entity is redacted with the mask character or the entity type.
String maskCharacter
A character that replaces each character in the redacted PII entity.
String jobName
Filters on the name of the job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the sentiment detection job.
String jobArn
The Amazon Resource Name (ARN) of the sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:sentiment-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned to the sentiment detection job
String jobStatus
The current status of the sentiment detection job. If the status is FAILED, the
Messages field shows the reason for the failure.
String message
A description of the status of a job.
Date submitTime
The time that the sentiment detection job was submitted for processing.
Date endTime
The time that the sentiment detection job ended.
InputDataConfig inputDataConfig
The input data configuration that you supplied when you created the sentiment detection job.
OutputDataConfig outputDataConfig
The output data configuration that you supplied when you created the sentiment detection job.
String languageCode
The language code of the input documents.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. For more information, see Amazon VPC.
Float positive
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE
sentiment.
Float negative
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE
sentiment.
Float neutral
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL
sentiment.
Float mixed
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED
sentiment.
String jobName
The identifier of the job.
String documentClassifierArn
The Amazon Resource Name (ARN) of the document classifier to use to process the job.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String clientRequestToken
A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your document classification job. For more information, see Amazon VPC.
List<E> tags
Tags to associate with the document classification job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel associated with the model to use.
String jobId
The identifier generated for the job. To get the status of the job, use this identifier with the
DescribeDocumentClassificationJob operation.
String jobArn
The Amazon Resource Name (ARN) of the document classification job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:document-classification-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job:
SUBMITTED - The job has been received and queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. For details, use the DescribeDocumentClassificationJob operation.
STOP_REQUESTED - Amazon Comprehend has received a stop request for the job and is processing the request.
STOPPED - The job was successfully stopped without completing.
String documentClassifierArn
The ARN of the custom classification model.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
String jobName
An identifier for the job.
String clientRequestToken
A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your dominant language detection job. For more information, see Amazon VPC.
List<E> tags
Tags to associate with the dominant language detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
The identifier generated for the job. To get the status of a job, use this identifier with the operation.
String jobArn
The Amazon Resource Name (ARN) of the dominant language detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:dominant-language-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:dominant-language-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job.
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the operation.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
String jobName
The identifier of the job.
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the specific entity recognizer to be used by the
StartEntitiesDetectionJob. This ARN is optional and is only used for a custom entity recognition
job.
String languageCode
The language of the input documents. All documents must be in the same language. You can specify any of the languages supported by Amazon Comprehend. If custom entities recognition is used, this parameter is ignored and the language used for training the model is used instead.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your entity detection job. For more information, see Amazon VPC.
List<E> tags
Tags to associate with the entities detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel associated with the model to use.
String jobId
The identifier generated for the job. To get the status of job, use this identifier with the operation.
String jobArn
The Amazon Resource Name (ARN) of the entities detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:entities-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:entities-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job.
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the operation.
STOP_REQUESTED - Amazon Comprehend has received a stop request for the job and is processing the request.
STOPPED - The job was successfully stopped without completing.
String entityRecognizerArn
The ARN of the custom entity recognition model.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String jobName
The identifier of the events detection job.
String languageCode
The language code of the input documents.
String clientRequestToken
An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
List<E> targetEventTypes
The types of events to detect in the input documents.
List<E> tags
Tags to associate with the events detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String jobArn
The Amazon Resource Name (ARN) of the events detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:events-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:events-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the events detection job.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
String jobName
The identifier of the job.
String languageCode
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your key phrases detection job. For more information, see Amazon VPC.
List<E> tags
Tags to associate with the key phrases detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
The identifier generated for the job. To get the status of a job, use this identifier with the operation.
String jobArn
The Amazon Resource Name (ARN) of the key phrase detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:key-phrases-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:key-phrases-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job.
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the operation.
InputDataConfig inputDataConfig
The input properties for a PII entities detection job.
OutputDataConfig outputDataConfig
Provides configuration parameters for the output of PII entity detection jobs.
String mode
Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
RedactionConfig redactionConfig
Provides configuration parameters for PII entity redaction.
This parameter is required if you set the Mode parameter to ONLY_REDACTION. In that
case, you must provide a RedactionConfig definition that includes the PiiEntityTypes
parameter.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String jobName
The identifier of the job.
String languageCode
The language of the input documents. Enter the language code for English (en) or Spanish (es).
