SDK for PHP 3.x

Client: Aws\Comprehend\ComprehendClient
Service ID: comprehend
Version: 2017-11-27

This page describes the parameters and results for the operations of the Amazon Comprehend (2017-11-27), and shows how to use the Aws\Comprehend\ComprehendClient object to call the described operations. This documentation is specific to the 2017-11-27 API version of the service.

Operation Summary

Each of the following operations can be created from a client using $client->getCommand('CommandName'), where "CommandName" is the name of one of the following operations. Note: a command is a value that encapsulates an operation and the parameters used to create an HTTP request.

You can also create and send a command immediately using the magic methods available on a client object: $client->commandName(/* parameters */). You can send the command asynchronously (returning a promise) by appending the word "Async" to the operation name: $client->commandNameAsync(/* parameters */).

BatchDetectDominantLanguage ( array $params = [] )
Determines the dominant language of the input text for a batch of documents.
BatchDetectEntities ( array $params = [] )
Inspects the text of a batch of documents for named entities and returns information about them.
BatchDetectKeyPhrases ( array $params = [] )
Detects the key noun phrases found in a batch of documents.
BatchDetectSentiment ( array $params = [] )
Inspects a batch of documents and returns an inference of the prevailing sentiment, POSITIVE, NEUTRAL, MIXED, or NEGATIVE, in each one.
BatchDetectSyntax ( array $params = [] )
Inspects the text of a batch of documents for the syntax and part of speech of the words in the document and returns information about them.
BatchDetectTargetedSentiment ( array $params = [] )
Inspects a batch of documents and returns a sentiment analysis for each entity identified in the documents.
ClassifyDocument ( array $params = [] )
Creates a classification request to analyze a single document in real-time.
ContainsPiiEntities ( array $params = [] )
Analyzes input text for the presence of personally identifiable information (PII) and returns the labels of identified PII entity types such as name, address, bank account number, or phone number.
CreateDataset ( array $params = [] )
Creates a dataset to upload training or test data for a model associated with a flywheel.
CreateDocumentClassifier ( array $params = [] )
Creates a new document classifier that you can use to categorize documents.
CreateEndpoint ( array $params = [] )
Creates a model-specific endpoint for synchronous inference for a previously trained custom model For information about endpoints, see Managing endpoints.
CreateEntityRecognizer ( array $params = [] )
Creates an entity recognizer using submitted files.
CreateFlywheel ( array $params = [] )
A flywheel is an Amazon Web Services resource that orchestrates the ongoing training of a model for custom classification or custom entity recognition.
DeleteDocumentClassifier ( array $params = [] )
Deletes a previously created document classifier Only those classifiers that are in terminated states (IN_ERROR, TRAINED) will be deleted.
DeleteEndpoint ( array $params = [] )
Deletes a model-specific endpoint for a previously-trained custom model.
DeleteEntityRecognizer ( array $params = [] )
Deletes an entity recognizer.
DeleteFlywheel ( array $params = [] )
Deletes a flywheel.
DeleteResourcePolicy ( array $params = [] )
Deletes a resource-based policy that is attached to a custom model.
DescribeDataset ( array $params = [] )
Returns information about the dataset that you specify.
DescribeDocumentClassificationJob ( array $params = [] )
Gets the properties associated with a document classification job.
DescribeDocumentClassifier ( array $params = [] )
Gets the properties associated with a document classifier.
DescribeDominantLanguageDetectionJob ( array $params = [] )
Gets the properties associated with a dominant language detection job.
DescribeEndpoint ( array $params = [] )
Gets the properties associated with a specific endpoint.
DescribeEntitiesDetectionJob ( array $params = [] )
Gets the properties associated with an entities detection job.
DescribeEntityRecognizer ( array $params = [] )
Provides details about an entity recognizer including status, S3 buckets containing training data, recognizer metadata, metrics, and so on.
DescribeEventsDetectionJob ( array $params = [] )
Gets the status and details of an events detection job.
DescribeFlywheel ( array $params = [] )
Provides configuration information about the flywheel.
DescribeFlywheelIteration ( array $params = [] )
Retrieve the configuration properties of a flywheel iteration.
DescribeKeyPhrasesDetectionJob ( array $params = [] )
Gets the properties associated with a key phrases detection job.
DescribePiiEntitiesDetectionJob ( array $params = [] )
Gets the properties associated with a PII entities detection job.
DescribeResourcePolicy ( array $params = [] )
Gets the details of a resource-based policy that is attached to a custom model, including the JSON body of the policy.
DescribeSentimentDetectionJob ( array $params = [] )
Gets the properties associated with a sentiment detection job.
DescribeTargetedSentimentDetectionJob ( array $params = [] )
Gets the properties associated with a targeted sentiment detection job.
DescribeTopicsDetectionJob ( array $params = [] )
Gets the properties associated with a topic detection job.
DetectDominantLanguage ( array $params = [] )
Determines the dominant language of the input text.
DetectEntities ( array $params = [] )
Detects named entities in input text when you use the pre-trained model.
DetectKeyPhrases ( array $params = [] )
Detects the key noun phrases found in the text.
DetectPiiEntities ( array $params = [] )
Inspects the input text for entities that contain personally identifiable information (PII) and returns information about them.
DetectSentiment ( array $params = [] )
Inspects text and returns an inference of the prevailing sentiment (POSITIVE, NEUTRAL, MIXED, or NEGATIVE).
DetectSyntax ( array $params = [] )
Inspects text for syntax and the part of speech of words in the document.
DetectTargetedSentiment ( array $params = [] )
Inspects the input text and returns a sentiment analysis for each entity identified in the text.
DetectToxicContent ( array $params = [] )
Performs toxicity analysis on the list of text strings that you provide as input.
ImportModel ( array $params = [] )
Creates a new custom model that replicates a source custom model that you import.
ListDatasets ( array $params = [] )
List the datasets that you have configured in this Region.
ListDocumentClassificationJobs ( array $params = [] )
Gets a list of the documentation classification jobs that you have submitted.
ListDocumentClassifierSummaries ( array $params = [] )
Gets a list of summaries of the document classifiers that you have created
ListDocumentClassifiers ( array $params = [] )
Gets a list of the document classifiers that you have created.
ListDominantLanguageDetectionJobs ( array $params = [] )
Gets a list of the dominant language detection jobs that you have submitted.
ListEndpoints ( array $params = [] )
Gets a list of all existing endpoints that you've created.
ListEntitiesDetectionJobs ( array $params = [] )
Gets a list of the entity detection jobs that you have submitted.
ListEntityRecognizerSummaries ( array $params = [] )
Gets a list of summaries for the entity recognizers that you have created.
ListEntityRecognizers ( array $params = [] )
Gets a list of the properties of all entity recognizers that you created, including recognizers currently in training.
ListEventsDetectionJobs ( array $params = [] )
Gets a list of the events detection jobs that you have submitted.
ListFlywheelIterationHistory ( array $params = [] )
Information about the history of a flywheel iteration.
ListFlywheels ( array $params = [] )
Gets a list of the flywheels that you have created.
ListKeyPhrasesDetectionJobs ( array $params = [] )
Get a list of key phrase detection jobs that you have submitted.
ListPiiEntitiesDetectionJobs ( array $params = [] )
Gets a list of the PII entity detection jobs that you have submitted.
ListSentimentDetectionJobs ( array $params = [] )
Gets a list of sentiment detection jobs that you have submitted.
ListTagsForResource ( array $params = [] )
Lists all tags associated with a given Amazon Comprehend resource.
ListTargetedSentimentDetectionJobs ( array $params = [] )
Gets a list of targeted sentiment detection jobs that you have submitted.
ListTopicsDetectionJobs ( array $params = [] )
Gets a list of the topic detection jobs that you have submitted.
PutResourcePolicy ( array $params = [] )
Attaches a resource-based policy to a custom model.
StartDocumentClassificationJob ( array $params = [] )
Starts an asynchronous document classification job using a custom classification model.
StartDominantLanguageDetectionJob ( array $params = [] )
Starts an asynchronous dominant language detection job for a collection of documents.
StartEntitiesDetectionJob ( array $params = [] )
Starts an asynchronous entity detection job for a collection of documents.
StartEventsDetectionJob ( array $params = [] )
Starts an asynchronous event detection job for a collection of documents.
StartFlywheelIteration ( array $params = [] )
Start the flywheel iteration.
StartKeyPhrasesDetectionJob ( array $params = [] )
Starts an asynchronous key phrase detection job for a collection of documents.
StartPiiEntitiesDetectionJob ( array $params = [] )
Starts an asynchronous PII entity detection job for a collection of documents.
StartSentimentDetectionJob ( array $params = [] )
Starts an asynchronous sentiment detection job for a collection of documents.
StartTargetedSentimentDetectionJob ( array $params = [] )
Starts an asynchronous targeted sentiment detection job for a collection of documents.
StartTopicsDetectionJob ( array $params = [] )
Starts an asynchronous topic detection job.
StopDominantLanguageDetectionJob ( array $params = [] )
Stops a dominant language detection job in progress.
StopEntitiesDetectionJob ( array $params = [] )
Stops an entities detection job in progress.
StopEventsDetectionJob ( array $params = [] )
Stops an events detection job in progress.
StopKeyPhrasesDetectionJob ( array $params = [] )
Stops a key phrases detection job in progress.
StopPiiEntitiesDetectionJob ( array $params = [] )
Stops a PII entities detection job in progress.
StopSentimentDetectionJob ( array $params = [] )
Stops a sentiment detection job in progress.
StopTargetedSentimentDetectionJob ( array $params = [] )
Stops a targeted sentiment detection job in progress.
StopTrainingDocumentClassifier ( array $params = [] )
Stops a document classifier training job while in progress.
StopTrainingEntityRecognizer ( array $params = [] )
Stops an entity recognizer training job while in progress.
TagResource ( array $params = [] )
Associates a specific tag with an Amazon Comprehend resource.
UntagResource ( array $params = [] )
Removes a specific tag associated with an Amazon Comprehend resource.
UpdateEndpoint ( array $params = [] )
Updates information about the specified endpoint.
UpdateFlywheel ( array $params = [] )
Update the configuration information for an existing flywheel.

Paginators

Paginators handle automatically iterating over paginated API results. Paginators are associated with specific API operations, and they accept the parameters that the corresponding API operation accepts. You can get a paginator from a client class using getPaginator($paginatorName, $operationParameters). This client supports the following paginators:

ListDatasets
ListDocumentClassificationJobs
ListDocumentClassifierSummaries
ListDocumentClassifiers
ListDominantLanguageDetectionJobs
ListEndpoints
ListEntitiesDetectionJobs
ListEntityRecognizerSummaries
ListEntityRecognizers
ListEventsDetectionJobs
ListFlywheelIterationHistory
ListFlywheels
ListKeyPhrasesDetectionJobs
ListPiiEntitiesDetectionJobs
ListSentimentDetectionJobs
ListTargetedSentimentDetectionJobs
ListTopicsDetectionJobs

Operations

BatchDetectDominantLanguage

$result = $client->batchDetectDominantLanguage([/* ... */]);
$promise = $client->batchDetectDominantLanguageAsync([/* ... */]);

Determines the dominant language of the input text for a batch of documents. For a list of languages that Amazon Comprehend can detect, see Amazon Comprehend Supported Languages.

Parameter Syntax

$result = $client->batchDetectDominantLanguage([
    'TextList' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
TextList
Required: Yes
Type: Array of strings

A list containing the UTF-8 encoded text of the input documents. The list can contain a maximum of 25 documents. Each document should contain at least 20 characters. The maximum size of each document is 5 KB.

Result Syntax

[
    'ErrorList' => [
        [
            'ErrorCode' => '<string>',
            'ErrorMessage' => '<string>',
            'Index' => <integer>,
        ],
        // ...
    ],
    'ResultList' => [
        [
            'Index' => <integer>,
            'Languages' => [
                [
                    'LanguageCode' => '<string>',
                    'Score' => <float>,
                ],
                // ...
            ],
        ],
        // ...
    ],
]

Result Details

Members
ErrorList
Required: Yes
Type: Array of BatchItemError structures

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.

ResultList
Required: Yes
Type: Array of BatchDetectDominantLanguageItemResult structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

BatchSizeLimitExceededException:

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

InternalServerException:

An internal server error occurred. Retry your request.

BatchDetectEntities

$result = $client->batchDetectEntities([/* ... */]);
$promise = $client->batchDetectEntitiesAsync([/* ... */]);

Inspects the text of a batch of documents for named entities and returns information about them. For more information about named entities, see Entities in the Comprehend Developer Guide.

Parameter Syntax

$result = $client->batchDetectEntities([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'TextList' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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.

TextList
Required: Yes
Type: Array of strings

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.

Result Syntax

[
    'ErrorList' => [
        [
            'ErrorCode' => '<string>',
            'ErrorMessage' => '<string>',
            'Index' => <integer>,
        ],
        // ...
    ],
    'ResultList' => [
        [
            'Entities' => [
                [
                    'BeginOffset' => <integer>,
                    'BlockReferences' => [
                        [
                            'BeginOffset' => <integer>,
                            'BlockId' => '<string>',
                            'ChildBlocks' => [
                                [
                                    'BeginOffset' => <integer>,
                                    'ChildBlockId' => '<string>',
                                    'EndOffset' => <integer>,
                                ],
                                // ...
                            ],
                            'EndOffset' => <integer>,
                        ],
                        // ...
                    ],
                    'EndOffset' => <integer>,
                    'Score' => <float>,
                    'Text' => '<string>',
                    'Type' => 'PERSON|LOCATION|ORGANIZATION|COMMERCIAL_ITEM|EVENT|DATE|QUANTITY|TITLE|OTHER',
                ],
                // ...
            ],
            'Index' => <integer>,
        ],
        // ...
    ],
]

Result Details

Members
ErrorList
Required: Yes
Type: Array of BatchItemError structures

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.

ResultList
Required: Yes
Type: Array of BatchDetectEntitiesItemResult structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

BatchSizeLimitExceededException:

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

InternalServerException:

An internal server error occurred. Retry your request.

BatchDetectKeyPhrases

$result = $client->batchDetectKeyPhrases([/* ... */]);
$promise = $client->batchDetectKeyPhrasesAsync([/* ... */]);

Detects the key noun phrases found in a batch of documents.

Parameter Syntax

$result = $client->batchDetectKeyPhrases([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'TextList' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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.

TextList
Required: Yes
Type: Array of strings

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.

Result Syntax

[
    'ErrorList' => [
        [
            'ErrorCode' => '<string>',
            'ErrorMessage' => '<string>',
            'Index' => <integer>,
        ],
        // ...
    ],
    'ResultList' => [
        [
            'Index' => <integer>,
            'KeyPhrases' => [
                [
                    'BeginOffset' => <integer>,
                    'EndOffset' => <integer>,
                    'Score' => <float>,
                    'Text' => '<string>',
                ],
                // ...
            ],
        ],
        // ...
    ],
]

Result Details

Members
ErrorList
Required: Yes
Type: Array of BatchItemError structures

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.

ResultList
Required: Yes
Type: Array of BatchDetectKeyPhrasesItemResult structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

BatchSizeLimitExceededException:

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

InternalServerException:

An internal server error occurred. Retry your request.

BatchDetectSentiment

$result = $client->batchDetectSentiment([/* ... */]);
$promise = $client->batchDetectSentimentAsync([/* ... */]);

Inspects a batch of documents and returns an inference of the prevailing sentiment, POSITIVE, NEUTRAL, MIXED, or NEGATIVE, in each one.

Parameter Syntax

$result = $client->batchDetectSentiment([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'TextList' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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.

TextList
Required: Yes
Type: Array of strings

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.

Result Syntax

[
    'ErrorList' => [
        [
            'ErrorCode' => '<string>',
            'ErrorMessage' => '<string>',
            'Index' => <integer>,
        ],
        // ...
    ],
    'ResultList' => [
        [
            'Index' => <integer>,
            'Sentiment' => 'POSITIVE|NEGATIVE|NEUTRAL|MIXED',
            'SentimentScore' => [
                'Mixed' => <float>,
                'Negative' => <float>,
                'Neutral' => <float>,
                'Positive' => <float>,
            ],
        ],
        // ...
    ],
]

Result Details

Members
ErrorList
Required: Yes
Type: Array of BatchItemError structures

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.

ResultList
Required: Yes
Type: Array of BatchDetectSentimentItemResult structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

BatchSizeLimitExceededException:

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

InternalServerException:

An internal server error occurred. Retry your request.

BatchDetectSyntax

$result = $client->batchDetectSyntax([/* ... */]);
$promise = $client->batchDetectSyntaxAsync([/* ... */]);

Inspects the text of a batch of documents for the syntax and part of speech of the words in the document and returns information about them. For more information, see Syntax in the Comprehend Developer Guide.

Parameter Syntax

$result = $client->batchDetectSyntax([
    'LanguageCode' => 'en|es|fr|de|it|pt', // REQUIRED
    'TextList' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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.

TextList
Required: Yes
Type: Array of strings

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.

Result Syntax

[
    'ErrorList' => [
        [
            'ErrorCode' => '<string>',
            'ErrorMessage' => '<string>',
            'Index' => <integer>,
        ],
        // ...
    ],
    'ResultList' => [
        [
            'Index' => <integer>,
            'SyntaxTokens' => [
                [
                    'BeginOffset' => <integer>,
                    'EndOffset' => <integer>,
                    'PartOfSpeech' => [
                        'Score' => <float>,
                        'Tag' => 'ADJ|ADP|ADV|AUX|CONJ|CCONJ|DET|INTJ|NOUN|NUM|O|PART|PRON|PROPN|PUNCT|SCONJ|SYM|VERB',
                    ],
                    'Text' => '<string>',
                    'TokenId' => <integer>,
                ],
                // ...
            ],
        ],
        // ...
    ],
]

Result Details

Members
ErrorList
Required: Yes
Type: Array of BatchItemError structures

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.

ResultList
Required: Yes
Type: Array of BatchDetectSyntaxItemResult structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

BatchSizeLimitExceededException:

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

InternalServerException:

An internal server error occurred. Retry your request.

BatchDetectTargetedSentiment

$result = $client->batchDetectTargetedSentiment([/* ... */]);
$promise = $client->batchDetectTargetedSentimentAsync([/* ... */]);

Inspects a batch of documents and returns a sentiment analysis for each entity identified in the documents.

For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->batchDetectTargetedSentiment([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'TextList' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

The language of the input documents. Currently, English is the only supported language.

TextList
Required: Yes
Type: Array of strings

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.

Result Syntax

[
    'ErrorList' => [
        [
            'ErrorCode' => '<string>',
            'ErrorMessage' => '<string>',
            'Index' => <integer>,
        ],
        // ...
    ],
    'ResultList' => [
        [
            'Entities' => [
                [
                    'DescriptiveMentionIndex' => [<integer>, ...],
                    'Mentions' => [
                        [
                            'BeginOffset' => <integer>,
                            'EndOffset' => <integer>,
                            'GroupScore' => <float>,
                            'MentionSentiment' => [
                                'Sentiment' => 'POSITIVE|NEGATIVE|NEUTRAL|MIXED',
                                'SentimentScore' => [
                                    'Mixed' => <float>,
                                    'Negative' => <float>,
                                    'Neutral' => <float>,
                                    'Positive' => <float>,
                                ],
                            ],
                            'Score' => <float>,
                            'Text' => '<string>',
                            'Type' => 'PERSON|LOCATION|ORGANIZATION|FACILITY|BRAND|COMMERCIAL_ITEM|MOVIE|MUSIC|BOOK|SOFTWARE|GAME|PERSONAL_TITLE|EVENT|DATE|QUANTITY|ATTRIBUTE|OTHER',
                        ],
                        // ...
                    ],
                ],
                // ...
            ],
            'Index' => <integer>,
        ],
        // ...
    ],
]

Result Details

Members
ErrorList
Required: Yes
Type: Array of BatchItemError structures

List of errors that the operation can return.

ResultList
Required: Yes
Type: Array of BatchDetectTargetedSentimentItemResult structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

BatchSizeLimitExceededException:

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

InternalServerException:

An internal server error occurred. Retry your request.

ClassifyDocument

$result = $client->classifyDocument([/* ... */]);
$promise = $client->classifyDocumentAsync([/* ... */]);

Creates a classification request to analyze a single document in real-time. ClassifyDocument supports the following model types:

  • Custom classifier - a custom model that you have created and trained. For input, you can provide plain text, a single-page document (PDF, Word, or image), or Amazon Textract API output. For more information, see Custom classification in the Amazon Comprehend Developer Guide.

  • Prompt safety classifier - Amazon Comprehend provides a pre-trained model for classifying input prompts for generative AI applications. For input, you provide English plain text input. For prompt safety classification, the response includes only the Classes field. For more information about prompt safety classifiers, see Prompt safety classification in the Amazon Comprehend Developer Guide.

If the system detects errors while processing a page in the input document, the API response includes an Errors field that describes the errors.

If the system detects a document-level error in your input document, the API returns an InvalidRequestException error response. For details about this exception, see Errors in semi-structured documents in the Comprehend Developer Guide.

Parameter Syntax

$result = $client->classifyDocument([
    'Bytes' => <string || resource || Psr\Http\Message\StreamInterface>,
    'DocumentReaderConfig' => [
        'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
        'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
        'FeatureTypes' => ['<string>', ...],
    ],
    'EndpointArn' => '<string>', // REQUIRED
    'Text' => '<string>',
]);

Parameter Details

Members
Bytes
Type: blob (string|resource|Psr\Http\Message\StreamInterface)

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
Type: DocumentReaderConfig structure

Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

EndpointArn
Required: Yes
Type: string

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.

Text
Type: string

The document text to be analyzed. If you enter text using this parameter, do not use the Bytes parameter.

Result Syntax

[
    'Classes' => [
        [
            'Name' => '<string>',
            'Page' => <integer>,
            'Score' => <float>,
        ],
        // ...
    ],
    'DocumentMetadata' => [
        'ExtractedCharacters' => [
            [
                'Count' => <integer>,
                'Page' => <integer>,
            ],
            // ...
        ],
        'Pages' => <integer>,
    ],
    'DocumentType' => [
        [
            'Page' => <integer>,
            'Type' => 'NATIVE_PDF|SCANNED_PDF|MS_WORD|IMAGE|PLAIN_TEXT|TEXTRACT_DETECT_DOCUMENT_TEXT_JSON|TEXTRACT_ANALYZE_DOCUMENT_JSON',
        ],
        // ...
    ],
    'Errors' => [
        [
            'ErrorCode' => 'TEXTRACT_BAD_PAGE|TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED|PAGE_CHARACTERS_EXCEEDED|PAGE_SIZE_EXCEEDED|INTERNAL_SERVER_ERROR',
            'ErrorMessage' => '<string>',
            'Page' => <integer>,
        ],
        // ...
    ],
    'Labels' => [
        [
            'Name' => '<string>',
            'Page' => <integer>,
            'Score' => <float>,
        ],
        // ...
    ],
    'Warnings' => [
        [
            'Page' => <integer>,
            'WarnCode' => 'INFERENCING_PLAINTEXT_WITH_NATIVE_TRAINED_MODEL|INFERENCING_NATIVE_DOCUMENT_WITH_PLAINTEXT_TRAINED_MODEL',
            'WarnMessage' => '<string>',
        ],
        // ...
    ],
]

Result Details

Members
Classes
Type: Array of DocumentClass structures

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.