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
List<E> tags
Tags to associate with the PII entities detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
The identifier generated for the job.
String jobArn
The Amazon Resource Name (ARN) of the PII entity detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:pii-entities-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
String jobName
The identifier of the job.
String languageCode
The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. All documents must be in the same language.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your sentiment detection job. For more information, see Amazon VPC.
List<E> tags
Tags to associate with the sentiment detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
The identifier generated for the job. To get the status of a job, use this identifier with the operation.
String jobArn
The Amazon Resource Name (ARN) of the sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:sentiment-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job.
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the operation.
InputDataConfig inputDataConfig
OutputDataConfig outputDataConfig
Specifies where to send the output files.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
String jobName
The identifier of the job.
String languageCode
The language of the input documents. Currently, English is the only supported language.
String clientRequestToken
A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
List<E> tags
Tags to associate with the targeted sentiment detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
The identifier generated for the job. To get the status of a job, use this identifier with the
DescribeTargetedSentimentDetectionJob operation.
String jobArn
The Amazon Resource Name (ARN) of the targeted sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:targeted-sentiment-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job.
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the DescribeTargetedSentimentDetectionJob
operation.
InputDataConfig inputDataConfig
Specifies the format and location of the input data for the job.
OutputDataConfig outputDataConfig
Specifies where to send the output files. The output is a compressed archive with two files,
topic-terms.csv that lists the terms associated with each topic, and doc-topics.csv
that lists the documents associated with each topic
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data. For more information, see Role-based permissions.
String jobName
The identifier of the job.
Integer numberOfTopics
The number of topics to detect.
String clientRequestToken
A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. For more information, see Amazon VPC.
List<E> tags
Tags to associate with the topics detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
String jobId
The identifier generated for the job. To get the status of the job, use this identifier with the
DescribeTopicDetectionJob operation.
String jobArn
The Amazon Resource Name (ARN) of the topics detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:topics-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:document-classification-job/1234abcd12ab34cd56ef1234567890ab
String jobStatus
The status of the job:
SUBMITTED - The job has been received and is queued for processing.
IN_PROGRESS - Amazon Comprehend is processing the job.
COMPLETED - The job was successfully completed and the output is available.
FAILED - The job did not complete. To get details, use the DescribeTopicDetectionJob operation.
String jobId
The identifier of the dominant language detection job to stop.
String jobId
The identifier of the entities detection job to stop.
String jobId
The identifier of the events detection job to stop.
String jobId
The identifier of the key phrases detection job to stop.
String jobId
The identifier of the PII entities detection job to stop.
String jobId
The identifier of the sentiment detection job to stop.
String jobId
The identifier of the targeted sentiment detection job to stop.
String documentClassifierArn
The Amazon Resource Name (ARN) that identifies the document classifier currently being trained.
String entityRecognizerArn
The Amazon Resource Name (ARN) that identifies the entity recognizer currently being trained.
Integer tokenId
A unique identifier for a token.
String text
The word that was recognized in the source text.
Integer beginOffset
The zero-based offset from the beginning of the source text to the first character in the word.
Integer endOffset
The zero-based offset from the beginning of the source text to the last character in the word.
PartOfSpeechTag partOfSpeech
Provides the part of speech label and the confidence level that Amazon Comprehend has that the part of speech was correctly identified. For more information, see Syntax in the Comprehend Developer Guide.
String key
The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.”
String value
The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department.
String resourceArn
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource to which you want to associate the tags.
List<E> tags
Tags being associated with a specific Amazon Comprehend resource. There can be a maximum of 50 tags (both existing and pending) associated with a specific resource.
String jobName
Filters on the name of the job.
String jobStatus
Filters the list of jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted before the specified time. Jobs are returned in ascending order, oldest to newest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Returns only jobs submitted after the specified time. Jobs are returned in descending order, newest to oldest.
String jobId
The identifier assigned to the targeted sentiment detection job.
String jobArn
The Amazon Resource Name (ARN) of the targeted sentiment detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:targeted-sentiment-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:targeted-sentiment-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name that you assigned to the targeted sentiment detection job.
String jobStatus
The current status of the targeted sentiment detection job. If the status is FAILED, the
Messages field shows the reason for the failure.
String message
A description of the status of a job.
Date submitTime
The time that the targeted sentiment detection job was submitted for processing.
Date endTime
The time that the targeted sentiment detection job ended.