DocumentMetadata
Type: DocumentMetadata structure

Extraction information about the document. This field is present in the response only if your request includes the Byte parameter.

DocumentType
Type: Array of DocumentTypeListItem structures

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.

Errors
Type: Array of ErrorsListItem structures

Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.

Labels
Type: Array of DocumentLabel structures

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.

Warnings
Type: Array of WarningsListItem structures

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.

Errors

InvalidRequestException:

The request is invalid.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

InternalServerException:

An internal server error occurred. Retry your request.

ContainsPiiEntities

$result = $client->containsPiiEntities([/* ... */]);
$promise = $client->containsPiiEntitiesAsync([/* ... */]);

Analyzes input text for the presence of personally identifiable information (PII) and returns the labels of identified PII entity types such as name, address, bank account number, or phone number.

Parameter Syntax

$result = $client->containsPiiEntities([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

The language of the input documents.

Text
Required: Yes
Type: string

A UTF-8 text string. The maximum string size is 100 KB.

Result Syntax

[
    'Labels' => [
        [
            'Name' => 'BANK_ACCOUNT_NUMBER|BANK_ROUTING|CREDIT_DEBIT_NUMBER|CREDIT_DEBIT_CVV|CREDIT_DEBIT_EXPIRY|PIN|EMAIL|ADDRESS|NAME|PHONE|SSN|DATE_TIME|PASSPORT_NUMBER|DRIVER_ID|URL|AGE|USERNAME|PASSWORD|AWS_ACCESS_KEY|AWS_SECRET_KEY|IP_ADDRESS|MAC_ADDRESS|ALL|LICENSE_PLATE|VEHICLE_IDENTIFICATION_NUMBER|UK_NATIONAL_INSURANCE_NUMBER|CA_SOCIAL_INSURANCE_NUMBER|US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER|UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER|IN_PERMANENT_ACCOUNT_NUMBER|IN_NREGA|INTERNATIONAL_BANK_ACCOUNT_NUMBER|SWIFT_CODE|UK_NATIONAL_HEALTH_SERVICE_NUMBER|CA_HEALTH_NUMBER|IN_AADHAAR|IN_VOTER_NUMBER',
            'Score' => <float>,
        ],
        // ...
    ],
]

Result Details

Members
Labels
Type: Array of EntityLabel structures

The labels used in the document being analyzed. Individual labels represent personally identifiable information (PII) entity types.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

CreateDataset

$result = $client->createDataset([/* ... */]);
$promise = $client->createDatasetAsync([/* ... */]);

Creates a dataset to upload training or test data for a model associated with a flywheel. For more information about datasets, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->createDataset([
    'ClientRequestToken' => '<string>',
    'DatasetName' => '<string>', // REQUIRED
    'DatasetType' => 'TRAIN|TEST',
    'Description' => '<string>',
    'FlywheelArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'AugmentedManifests' => [
            [
                'AnnotationDataS3Uri' => '<string>',
                'AttributeNames' => ['<string>', ...], // REQUIRED
                'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                'S3Uri' => '<string>', // REQUIRED
                'SourceDocumentsS3Uri' => '<string>',
            ],
            // ...
        ],
        'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
        'DocumentClassifierInputDataConfig' => [
            'LabelDelimiter' => '<string>',
            'S3Uri' => '<string>', // REQUIRED
        ],
        'EntityRecognizerInputDataConfig' => [
            'Annotations' => [
                'S3Uri' => '<string>', // REQUIRED
            ],
            'Documents' => [ // REQUIRED
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>', // REQUIRED
            ],
            'EntityList' => [
                'S3Uri' => '<string>', // REQUIRED
            ],
        ],
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DatasetName
Required: Yes
Type: string

Name of the dataset.

DatasetType
Type: string

The dataset type. You can specify that the data in a dataset is for training the model or for testing the model.

Description
Type: string

Description of the dataset.

FlywheelArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the flywheel of the flywheel to receive the data.

InputDataConfig
Required: Yes
Type: DatasetInputDataConfig structure

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.

Tags
Type: Array of Tag structures

Tags for the dataset.

Result Syntax

[
    'DatasetArn' => '<string>',
]

Result Details

Members
DatasetArn
Type: string

The ARN of the dataset.

Errors

InvalidRequestException:

The request is invalid.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

CreateDocumentClassifier

$result = $client->createDocumentClassifier([/* ... */]);
$promise = $client->createDocumentClassifierAsync([/* ... */]);

Creates a new document classifier that you can use to categorize documents. To create a classifier, you provide a set of training documents that are labeled with the categories that you want to use. For more information, see Training classifier models in the Comprehend Developer Guide.

Parameter Syntax

$result = $client->createDocumentClassifier([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'DocumentClassifierName' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'AugmentedManifests' => [
            [
                'AnnotationDataS3Uri' => '<string>',
                'AttributeNames' => ['<string>', ...], // REQUIRED
                'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                'S3Uri' => '<string>', // REQUIRED
                'SourceDocumentsS3Uri' => '<string>',
                'Split' => 'TRAIN|TEST',
            ],
            // ...
        ],
        'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
        'Documents' => [
            'S3Uri' => '<string>', // REQUIRED
            'TestS3Uri' => '<string>',
        ],
        'LabelDelimiter' => '<string>',
        'S3Uri' => '<string>',
        'TestS3Uri' => '<string>',
    ],
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Mode' => 'MULTI_CLASS|MULTI_LABEL',
    'ModelKmsKeyId' => '<string>',
    'ModelPolicy' => '<string>',
    'OutputDataConfig' => [
        'FlywheelStatsS3Prefix' => '<string>',
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>',
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VersionName' => '<string>',
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

DocumentClassifierName
Required: Yes
Type: string

The name of the document classifier.

InputDataConfig
Required: Yes
Type: DocumentClassifierInputDataConfig structure

Specifies the format and location of the input data for the job.

LanguageCode
Required: Yes
Type: string

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.

Mode
Type: string

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 (|).

ModelKmsKeyId
Type: string

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"

ModelPolicy
Type: string

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"]}'

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.

Tags
Type: Array of Tag structures

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.

VersionName
Type: string

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'DocumentClassifierArn' => '<string>',
]

Result Details

Members
DocumentClassifierArn
Type: string

The Amazon Resource Name (ARN) that identifies the document classifier.

Errors

InvalidRequestException:

The request is invalid.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

InternalServerException:

An internal server error occurred. Retry your request.

CreateEndpoint

$result = $client->createEndpoint([/* ... */]);
$promise = $client->createEndpointAsync([/* ... */]);

Creates a model-specific endpoint for synchronous inference for a previously trained custom model For information about endpoints, see Managing endpoints.

Parameter Syntax

$result = $client->createEndpoint([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>',
    'DesiredInferenceUnits' => <integer>, // REQUIRED
    'EndpointName' => '<string>', // REQUIRED
    'FlywheelArn' => '<string>',
    'ModelArn' => '<string>',
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

An idempotency token provided by the customer. If this token matches a previous endpoint creation request, Amazon Comprehend will not return a ResourceInUseException.

DataAccessRoleArn
Type: string

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).

DesiredInferenceUnits
Required: Yes
Type: int

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.

EndpointName
Required: Yes
Type: string

This is the descriptive suffix that becomes part of the EndpointArn used for all subsequent requests to this resource.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel to which the endpoint will be attached.

ModelArn
Type: string

The Amazon Resource Number (ARN) of the model to which the endpoint will be attached.

Tags
Type: Array of Tag structures

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.

Result Syntax

[
    'EndpointArn' => '<string>',
    'ModelArn' => '<string>',
]

Result Details

Members
EndpointArn
Type: string

The Amazon Resource Number (ARN) of the endpoint being created.

ModelArn
Type: string

The Amazon Resource Number (ARN) of the model to which the endpoint is attached.

Errors

InvalidRequestException:

The request is invalid.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

InternalServerException:

An internal server error occurred. Retry your request.

CreateEntityRecognizer

$result = $client->createEntityRecognizer([/* ... */]);
$promise = $client->createEntityRecognizerAsync([/* ... */]);

Creates an entity recognizer using submitted files. After your CreateEntityRecognizer request is submitted, you can check job status using the DescribeEntityRecognizer API.

Parameter Syntax

$result = $client->createEntityRecognizer([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'Annotations' => [
            'S3Uri' => '<string>', // REQUIRED
            'TestS3Uri' => '<string>',
        ],
        'AugmentedManifests' => [
            [
                'AnnotationDataS3Uri' => '<string>',
                'AttributeNames' => ['<string>', ...], // REQUIRED
                'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                'S3Uri' => '<string>', // REQUIRED
                'SourceDocumentsS3Uri' => '<string>',
                'Split' => 'TRAIN|TEST',
            ],
            // ...
        ],
        'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
        'Documents' => [
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>', // REQUIRED
            'TestS3Uri' => '<string>',
        ],
        'EntityList' => [
            'S3Uri' => '<string>', // REQUIRED
        ],
        'EntityTypes' => [ // REQUIRED
            [
                'Type' => '<string>', // REQUIRED
            ],
            // ...
        ],
    ],
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'ModelKmsKeyId' => '<string>',
    'ModelPolicy' => '<string>',
    'RecognizerName' => '<string>', // REQUIRED
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VersionName' => '<string>',
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

InputDataConfig
Required: Yes
Type: EntityRecognizerInputDataConfig structure

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.

LanguageCode
Required: Yes
Type: string

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.

ModelKmsKeyId
Type: string

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"

ModelPolicy
Type: string

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"]}'

RecognizerName
Required: Yes
Type: string

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.

Tags
Type: Array of Tag structures

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.

VersionName
Type: string

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'EntityRecognizerArn' => '<string>',
]

Result Details

Members
EntityRecognizerArn
Type: string

The Amazon Resource Name (ARN) that identifies the entity recognizer.

Errors

InvalidRequestException:

The request is invalid.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

InternalServerException:

An internal server error occurred. Retry your request.

CreateFlywheel

$result = $client->createFlywheel([/* ... */]);
$promise = $client->createFlywheelAsync([/* ... */]);

A flywheel is an Amazon Web Services resource that orchestrates the ongoing training of a model for custom classification or custom entity recognition. You can create a flywheel to start with an existing trained model, or Comprehend can create and train a new model.

When you create the flywheel, Comprehend creates a data lake in your account. The data lake holds the training data and test data for all versions of the model.

To use a flywheel with an existing trained model, you specify the active model version. Comprehend copies the model's training data and test data into the flywheel's data lake.

To use the flywheel with a new model, you need to provide a dataset for training data (and optional test data) when you create the flywheel.

For more information about flywheels, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->createFlywheel([
    'ActiveModelArn' => '<string>',
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'DataLakeS3Uri' => '<string>', // REQUIRED
    'DataSecurityConfig' => [
        'DataLakeKmsKeyId' => '<string>',
        'ModelKmsKeyId' => '<string>',
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...], // REQUIRED
            'Subnets' => ['<string>', ...], // REQUIRED
        ],
    ],
    'FlywheelName' => '<string>', // REQUIRED
    'ModelType' => 'DOCUMENT_CLASSIFIER|ENTITY_RECOGNIZER',
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'TaskConfig' => [
        'DocumentClassificationConfig' => [
            'Labels' => ['<string>', ...],
            'Mode' => 'MULTI_CLASS|MULTI_LABEL', // REQUIRED
        ],
        'EntityRecognitionConfig' => [
            'EntityTypes' => [ // REQUIRED
                [
                    'Type' => '<string>', // REQUIRED
                ],
                // ...
            ],
        ],
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    ],
]);

Parameter Details

Members
ActiveModelArn
Type: string

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.

ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

DataLakeS3Uri
Required: Yes
Type: string

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
Type: DataSecurityConfig structure

Data security configurations.

FlywheelName
Required: Yes
Type: string

Name for the flywheel.

ModelType
Type: string

The model type. You need to set ModelType if you are creating a flywheel for a new model.

Tags
Type: Array of Tag structures

The tags to associate with this flywheel.

TaskConfig
Type: TaskConfig structure

Configuration about the model associated with the flywheel. You need to set TaskConfig if you are creating a flywheel for a new model.

Result Syntax

[
    'ActiveModelArn' => '<string>',
    'FlywheelArn' => '<string>',
]

Result Details

Members
ActiveModelArn
Type: string

The Amazon Resource Number (ARN) of the active model version.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel.

Errors

InvalidRequestException:

The request is invalid.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DeleteDocumentClassifier

$result = $client->deleteDocumentClassifier([/* ... */]);
$promise = $client->deleteDocumentClassifierAsync([/* ... */]);

Deletes a previously created document classifier

Only those classifiers that are in terminated states (IN_ERROR, TRAINED) will be deleted. If an active inference job is using the model, a ResourceInUseException will be returned.

This is an asynchronous action that puts the classifier into a DELETING state, and it is then removed by a background job. Once removed, the classifier disappears from your account and is no longer available for use.

Parameter Syntax

$result = $client->deleteDocumentClassifier([
    'DocumentClassifierArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
DocumentClassifierArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) that identifies the document classifier.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DeleteEndpoint

$result = $client->deleteEndpoint([/* ... */]);
$promise = $client->deleteEndpointAsync([/* ... */]);

Deletes a model-specific endpoint for a previously-trained custom model. All endpoints must be deleted in order for the model to be deleted. For information about endpoints, see Managing endpoints.

Parameter Syntax

$result = $client->deleteEndpoint([
    'EndpointArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
EndpointArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the endpoint being deleted.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DeleteEntityRecognizer

$result = $client->deleteEntityRecognizer([/* ... */]);
$promise = $client->deleteEntityRecognizerAsync([/* ... */]);

Deletes an entity recognizer.

Only those recognizers that are in terminated states (IN_ERROR, TRAINED) will be deleted. If an active inference job is using the model, a ResourceInUseException will be returned.

This is an asynchronous action that puts the recognizer into a DELETING state, and it is then removed by a background job. Once removed, the recognizer disappears from your account and is no longer available for use.

Parameter Syntax

$result = $client->deleteEntityRecognizer([
    'EntityRecognizerArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
EntityRecognizerArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) that identifies the entity recognizer.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DeleteFlywheel

$result = $client->deleteFlywheel([/* ... */]);
$promise = $client->deleteFlywheelAsync([/* ... */]);

Deletes a flywheel. When you delete the flywheel, Amazon Comprehend does not delete the data lake or the model associated with the flywheel.

For more information about flywheels, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->deleteFlywheel([
    'FlywheelArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
FlywheelArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the flywheel to delete.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DeleteResourcePolicy

$result = $client->deleteResourcePolicy([/* ... */]);
$promise = $client->deleteResourcePolicyAsync([/* ... */]);

Deletes a resource-based policy that is attached to a custom model.

Parameter Syntax

$result = $client->deleteResourcePolicy([
    'PolicyRevisionId' => '<string>',
    'ResourceArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
PolicyRevisionId
Type: string

The revision ID of the policy to delete.

ResourceArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the custom model version that has the policy to delete.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeDataset

$result = $client->describeDataset([/* ... */]);
$promise = $client->describeDatasetAsync([/* ... */]);

Returns information about the dataset that you specify. For more information about datasets, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->describeDataset([
    'DatasetArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
DatasetArn
Required: Yes
Type: string

The ARN of the dataset.

Result Syntax

[
    'DatasetProperties' => [
        'CreationTime' => <DateTime>,
        'DatasetArn' => '<string>',
        'DatasetName' => '<string>',
        'DatasetS3Uri' => '<string>',
        'DatasetType' => 'TRAIN|TEST',
        'Description' => '<string>',
        'EndTime' => <DateTime>,
        'Message' => '<string>',
        'NumberOfDocuments' => <integer>,
        'Status' => 'CREATING|COMPLETED|FAILED',
    ],
]

Result Details

Members
DatasetProperties
Type: DatasetProperties structure

The dataset properties.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeDocumentClassificationJob

$result = $client->describeDocumentClassificationJob([/* ... */]);
$promise = $client->describeDocumentClassificationJobAsync([/* ... */]);

Gets the properties associated with a document classification job. Use this operation to get the status of a classification job.

Parameter Syntax

$result = $client->describeDocumentClassificationJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The StartDocumentClassificationJob operation returns this identifier in its response.

Result Syntax

[
    'DocumentClassificationJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'DocumentClassifierArn' => '<string>',
        'EndTime' => <DateTime>,
        'FlywheelArn' => '<string>',
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
DocumentClassificationJobProperties

An object that describes the properties associated with the document classification job.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeDocumentClassifier

$result = $client->describeDocumentClassifier([/* ... */]);
$promise = $client->describeDocumentClassifierAsync([/* ... */]);

Gets the properties associated with a document classifier.

Parameter Syntax

$result = $client->describeDocumentClassifier([
    'DocumentClassifierArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
DocumentClassifierArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) that identifies the document classifier. The CreateDocumentClassifier operation returns this identifier in its response.

Result Syntax

[
    'DocumentClassifierProperties' => [
        'ClassifierMetadata' => [
            'EvaluationMetrics' => [
                'Accuracy' => <float>,
                'F1Score' => <float>,
                'HammingLoss' => <float>,
                'MicroF1Score' => <float>,
                'MicroPrecision' => <float>,
                'MicroRecall' => <float>,
                'Precision' => <float>,
                'Recall' => <float>,
            ],
            'NumberOfLabels' => <integer>,
            'NumberOfTestDocuments' => <integer>,
            'NumberOfTrainedDocuments' => <integer>,
        ],
        'DataAccessRoleArn' => '<string>',
        'DocumentClassifierArn' => '<string>',
        'EndTime' => <DateTime>,
        'FlywheelArn' => '<string>',
        'InputDataConfig' => [
            'AugmentedManifests' => [
                [
                    'AnnotationDataS3Uri' => '<string>',
                    'AttributeNames' => ['<string>', ...],
                    'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                    'S3Uri' => '<string>',
                    'SourceDocumentsS3Uri' => '<string>',
                    'Split' => 'TRAIN|TEST',
                ],
                // ...
            ],
            'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
            'Documents' => [
                'S3Uri' => '<string>',
                'TestS3Uri' => '<string>',
            ],
            'LabelDelimiter' => '<string>',
            'S3Uri' => '<string>',
            'TestS3Uri' => '<string>',
        ],
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'Mode' => 'MULTI_CLASS|MULTI_LABEL',
        'ModelKmsKeyId' => '<string>',
        'OutputDataConfig' => [
            'FlywheelStatsS3Prefix' => '<string>',
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SourceModelArn' => '<string>',
        'Status' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
        'SubmitTime' => <DateTime>,
        'TrainingEndTime' => <DateTime>,
        'TrainingStartTime' => <DateTime>,
        'VersionName' => '<string>',
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
DocumentClassifierProperties

An object that contains the properties associated with a document classifier.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeDominantLanguageDetectionJob

$result = $client->describeDominantLanguageDetectionJob([/* ... */]);
$promise = $client->describeDominantLanguageDetectionJobAsync([/* ... */]);

Gets the properties associated with a dominant language detection job. Use this operation to get the status of a detection job.

Parameter Syntax

$result = $client->describeDominantLanguageDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The StartDominantLanguageDetectionJob operation returns this identifier in its response.

Result Syntax

[
    'DominantLanguageDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
DominantLanguageDetectionJobProperties

An object that contains the properties associated with a dominant language detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeEndpoint

$result = $client->describeEndpoint([/* ... */]);
$promise = $client->describeEndpointAsync([/* ... */]);

Gets the properties associated with a specific endpoint. Use this operation to get the status of an endpoint. For information about endpoints, see Managing endpoints.

Parameter Syntax

$result = $client->describeEndpoint([
    'EndpointArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
EndpointArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the endpoint being described.

Result Syntax

[
    'EndpointProperties' => [
        'CreationTime' => <DateTime>,
        'CurrentInferenceUnits' => <integer>,
        'DataAccessRoleArn' => '<string>',
        'DesiredDataAccessRoleArn' => '<string>',
        'DesiredInferenceUnits' => <integer>,
        'DesiredModelArn' => '<string>',
        'EndpointArn' => '<string>',
        'FlywheelArn' => '<string>',
        'LastModifiedTime' => <DateTime>,
        'Message' => '<string>',
        'ModelArn' => '<string>',
        'Status' => 'CREATING|DELETING|FAILED|IN_SERVICE|UPDATING',
    ],
]

Result Details

Members
EndpointProperties
Type: EndpointProperties structure

Describes information associated with the specific endpoint.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeEntitiesDetectionJob

$result = $client->describeEntitiesDetectionJob([/* ... */]);
$promise = $client->describeEntitiesDetectionJobAsync([/* ... */]);

Gets the properties associated with an entities detection job. Use this operation to get the status of a detection job.

Parameter Syntax

$result = $client->describeEntitiesDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The StartEntitiesDetectionJob operation returns this identifier in its response.

Result Syntax

[
    'EntitiesDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'EntityRecognizerArn' => '<string>',
        'FlywheelArn' => '<string>',
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
EntitiesDetectionJobProperties

An object that contains the properties associated with an entities detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeEntityRecognizer

$result = $client->describeEntityRecognizer([/* ... */]);
$promise = $client->describeEntityRecognizerAsync([/* ... */]);

Provides details about an entity recognizer including status, S3 buckets containing training data, recognizer metadata, metrics, and so on.

Parameter Syntax

$result = $client->describeEntityRecognizer([
    'EntityRecognizerArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
EntityRecognizerArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) that identifies the entity recognizer.

Result Syntax

[
    'EntityRecognizerProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'EntityRecognizerArn' => '<string>',
        'FlywheelArn' => '<string>',
        'InputDataConfig' => [
            'Annotations' => [
                'S3Uri' => '<string>',
                'TestS3Uri' => '<string>',
            ],
            'AugmentedManifests' => [
                [
                    'AnnotationDataS3Uri' => '<string>',
                    'AttributeNames' => ['<string>', ...],
                    'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                    'S3Uri' => '<string>',
                    'SourceDocumentsS3Uri' => '<string>',
                    'Split' => 'TRAIN|TEST',
                ],
                // ...
            ],
            'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
            'Documents' => [
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
                'TestS3Uri' => '<string>',
            ],
            'EntityList' => [
                'S3Uri' => '<string>',
            ],
            'EntityTypes' => [
                [
                    'Type' => '<string>',
                ],
                // ...
            ],
        ],
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'ModelKmsKeyId' => '<string>',
        'OutputDataConfig' => [
            'FlywheelStatsS3Prefix' => '<string>',
        ],
        'RecognizerMetadata' => [
            'EntityTypes' => [
                [
                    'EvaluationMetrics' => [
                        'F1Score' => <float>,
                        'Precision' => <float>,
                        'Recall' => <float>,
                    ],
                    'NumberOfTrainMentions' => <integer>,
                    'Type' => '<string>',
                ],
                // ...
            ],
            'EvaluationMetrics' => [
                'F1Score' => <float>,
                'Precision' => <float>,
                'Recall' => <float>,
            ],
            'NumberOfTestDocuments' => <integer>,
            'NumberOfTrainedDocuments' => <integer>,
        ],
        'SourceModelArn' => '<string>',
        'Status' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
        'SubmitTime' => <DateTime>,
        'TrainingEndTime' => <DateTime>,
        'TrainingStartTime' => <DateTime>,
        'VersionName' => '<string>',
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
EntityRecognizerProperties
Type: EntityRecognizerProperties structure

Describes information associated with an entity recognizer.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeEventsDetectionJob

$result = $client->describeEventsDetectionJob([/* ... */]);
$promise = $client->describeEventsDetectionJobAsync([/* ... */]);

Gets the status and details of an events detection job.