InputDataConfig inputDataConfig
OutputDataConfig outputDataConfig
String languageCode
The language code of the input documents.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
String volumeKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt the data on the storage volume attached to the ML compute instance(s) that process the targeted sentiment detection job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
List<E> descriptiveMentionIndex
One or more index into the Mentions array that provides the best name for the entity group.
List<E> mentions
An array of mentions of the entity in the document. The array represents a co-reference group. See Co-reference group for an example.
Float score
Model confidence that the entity is relevant. Value range is zero to one, where one is highest confidence.
Float groupScore
The confidence that all the entities mentioned in the group relate to the same entity.
String text
The text in the document that identifies the entity.
String type
The type of the entity. Amazon Comprehend supports a variety of entity types.
MentionSentiment mentionSentiment
Contains the sentiment and sentiment score for the mention.
Integer beginOffset
The offset into the document text where the mention begins.
Integer endOffset
The offset into the document text where the mention ends.
String languageCode
Language code for the language that the model supports.
DocumentClassificationConfig documentClassificationConfig
Configuration required for a document classification model.
EntityRecognitionConfig entityRecognitionConfig
Configuration required for an entity recognition model.
String text
The text content.
String jobName
String jobStatus
Filters the list of topic detection jobs based on job status. Returns only jobs with the specified status.
Date submitTimeBefore
Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted before the specified time. Jobs are returned in descending order, newest to oldest.
Date submitTimeAfter
Filters the list of jobs based on the time that the job was submitted for processing. Only returns jobs submitted after the specified time. Jobs are returned in ascending order, oldest to newest.
String jobId
The identifier assigned to the topic detection job.
String jobArn
The Amazon Resource Name (ARN) of the topics detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:
arn:<partition>:comprehend:<region>:<account-id>:topics-detection-job/<job-id>
The following is an example job ARN:
arn:aws:comprehend:us-west-2:111122223333:topics-detection-job/1234abcd12ab34cd56ef1234567890ab
String jobName
The name of the topic detection job.
String jobStatus
The current status of the topic detection job. If the status is Failed, the reason for the failure
is shown in the Message field.
String message
A description for the status of a job.
Date submitTime
The time that the topic detection job was submitted for processing.
Date endTime
The time that the topic detection job was completed.
InputDataConfig inputDataConfig
The input data configuration supplied when you created the topic detection job.
OutputDataConfig outputDataConfig
The output data configuration supplied when you created the topic detection job.
Integer numberOfTopics
The number of topics to detect supplied when you created the topic detection job. The default is 10.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your job data.
String volumeKmsKeyId
ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
VpcConfig vpcConfig
Configuration parameters for a private Virtual Private Cloud (VPC) containing the resources you are using for your topic detection job. For more information, see Amazon VPC.
String resourceArn
The Amazon Resource Name (ARN) of the given Amazon Comprehend resource from which you want to remove the tags.
List<E> tagKeys
The initial part of a key-value pair that forms a tag being removed from a given resource. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department. Keys must be unique and cannot be duplicated for a particular resource.
String modelKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats:
KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS Key:
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
String volumeKmsKeyId
ID for the KMS key that Amazon Comprehend uses to encrypt the volume.
VpcConfig vpcConfig
String endpointArn
The Amazon Resource Number (ARN) of the endpoint being updated.
String desiredModelArn
The ARN of the new model to use when updating an existing endpoint.
Integer desiredInferenceUnits
The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.
String desiredDataAccessRoleArn
Data access role ARN to use in case the new model is encrypted with a customer CMK.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel
String desiredModelArn
The Amazon Resource Number (ARN) of the new model.
String flywheelArn
The Amazon Resource Number (ARN) of the flywheel to update.
String activeModelArn
The Amazon Resource Number (ARN) of the active model version.
String dataAccessRoleArn
The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to access the flywheel data.
UpdateDataSecurityConfig dataSecurityConfig
Flywheel data security configuration.
FlywheelProperties flywheelProperties
The flywheel properties.
List<E> securityGroupIds
The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by "sg-", for instance: "sg-03b388029b0a285ea". For more information, see Security Groups for your VPC.
List<E> subnets
The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s Region. This ID number is preceded by "subnet-", for instance: "subnet-04ccf456919e69055". For more information, see VPCs and Subnets.
Copyright © 2024. All rights reserved.