Parameter Syntax

$result = $client->describeEventsDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the events detection job.

Result Syntax

[
    'EventsDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'TargetEventTypes' => ['<string>', ...],
    ],
]

Result Details

Members
EventsDetectionJobProperties

An object that contains the properties associated with an event detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeFlywheel

$result = $client->describeFlywheel([/* ... */]);
$promise = $client->describeFlywheelAsync([/* ... */]);

Provides configuration information about the flywheel. For more information about flywheels, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->describeFlywheel([
    'FlywheelArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
FlywheelArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the flywheel.

Result Syntax

[
    'FlywheelProperties' => [
        'ActiveModelArn' => '<string>',
        'CreationTime' => <DateTime>,
        'DataAccessRoleArn' => '<string>',
        'DataLakeS3Uri' => '<string>',
        'DataSecurityConfig' => [
            'DataLakeKmsKeyId' => '<string>',
            'ModelKmsKeyId' => '<string>',
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        'FlywheelArn' => '<string>',
        'LastModifiedTime' => <DateTime>,
        'LatestFlywheelIteration' => '<string>',
        'Message' => '<string>',
        'ModelType' => 'DOCUMENT_CLASSIFIER|ENTITY_RECOGNIZER',
        'Status' => 'CREATING|ACTIVE|UPDATING|DELETING|FAILED',
        'TaskConfig' => [
            'DocumentClassificationConfig' => [
                'Labels' => ['<string>', ...],
                'Mode' => 'MULTI_CLASS|MULTI_LABEL',
            ],
            'EntityRecognitionConfig' => [
                'EntityTypes' => [
                    [
                        'Type' => '<string>',
                    ],
                    // ...
                ],
            ],
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        ],
    ],
]

Result Details

Members
FlywheelProperties
Type: FlywheelProperties structure

The flywheel properties.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeFlywheelIteration

$result = $client->describeFlywheelIteration([/* ... */]);
$promise = $client->describeFlywheelIterationAsync([/* ... */]);

Retrieve the configuration properties of a flywheel iteration. For more information about flywheels, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->describeFlywheelIteration([
    'FlywheelArn' => '<string>', // REQUIRED
    'FlywheelIterationId' => '<string>', // REQUIRED
]);

Parameter Details

Members
FlywheelArn
Required: Yes
Type: string

FlywheelIterationId
Required: Yes
Type: string

Result Syntax

[
    'FlywheelIterationProperties' => [
        'CreationTime' => <DateTime>,
        'EndTime' => <DateTime>,
        'EvaluatedModelArn' => '<string>',
        'EvaluatedModelMetrics' => [
            'AverageAccuracy' => <float>,
            'AverageF1Score' => <float>,
            'AveragePrecision' => <float>,
            'AverageRecall' => <float>,
        ],
        'EvaluationManifestS3Prefix' => '<string>',
        'FlywheelArn' => '<string>',
        'FlywheelIterationId' => '<string>',
        'Message' => '<string>',
        'Status' => 'TRAINING|EVALUATING|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'TrainedModelArn' => '<string>',
        'TrainedModelMetrics' => [
            'AverageAccuracy' => <float>,
            'AverageF1Score' => <float>,
            'AveragePrecision' => <float>,
            'AverageRecall' => <float>,
        ],
    ],
]

Result Details

Members
FlywheelIterationProperties
Type: FlywheelIterationProperties structure

The configuration properties of a flywheel iteration.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeKeyPhrasesDetectionJob

$result = $client->describeKeyPhrasesDetectionJob([/* ... */]);
$promise = $client->describeKeyPhrasesDetectionJobAsync([/* ... */]);

Gets the properties associated with a key phrases detection job. Use this operation to get the status of a detection job.

Parameter Syntax

$result = $client->describeKeyPhrasesDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The StartKeyPhrasesDetectionJob operation returns this identifier in its response.

Result Syntax

[
    'KeyPhrasesDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
KeyPhrasesDetectionJobProperties

An object that contains the properties associated with a key phrases detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribePiiEntitiesDetectionJob

$result = $client->describePiiEntitiesDetectionJob([/* ... */]);
$promise = $client->describePiiEntitiesDetectionJobAsync([/* ... */]);

Gets the properties associated with a PII entities detection job. For example, you can use this operation to get the job status.

Parameter Syntax

$result = $client->describePiiEntitiesDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.

Result Syntax

[
    'PiiEntitiesDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'Mode' => 'ONLY_REDACTION|ONLY_OFFSETS',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'RedactionConfig' => [
            'MaskCharacter' => '<string>',
            'MaskMode' => 'MASK|REPLACE_WITH_PII_ENTITY_TYPE',
            'PiiEntityTypes' => ['<string>', ...],
        ],
        'SubmitTime' => <DateTime>,
    ],
]

Result Details

Members
PiiEntitiesDetectionJobProperties

Provides information about a PII entities detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeResourcePolicy

$result = $client->describeResourcePolicy([/* ... */]);
$promise = $client->describeResourcePolicyAsync([/* ... */]);

Gets the details of a resource-based policy that is attached to a custom model, including the JSON body of the policy.

Parameter Syntax

$result = $client->describeResourcePolicy([
    'ResourceArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
ResourceArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the custom model version that has the resource policy.

Result Syntax

[
    'CreationTime' => <DateTime>,
    'LastModifiedTime' => <DateTime>,
    'PolicyRevisionId' => '<string>',
    'ResourcePolicy' => '<string>',
]

Result Details

Members
CreationTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time at which the policy was created.

LastModifiedTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time at which the policy was last modified.

PolicyRevisionId
Type: string

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.

ResourcePolicy
Type: string

The JSON body of the resource-based policy.

Errors

InvalidRequestException:

The request is invalid.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeSentimentDetectionJob

$result = $client->describeSentimentDetectionJob([/* ... */]);
$promise = $client->describeSentimentDetectionJobAsync([/* ... */]);

Gets the properties associated with a sentiment detection job. Use this operation to get the status of a detection job.

Parameter Syntax

$result = $client->describeSentimentDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The operation returns this identifier in its response.

Result Syntax

[
    'SentimentDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
SentimentDetectionJobProperties

An object that contains the properties associated with a sentiment detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeTargetedSentimentDetectionJob

$result = $client->describeTargetedSentimentDetectionJob([/* ... */]);
$promise = $client->describeTargetedSentimentDetectionJobAsync([/* ... */]);

Gets the properties associated with a targeted sentiment detection job. Use this operation to get the status of the job.

Parameter Syntax

$result = $client->describeTargetedSentimentDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier that Amazon Comprehend generated for the job. The StartTargetedSentimentDetectionJob operation returns this identifier in its response.

Result Syntax

[
    'TargetedSentimentDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        'Message' => '<string>',
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
TargetedSentimentDetectionJobProperties

An object that contains the properties associated with a targeted sentiment detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DescribeTopicsDetectionJob

$result = $client->describeTopicsDetectionJob([/* ... */]);
$promise = $client->describeTopicsDetectionJobAsync([/* ... */]);

Gets the properties associated with a topic detection job. Use this operation to get the status of a detection job.

Parameter Syntax

$result = $client->describeTopicsDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier assigned by the user to the detection job.

Result Syntax

[
    'TopicsDetectionJobProperties' => [
        'DataAccessRoleArn' => '<string>',
        'EndTime' => <DateTime>,
        'InputDataConfig' => [
            'DocumentReaderConfig' => [
                'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                'FeatureTypes' => ['<string>', ...],
            ],
            'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
            'S3Uri' => '<string>',
        ],
        'JobArn' => '<string>',
        'JobId' => '<string>',
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'Message' => '<string>',
        'NumberOfTopics' => <integer>,
        'OutputDataConfig' => [
            'KmsKeyId' => '<string>',
            'S3Uri' => '<string>',
        ],
        'SubmitTime' => <DateTime>,
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...],
            'Subnets' => ['<string>', ...],
        ],
    ],
]

Result Details

Members
TopicsDetectionJobProperties

The list of properties for the requested job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

DetectDominantLanguage

$result = $client->detectDominantLanguage([/* ... */]);
$promise = $client->detectDominantLanguageAsync([/* ... */]);

Determines the dominant language of the input text. For a list of languages that Amazon Comprehend can detect, see Amazon Comprehend Supported Languages.

Parameter Syntax

$result = $client->detectDominantLanguage([
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
Text
Required: Yes
Type: string

A UTF-8 text string. The string must contain at least 20 characters. The maximum string size is 100 KB.

Result Syntax

[
    'Languages' => [
        [
            'LanguageCode' => '<string>',
            'Score' => <float>,
        ],
        // ...
    ],
]

Result Details

Members
Languages
Type: Array of DominantLanguage structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

InternalServerException:

An internal server error occurred. Retry your request.

DetectEntities

$result = $client->detectEntities([/* ... */]);
$promise = $client->detectEntitiesAsync([/* ... */]);

Detects named entities in input text when you use the pre-trained model. Detects custom entities if you have a custom entity recognition model.

When detecting named entities using the pre-trained model, use plain text as the input. For more information about named entities, see Entities in the Comprehend Developer Guide.

When you use a custom entity recognition model, you can input plain text or you can upload a single-page input document (text, PDF, Word, or image).

If the system detects errors while processing a page in the input document, the API response includes an entry in Errors for each error.

If the system detects a document-level error in your input document, the API returns an InvalidRequestException error response. For details about this exception, see Errors in semi-structured documents in the Comprehend Developer Guide.

Parameter Syntax

$result = $client->detectEntities([
    'Bytes' => <string || resource || Psr\Http\Message\StreamInterface>,
    'DocumentReaderConfig' => [
        'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
        'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
        'FeatureTypes' => ['<string>', ...],
    ],
    'EndpointArn' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
    'Text' => '<string>',
]);

Parameter Details

Members
Bytes
Type: blob (string|resource|Psr\Http\Message\StreamInterface)

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
Type: DocumentReaderConfig structure

Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

EndpointArn
Type: string

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.

LanguageCode
Type: string

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.

Text
Type: string

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.

Result Syntax

[
    'Blocks' => [
        [
            'BlockType' => 'LINE|WORD',
            'Geometry' => [
                'BoundingBox' => [
                    'Height' => <float>,
                    'Left' => <float>,
                    'Top' => <float>,
                    'Width' => <float>,
                ],
                'Polygon' => [
                    [
                        'X' => <float>,
                        'Y' => <float>,
                    ],
                    // ...
                ],
            ],
            'Id' => '<string>',
            'Page' => <integer>,
            'Relationships' => [
                [
                    'Ids' => ['<string>', ...],
                    'Type' => 'CHILD',
                ],
                // ...
            ],
            'Text' => '<string>',
        ],
        // ...
    ],
    'DocumentMetadata' => [
        'ExtractedCharacters' => [
            [
                'Count' => <integer>,
                'Page' => <integer>,
            ],
            // ...
        ],
        'Pages' => <integer>,
    ],
    'DocumentType' => [
        [
            'Page' => <integer>,
            'Type' => 'NATIVE_PDF|SCANNED_PDF|MS_WORD|IMAGE|PLAIN_TEXT|TEXTRACT_DETECT_DOCUMENT_TEXT_JSON|TEXTRACT_ANALYZE_DOCUMENT_JSON',
        ],
        // ...
    ],
    'Entities' => [
        [
            'BeginOffset' => <integer>,
            'BlockReferences' => [
                [
                    'BeginOffset' => <integer>,
                    'BlockId' => '<string>',
                    'ChildBlocks' => [
                        [
                            'BeginOffset' => <integer>,
                            'ChildBlockId' => '<string>',
                            'EndOffset' => <integer>,
                        ],
                        // ...
                    ],
                    'EndOffset' => <integer>,
                ],
                // ...
            ],
            'EndOffset' => <integer>,
            'Score' => <float>,
            'Text' => '<string>',
            'Type' => 'PERSON|LOCATION|ORGANIZATION|COMMERCIAL_ITEM|EVENT|DATE|QUANTITY|TITLE|OTHER',
        ],
        // ...
    ],
    'Errors' => [
        [
            'ErrorCode' => 'TEXTRACT_BAD_PAGE|TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED|PAGE_CHARACTERS_EXCEEDED|PAGE_SIZE_EXCEEDED|INTERNAL_SERVER_ERROR',
            'ErrorMessage' => '<string>',
            'Page' => <integer>,
        ],
        // ...
    ],
]

Result Details

Members
Blocks
Type: Array of Block structures

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.

DocumentMetadata
Type: DocumentMetadata structure

Information about the document, discovered during text extraction. This field is present in the response only if your request used the Byte parameter.

DocumentType
Type: Array of DocumentTypeListItem structures

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.

Entities
Type: Array of Entity structures

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.

Errors
Type: Array of ErrorsListItem structures

Page-level errors that the system detected while processing the input document. The field is empty if the system encountered no errors.

Errors

InvalidRequestException:

The request is invalid.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

DetectKeyPhrases

$result = $client->detectKeyPhrases([/* ... */]);
$promise = $client->detectKeyPhrasesAsync([/* ... */]);

Detects the key noun phrases found in the text.

Parameter Syntax

$result = $client->detectKeyPhrases([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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.

Text
Required: Yes
Type: string

A UTF-8 text string. The string must contain less than 100 KB of UTF-8 encoded characters.

Result Syntax

[
    'KeyPhrases' => [
        [
            'BeginOffset' => <integer>,
            'EndOffset' => <integer>,
            'Score' => <float>,
            'Text' => '<string>',
        ],
        // ...
    ],
]

Result Details

Members
KeyPhrases
Type: Array of KeyPhrase structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

DetectPiiEntities

$result = $client->detectPiiEntities([/* ... */]);
$promise = $client->detectPiiEntitiesAsync([/* ... */]);

Inspects the input text for entities that contain personally identifiable information (PII) and returns information about them.

Parameter Syntax

$result = $client->detectPiiEntities([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

The language of the input text. Enter the language code for English (en) or Spanish (es).

Text
Required: Yes
Type: string

A UTF-8 text string. The maximum string size is 100 KB.

Result Syntax

[
    'Entities' => [
        [
            'BeginOffset' => <integer>,
            'EndOffset' => <integer>,
            'Score' => <float>,
            'Type' => 'BANK_ACCOUNT_NUMBER|BANK_ROUTING|CREDIT_DEBIT_NUMBER|CREDIT_DEBIT_CVV|CREDIT_DEBIT_EXPIRY|PIN|EMAIL|ADDRESS|NAME|PHONE|SSN|DATE_TIME|PASSPORT_NUMBER|DRIVER_ID|URL|AGE|USERNAME|PASSWORD|AWS_ACCESS_KEY|AWS_SECRET_KEY|IP_ADDRESS|MAC_ADDRESS|ALL|LICENSE_PLATE|VEHICLE_IDENTIFICATION_NUMBER|UK_NATIONAL_INSURANCE_NUMBER|CA_SOCIAL_INSURANCE_NUMBER|US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER|UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER|IN_PERMANENT_ACCOUNT_NUMBER|IN_NREGA|INTERNATIONAL_BANK_ACCOUNT_NUMBER|SWIFT_CODE|UK_NATIONAL_HEALTH_SERVICE_NUMBER|CA_HEALTH_NUMBER|IN_AADHAAR|IN_VOTER_NUMBER',
        ],
        // ...
    ],
]

Result Details

Members
Entities
Type: Array of PiiEntity structures

A collection of PII entities identified in the input text. For each entity, the response provides the entity type, where the entity text begins and ends, and the level of confidence that Amazon Comprehend has in the detection.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

DetectSentiment

$result = $client->detectSentiment([/* ... */]);
$promise = $client->detectSentimentAsync([/* ... */]);

Inspects text and returns an inference of the prevailing sentiment (POSITIVE, NEUTRAL, MIXED, or NEGATIVE).

Parameter Syntax

$result = $client->detectSentiment([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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.

Text
Required: Yes
Type: string

A UTF-8 text string. The maximum string size is 5 KB.

Result Syntax

[
    'Sentiment' => 'POSITIVE|NEGATIVE|NEUTRAL|MIXED',
    'SentimentScore' => [
        'Mixed' => <float>,
        'Negative' => <float>,
        'Neutral' => <float>,
        'Positive' => <float>,
    ],
]

Result Details

Members
Sentiment
Type: string

The inferred sentiment that Amazon Comprehend has the highest level of confidence in.

SentimentScore
Type: SentimentScore structure

An object that lists the sentiments, and their corresponding confidence levels.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

DetectSyntax

$result = $client->detectSyntax([/* ... */]);
$promise = $client->detectSyntaxAsync([/* ... */]);

Inspects text for syntax and the part of speech of words in the document. For more information, see Syntax in the Comprehend Developer Guide.

Parameter Syntax

$result = $client->detectSyntax([
    'LanguageCode' => 'en|es|fr|de|it|pt', // REQUIRED
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

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").

Text
Required: Yes
Type: string

A UTF-8 string. The maximum string size is 5 KB.

Result Syntax

[
    'SyntaxTokens' => [
        [
            'BeginOffset' => <integer>,
            'EndOffset' => <integer>,
            'PartOfSpeech' => [
                'Score' => <float>,
                'Tag' => 'ADJ|ADP|ADV|AUX|CONJ|CCONJ|DET|INTJ|NOUN|NUM|O|PART|PRON|PROPN|PUNCT|SCONJ|SYM|VERB',
            ],
            'Text' => '<string>',
            'TokenId' => <integer>,
        ],
        // ...
    ],
]

Result Details

Members
SyntaxTokens
Type: Array of SyntaxToken structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

DetectTargetedSentiment

$result = $client->detectTargetedSentiment([/* ... */]);
$promise = $client->detectTargetedSentimentAsync([/* ... */]);

Inspects the input text and returns a sentiment analysis for each entity identified in the text.

For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->detectTargetedSentiment([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Text' => '<string>', // REQUIRED
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

The language of the input documents. Currently, English is the only supported language.

Text
Required: Yes
Type: string

A UTF-8 text string. The maximum string length is 5 KB.

Result Syntax

[
    'Entities' => [
        [
            'DescriptiveMentionIndex' => [<integer>, ...],
            'Mentions' => [
                [
                    'BeginOffset' => <integer>,
                    'EndOffset' => <integer>,
                    'GroupScore' => <float>,
                    'MentionSentiment' => [
                        'Sentiment' => 'POSITIVE|NEGATIVE|NEUTRAL|MIXED',
                        'SentimentScore' => [
                            'Mixed' => <float>,
                            'Negative' => <float>,
                            'Neutral' => <float>,
                            'Positive' => <float>,
                        ],
                    ],
                    'Score' => <float>,
                    'Text' => '<string>',
                    'Type' => 'PERSON|LOCATION|ORGANIZATION|FACILITY|BRAND|COMMERCIAL_ITEM|MOVIE|MUSIC|BOOK|SOFTWARE|GAME|PERSONAL_TITLE|EVENT|DATE|QUANTITY|ATTRIBUTE|OTHER',
                ],
                // ...
            ],
        ],
        // ...
    ],
]

Result Details

Members
Entities
Type: Array of TargetedSentimentEntity structures

Targeted sentiment analysis for each of the entities identified in the input text.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

DetectToxicContent

$result = $client->detectToxicContent([/* ... */]);
$promise = $client->detectToxicContentAsync([/* ... */]);

Performs toxicity analysis on the list of text strings that you provide as input. The API response contains a results list that matches the size of the input list. For more information about toxicity detection, see Toxicity detection in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->detectToxicContent([
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'TextSegments' => [ // REQUIRED
        [
            'Text' => '<string>', // REQUIRED
        ],
        // ...
    ],
]);

Parameter Details

Members
LanguageCode
Required: Yes
Type: string

The language of the input text. Currently, English is the only supported language.

TextSegments
Required: Yes
Type: Array of TextSegment structures

A list of up to 10 text strings. Each string has a maximum size of 1 KB, and the maximum size of the list is 10 KB.

Result Syntax

[
    'ResultList' => [
        [
            'Labels' => [
                [
                    'Name' => 'GRAPHIC|HARASSMENT_OR_ABUSE|HATE_SPEECH|INSULT|PROFANITY|SEXUAL|VIOLENCE_OR_THREAT',
                    'Score' => <float>,
                ],
                // ...
            ],
            'Toxicity' => <float>,
        ],
        // ...
    ],
]

Result Details

Members
ResultList
Type: Array of ToxicLabels structures

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.

Errors

InvalidRequestException:

The request is invalid.

TextSizeLimitExceededException:

The size of the input text exceeds the limit. Use a smaller document.

UnsupportedLanguageException:

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

InternalServerException:

An internal server error occurred. Retry your request.

ImportModel

$result = $client->importModel([/* ... */]);
$promise = $client->importModelAsync([/* ... */]);

Creates a new custom model that replicates a source custom model that you import. The source model can be in your Amazon Web Services account or another one.

If the source model is in another Amazon Web Services account, then it must have a resource-based policy that authorizes you to import it.

The source model must be in the same Amazon Web Services Region that you're using when you import. You can't import a model that's in a different Region.

Parameter Syntax

$result = $client->importModel([
    'DataAccessRoleArn' => '<string>',
    'ModelKmsKeyId' => '<string>',
    'ModelName' => '<string>',
    'SourceModelArn' => '<string>', // REQUIRED
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VersionName' => '<string>',
]);

Parameter Details

Members
DataAccessRoleArn
Type: string

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.

ModelKmsKeyId
Type: string

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"

ModelName
Type: string

The name to assign to the custom model that is created in Amazon Comprehend by this import.

SourceModelArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the custom model to import.

Tags
Type: Array of Tag structures

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.

VersionName
Type: string

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.

Result Syntax

[
    'ModelArn' => '<string>',
]

Result Details

Members
ModelArn
Type: string

The Amazon Resource Name (ARN) of the custom model being imported.

Errors

InvalidRequestException:

The request is invalid.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

InternalServerException:

An internal server error occurred. Retry your request.

ListDatasets

$result = $client->listDatasets([/* ... */]);
$promise = $client->listDatasetsAsync([/* ... */]);

List the datasets that you have configured in this Region. For more information about datasets, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->listDatasets([
    'Filter' => [
        'CreationTimeAfter' => <integer || string || DateTime>,
        'CreationTimeBefore' => <integer || string || DateTime>,
        'DatasetType' => 'TRAIN|TEST',
        'Status' => 'CREATING|COMPLETED|FAILED',
    ],
    'FlywheelArn' => '<string>',
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: DatasetFilter structure

Filters the datasets to be returned in the response.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel.

MaxResults
Type: int

Maximum number of results to return in a response. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'DatasetPropertiesList' => [
        [
            'CreationTime' => <DateTime>,
            'DatasetArn' => '<string>',
            'DatasetName' => '<string>',
            'DatasetS3Uri' => '<string>',
            'DatasetType' => 'TRAIN|TEST',
            'Description' => '<string>',
            'EndTime' => <DateTime>,
            'Message' => '<string>',
            'NumberOfDocuments' => <integer>,
            'Status' => 'CREATING|COMPLETED|FAILED',
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
DatasetPropertiesList
Type: Array of DatasetProperties structures

The dataset properties list.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

ListDocumentClassificationJobs

$result = $client->listDocumentClassificationJobs([/* ... */]);
$promise = $client->listDocumentClassificationJobsAsync([/* ... */]);

Gets a list of the documentation classification jobs that you have submitted.

Parameter Syntax

$result = $client->listDocumentClassificationJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'DocumentClassificationJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'DocumentClassifierArn' => '<string>',
            'EndTime' => <DateTime>,
            'FlywheelArn' => '<string>',
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
DocumentClassificationJobPropertiesList
Type: Array of DocumentClassificationJobProperties structures

A list containing the properties of each job returned.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListDocumentClassifierSummaries

$result = $client->listDocumentClassifierSummaries([/* ... */]);
$promise = $client->listDocumentClassifierSummariesAsync([/* ... */]);

Gets a list of summaries of the document classifiers that you have created

Parameter Syntax

$result = $client->listDocumentClassifierSummaries([
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
MaxResults
Type: int

The maximum number of results to return on each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'DocumentClassifierSummariesList' => [
        [
            'DocumentClassifierName' => '<string>',
            'LatestVersionCreatedAt' => <DateTime>,
            'LatestVersionName' => '<string>',
            'LatestVersionStatus' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
            'NumberOfVersions' => <integer>,
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
DocumentClassifierSummariesList
Type: Array of DocumentClassifierSummary structures

The list of summaries of document classifiers.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

ListDocumentClassifiers

$result = $client->listDocumentClassifiers([/* ... */]);
$promise = $client->listDocumentClassifiersAsync([/* ... */]);

Gets a list of the document classifiers that you have created.

Parameter Syntax

$result = $client->listDocumentClassifiers([
    'Filter' => [
        'DocumentClassifierName' => '<string>',
        'Status' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: DocumentClassifierFilter structure

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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'DocumentClassifierPropertiesList' => [
        [
            'ClassifierMetadata' => [
                'EvaluationMetrics' => [
                    'Accuracy' => <float>,
                    'F1Score' => <float>,
                    'HammingLoss' => <float>,
                    'MicroF1Score' => <float>,
                    'MicroPrecision' => <float>,
                    'MicroRecall' => <float>,
                    'Precision' => <float>,
                    'Recall' => <float>,
                ],
                'NumberOfLabels' => <integer>,
                'NumberOfTestDocuments' => <integer>,
                'NumberOfTrainedDocuments' => <integer>,
            ],
            'DataAccessRoleArn' => '<string>',
            'DocumentClassifierArn' => '<string>',
            'EndTime' => <DateTime>,
            'FlywheelArn' => '<string>',
            'InputDataConfig' => [
                'AugmentedManifests' => [
                    [
                        'AnnotationDataS3Uri' => '<string>',
                        'AttributeNames' => ['<string>', ...],
                        'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                        'S3Uri' => '<string>',
                        'SourceDocumentsS3Uri' => '<string>',
                        'Split' => 'TRAIN|TEST',
                    ],
                    // ...
                ],
                'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                'Documents' => [
                    'S3Uri' => '<string>',
                    'TestS3Uri' => '<string>',
                ],
                'LabelDelimiter' => '<string>',
                'S3Uri' => '<string>',
                'TestS3Uri' => '<string>',
            ],
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'Mode' => 'MULTI_CLASS|MULTI_LABEL',
            'ModelKmsKeyId' => '<string>',
            'OutputDataConfig' => [
                'FlywheelStatsS3Prefix' => '<string>',
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SourceModelArn' => '<string>',
            'Status' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
            'SubmitTime' => <DateTime>,
            'TrainingEndTime' => <DateTime>,
            'TrainingStartTime' => <DateTime>,
            'VersionName' => '<string>',
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
DocumentClassifierPropertiesList
Type: Array of DocumentClassifierProperties structures

A list containing the properties of each job returned.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListDominantLanguageDetectionJobs

$result = $client->listDominantLanguageDetectionJobs([/* ... */]);
$promise = $client->listDominantLanguageDetectionJobsAsync([/* ... */]);

Gets a list of the dominant language detection jobs that you have submitted.

Parameter Syntax

$result = $client->listDominantLanguageDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'DominantLanguageDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
DominantLanguageDetectionJobPropertiesList
Type: Array of DominantLanguageDetectionJobProperties structures

A list containing the properties of each job that is returned.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListEndpoints

$result = $client->listEndpoints([/* ... */]);
$promise = $client->listEndpointsAsync([/* ... */]);

Gets a list of all existing endpoints that you've created. For information about endpoints, see Managing endpoints.

Parameter Syntax

$result = $client->listEndpoints([
    'Filter' => [
        'CreationTimeAfter' => <integer || string || DateTime>,
        'CreationTimeBefore' => <integer || string || DateTime>,
        'ModelArn' => '<string>',
        'Status' => 'CREATING|DELETING|FAILED|IN_SERVICE|UPDATING',
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: EndpointFilter structure

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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'EndpointPropertiesList' => [
        [
            'CreationTime' => <DateTime>,
            'CurrentInferenceUnits' => <integer>,
            'DataAccessRoleArn' => '<string>',
            'DesiredDataAccessRoleArn' => '<string>',
            'DesiredInferenceUnits' => <integer>,
            'DesiredModelArn' => '<string>',
            'EndpointArn' => '<string>',
            'FlywheelArn' => '<string>',
            'LastModifiedTime' => <DateTime>,
            'Message' => '<string>',
            'ModelArn' => '<string>',
            'Status' => 'CREATING|DELETING|FAILED|IN_SERVICE|UPDATING',
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
EndpointPropertiesList
Type: Array of EndpointProperties structures

Displays a list of endpoint properties being retrieved by the service in response to the request.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

ListEntitiesDetectionJobs

$result = $client->listEntitiesDetectionJobs([/* ... */]);
$promise = $client->listEntitiesDetectionJobsAsync([/* ... */]);

Gets a list of the entity detection jobs that you have submitted.

Parameter Syntax

$result = $client->listEntitiesDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: EntitiesDetectionJobFilter structure

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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'EntitiesDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'EntityRecognizerArn' => '<string>',
            'FlywheelArn' => '<string>',
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
EntitiesDetectionJobPropertiesList
Type: Array of EntitiesDetectionJobProperties structures

A list containing the properties of each job that is returned.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListEntityRecognizerSummaries

$result = $client->listEntityRecognizerSummaries([/* ... */]);
$promise = $client->listEntityRecognizerSummariesAsync([/* ... */]);

Gets a list of summaries for the entity recognizers that you have created.

Parameter Syntax

$result = $client->listEntityRecognizerSummaries([
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
MaxResults
Type: int

The maximum number of results to return on each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'EntityRecognizerSummariesList' => [
        [
            'LatestVersionCreatedAt' => <DateTime>,
            'LatestVersionName' => '<string>',
            'LatestVersionStatus' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
            'NumberOfVersions' => <integer>,
            'RecognizerName' => '<string>',
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
EntityRecognizerSummariesList
Type: Array of EntityRecognizerSummary structures

The list entity recognizer summaries.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InternalServerException:

An internal server error occurred. Retry your request.

ListEntityRecognizers

$result = $client->listEntityRecognizers([/* ... */]);
$promise = $client->listEntityRecognizersAsync([/* ... */]);

Gets a list of the properties of all entity recognizers that you created, including recognizers currently in training. Allows you to filter the list of recognizers based on criteria such as status and submission time. This call returns up to 500 entity recognizers in the list, with a default number of 100 recognizers in the list.

The results of this list are not in any particular order. Please get the list and sort locally if needed.

Parameter Syntax

$result = $client->listEntityRecognizers([
    'Filter' => [
        'RecognizerName' => '<string>',
        'Status' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: EntityRecognizerFilter structure

Filters the list of entities returned. You can filter on Status, SubmitTimeBefore, or SubmitTimeAfter. You can only set one filter at a time.

MaxResults
Type: int

The maximum number of results to return on each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'EntityRecognizerPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'EntityRecognizerArn' => '<string>',
            'FlywheelArn' => '<string>',
            'InputDataConfig' => [
                'Annotations' => [
                    'S3Uri' => '<string>',
                    'TestS3Uri' => '<string>',
                ],
                'AugmentedManifests' => [
                    [
                        'AnnotationDataS3Uri' => '<string>',
                        'AttributeNames' => ['<string>', ...],
                        'DocumentType' => 'PLAIN_TEXT_DOCUMENT|SEMI_STRUCTURED_DOCUMENT',
                        'S3Uri' => '<string>',
                        'SourceDocumentsS3Uri' => '<string>',
                        'Split' => 'TRAIN|TEST',
                    ],
                    // ...
                ],
                'DataFormat' => 'COMPREHEND_CSV|AUGMENTED_MANIFEST',
                'Documents' => [
                    'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                    'S3Uri' => '<string>',
                    'TestS3Uri' => '<string>',
                ],
                'EntityList' => [
                    'S3Uri' => '<string>',
                ],
                'EntityTypes' => [
                    [
                        'Type' => '<string>',
                    ],
                    // ...
                ],
            ],
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'ModelKmsKeyId' => '<string>',
            'OutputDataConfig' => [
                'FlywheelStatsS3Prefix' => '<string>',
            ],
            'RecognizerMetadata' => [
                'EntityTypes' => [
                    [
                        'EvaluationMetrics' => [
                            'F1Score' => <float>,
                            'Precision' => <float>,
                            'Recall' => <float>,
                        ],
                        'NumberOfTrainMentions' => <integer>,
                        'Type' => '<string>',
                    ],
                    // ...
                ],
                'EvaluationMetrics' => [
                    'F1Score' => <float>,
                    'Precision' => <float>,
                    'Recall' => <float>,
                ],
                'NumberOfTestDocuments' => <integer>,
                'NumberOfTrainedDocuments' => <integer>,
            ],
            'SourceModelArn' => '<string>',
            'Status' => 'SUBMITTED|TRAINING|DELETING|STOP_REQUESTED|STOPPED|IN_ERROR|TRAINED|TRAINED_WITH_WARNING',
            'SubmitTime' => <DateTime>,
            'TrainingEndTime' => <DateTime>,
            'TrainingStartTime' => <DateTime>,
            'VersionName' => '<string>',
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
EntityRecognizerPropertiesList
Type: Array of EntityRecognizerProperties structures

The list of properties of an entity recognizer.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListEventsDetectionJobs

$result = $client->listEventsDetectionJobs([/* ... */]);
$promise = $client->listEventsDetectionJobsAsync([/* ... */]);

Gets a list of the events detection jobs that you have submitted.

Parameter Syntax

$result = $client->listEventsDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: EventsDetectionJobFilter structure

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.

MaxResults
Type: int

The maximum number of results to return in each page.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'EventsDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'TargetEventTypes' => ['<string>', ...],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
EventsDetectionJobPropertiesList
Type: Array of EventsDetectionJobProperties structures

A list containing the properties of each job that is returned.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListFlywheelIterationHistory

$result = $client->listFlywheelIterationHistory([/* ... */]);
$promise = $client->listFlywheelIterationHistoryAsync([/* ... */]);

Information about the history of a flywheel iteration. For more information about flywheels, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->listFlywheelIterationHistory([
    'Filter' => [
        'CreationTimeAfter' => <integer || string || DateTime>,
        'CreationTimeBefore' => <integer || string || DateTime>,
    ],
    'FlywheelArn' => '<string>', // REQUIRED
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: FlywheelIterationFilter structure

Filter the flywheel iteration history based on creation time.

FlywheelArn
Required: Yes
Type: string

The ARN of the flywheel.

MaxResults
Type: int

Maximum number of iteration history results to return

NextToken
Type: string

Next token

Result Syntax

[
    'FlywheelIterationPropertiesList' => [
        [
            'CreationTime' => <DateTime>,
            'EndTime' => <DateTime>,
            'EvaluatedModelArn' => '<string>',
            'EvaluatedModelMetrics' => [
                'AverageAccuracy' => <float>,
                'AverageF1Score' => <float>,
                'AveragePrecision' => <float>,
                'AverageRecall' => <float>,
            ],
            'EvaluationManifestS3Prefix' => '<string>',
            'FlywheelArn' => '<string>',
            'FlywheelIterationId' => '<string>',
            'Message' => '<string>',
            'Status' => 'TRAINING|EVALUATING|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'TrainedModelArn' => '<string>',
            'TrainedModelMetrics' => [
                'AverageAccuracy' => <float>,
                'AverageF1Score' => <float>,
                'AveragePrecision' => <float>,
                'AverageRecall' => <float>,
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
FlywheelIterationPropertiesList
Type: Array of FlywheelIterationProperties structures

List of flywheel iteration properties

NextToken
Type: string

Next token

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

ListFlywheels

$result = $client->listFlywheels([/* ... */]);
$promise = $client->listFlywheelsAsync([/* ... */]);

Gets a list of the flywheels that you have created.

Parameter Syntax

$result = $client->listFlywheels([
    'Filter' => [
        'CreationTimeAfter' => <integer || string || DateTime>,
        'CreationTimeBefore' => <integer || string || DateTime>,
        'Status' => 'CREATING|ACTIVE|UPDATING|DELETING|FAILED',
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: FlywheelFilter structure

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.

MaxResults
Type: int

Maximum number of results to return in a response. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'FlywheelSummaryList' => [
        [
            'ActiveModelArn' => '<string>',
            'CreationTime' => <DateTime>,
            'DataLakeS3Uri' => '<string>',
            'FlywheelArn' => '<string>',
            'LastModifiedTime' => <DateTime>,
            'LatestFlywheelIteration' => '<string>',
            'Message' => '<string>',
            'ModelType' => 'DOCUMENT_CLASSIFIER|ENTITY_RECOGNIZER',
            'Status' => 'CREATING|ACTIVE|UPDATING|DELETING|FAILED',
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
FlywheelSummaryList
Type: Array of FlywheelSummary structures

A list of flywheel properties retrieved by the service in response to the request.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListKeyPhrasesDetectionJobs

$result = $client->listKeyPhrasesDetectionJobs([/* ... */]);
$promise = $client->listKeyPhrasesDetectionJobsAsync([/* ... */]);

Get a list of key phrase detection jobs that you have submitted.

Parameter Syntax

$result = $client->listKeyPhrasesDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'KeyPhrasesDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
    'NextToken' => '<string>',
]

Result Details

Members
KeyPhrasesDetectionJobPropertiesList
Type: Array of KeyPhrasesDetectionJobProperties structures

A list containing the properties of each job that is returned.

NextToken
Type: string

Identifies the next page of results to return.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListPiiEntitiesDetectionJobs

$result = $client->listPiiEntitiesDetectionJobs([/* ... */]);
$promise = $client->listPiiEntitiesDetectionJobsAsync([/* ... */]);

Gets a list of the PII entity detection jobs that you have submitted.

Parameter Syntax

$result = $client->listPiiEntitiesDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
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.

MaxResults
Type: int

The maximum number of results to return in each page.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'NextToken' => '<string>',
    'PiiEntitiesDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'Mode' => 'ONLY_REDACTION|ONLY_OFFSETS',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'RedactionConfig' => [
                'MaskCharacter' => '<string>',
                'MaskMode' => 'MASK|REPLACE_WITH_PII_ENTITY_TYPE',
                'PiiEntityTypes' => ['<string>', ...],
            ],
            'SubmitTime' => <DateTime>,
        ],
        // ...
    ],
]

Result Details

Members
NextToken
Type: string

Identifies the next page of results to return.

PiiEntitiesDetectionJobPropertiesList
Type: Array of PiiEntitiesDetectionJobProperties structures

A list containing the properties of each job that is returned.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListSentimentDetectionJobs

$result = $client->listSentimentDetectionJobs([/* ... */]);
$promise = $client->listSentimentDetectionJobsAsync([/* ... */]);

Gets a list of sentiment detection jobs that you have submitted.

Parameter Syntax

$result = $client->listSentimentDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: SentimentDetectionJobFilter structure

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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'NextToken' => '<string>',
    'SentimentDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
]

Result Details

Members
NextToken
Type: string

Identifies the next page of results to return.

SentimentDetectionJobPropertiesList
Type: Array of SentimentDetectionJobProperties structures

A list containing the properties of each job that is returned.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListTagsForResource

$result = $client->listTagsForResource([/* ... */]);
$promise = $client->listTagsForResourceAsync([/* ... */]);

Lists all tags associated with a given Amazon Comprehend resource.

Parameter Syntax

$result = $client->listTagsForResource([
    'ResourceArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
ResourceArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.

Result Syntax

[
    'ResourceArn' => '<string>',
    'Tags' => [
        [
            'Key' => '<string>',
            'Value' => '<string>',
        ],
        // ...
    ],
]

Result Details

Members
ResourceArn
Type: string

The Amazon Resource Name (ARN) of the given Amazon Comprehend resource you are querying.

Tags
Type: Array of Tag structures

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.

Errors

InvalidRequestException:

The request is invalid.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

ListTargetedSentimentDetectionJobs

$result = $client->listTargetedSentimentDetectionJobs([/* ... */]);
$promise = $client->listTargetedSentimentDetectionJobsAsync([/* ... */]);

Gets a list of targeted sentiment detection jobs that you have submitted.

Parameter Syntax

$result = $client->listTargetedSentimentDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'NextToken' => '<string>',
    'TargetedSentimentDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
            'Message' => '<string>',
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
]

Result Details

Members
NextToken
Type: string

Identifies the next page of results to return.

TargetedSentimentDetectionJobPropertiesList
Type: Array of TargetedSentimentDetectionJobProperties structures

A list containing the properties of each job that is returned.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

ListTopicsDetectionJobs

$result = $client->listTopicsDetectionJobs([/* ... */]);
$promise = $client->listTopicsDetectionJobsAsync([/* ... */]);

Gets a list of the topic detection jobs that you have submitted.

Parameter Syntax

$result = $client->listTopicsDetectionJobs([
    'Filter' => [
        'JobName' => '<string>',
        'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
        'SubmitTimeAfter' => <integer || string || DateTime>,
        'SubmitTimeBefore' => <integer || string || DateTime>,
    ],
    'MaxResults' => <integer>,
    'NextToken' => '<string>',
]);

Parameter Details

Members
Filter
Type: TopicsDetectionJobFilter structure

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.

MaxResults
Type: int

The maximum number of results to return in each page. The default is 100.

NextToken
Type: string

Identifies the next page of results to return.

Result Syntax

[
    'NextToken' => '<string>',
    'TopicsDetectionJobPropertiesList' => [
        [
            'DataAccessRoleArn' => '<string>',
            'EndTime' => <DateTime>,
            'InputDataConfig' => [
                'DocumentReaderConfig' => [
                    'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT',
                    'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
                    'FeatureTypes' => ['<string>', ...],
                ],
                'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
                'S3Uri' => '<string>',
            ],
            'JobArn' => '<string>',
            'JobId' => '<string>',
            'JobName' => '<string>',
            'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
            'Message' => '<string>',
            'NumberOfTopics' => <integer>,
            'OutputDataConfig' => [
                'KmsKeyId' => '<string>',
                'S3Uri' => '<string>',
            ],
            'SubmitTime' => <DateTime>,
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        // ...
    ],
]

Result Details

Members
NextToken
Type: string

Identifies the next page of results to return.

TopicsDetectionJobPropertiesList
Type: Array of TopicsDetectionJobProperties structures

A list containing the properties of each job that is returned.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

InvalidFilterException:

The filter specified for the operation is invalid. Specify a different filter.

InternalServerException:

An internal server error occurred. Retry your request.

PutResourcePolicy

$result = $client->putResourcePolicy([/* ... */]);
$promise = $client->putResourcePolicyAsync([/* ... */]);

Attaches a resource-based policy to a custom model. You can use this policy to authorize an entity in another Amazon Web Services account to import the custom model, which replicates it in Amazon Comprehend in their account.

Parameter Syntax

$result = $client->putResourcePolicy([
    'PolicyRevisionId' => '<string>',
    'ResourceArn' => '<string>', // REQUIRED
    'ResourcePolicy' => '<string>', // REQUIRED
]);

Parameter Details

Members
PolicyRevisionId
Type: string

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.

ResourceArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the custom model to attach the policy to.

ResourcePolicy
Required: Yes
Type: string

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"]}'

Result Syntax

[
    'PolicyRevisionId' => '<string>',
]

Result Details

Members
PolicyRevisionId
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartDocumentClassificationJob

$result = $client->startDocumentClassificationJob([/* ... */]);
$promise = $client->startDocumentClassificationJobAsync([/* ... */]);

Starts an asynchronous document classification job using a custom classification model. Use the DescribeDocumentClassificationJob operation to track the progress of the job.

Parameter Syntax

$result = $client->startDocumentClassificationJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'DocumentClassifierArn' => '<string>',
    'FlywheelArn' => '<string>',
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

DocumentClassifierArn
Type: string

The Amazon Resource Name (ARN) of the document classifier to use to process the job.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel associated with the model to use.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

The identifier of the job.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'DocumentClassifierArn' => '<string>',
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
DocumentClassifierArn
Type: string

The ARN of the custom classification model.

JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of the job, use this identifier with the DescribeDocumentClassificationJob operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartDominantLanguageDetectionJob

$result = $client->startDominantLanguageDetectionJob([/* ... */]);
$promise = $client->startDominantLanguageDetectionJobAsync([/* ... */]);

Starts an asynchronous dominant language detection job for a collection of documents. Use the operation to track the status of a job.

Parameter Syntax

$result = $client->startDominantLanguageDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

An identifier for the job.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of a job, use this identifier with the operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartEntitiesDetectionJob

$result = $client->startEntitiesDetectionJob([/* ... */]);
$promise = $client->startEntitiesDetectionJobAsync([/* ... */]);

Starts an asynchronous entity detection job for a collection of documents. Use the operation to track the status of a job.

This API can be used for either standard entity detection or custom entity recognition. In order to be used for custom entity recognition, the optional EntityRecognizerArn must be used in order to provide access to the recognizer being used to detect the custom entity.

Parameter Syntax

$result = $client->startEntitiesDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'EntityRecognizerArn' => '<string>',
    'FlywheelArn' => '<string>',
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

EntityRecognizerArn
Type: string

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.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel associated with the model to use.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

The identifier of the job.

LanguageCode
Required: Yes
Type: string

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.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'EntityRecognizerArn' => '<string>',
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
EntityRecognizerArn
Type: string

The ARN of the custom entity recognition model.

JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of job, use this identifier with the operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartEventsDetectionJob

$result = $client->startEventsDetectionJob([/* ... */]);
$promise = $client->startEventsDetectionJobAsync([/* ... */]);

Starts an asynchronous event detection job for a collection of documents.

Parameter Syntax

$result = $client->startEventsDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'TargetEventTypes' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
ClientRequestToken
Type: string

An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

The identifier of the events detection job.

LanguageCode
Required: Yes
Type: string

The language code of the input documents.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

TargetEventTypes
Required: Yes
Type: Array of strings

The types of events to detect in the input documents.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

An unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

JobStatus
Type: string

The status of the events detection job.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartFlywheelIteration

$result = $client->startFlywheelIteration([/* ... */]);
$promise = $client->startFlywheelIterationAsync([/* ... */]);

Start the flywheel iteration.This operation uses any new datasets to train a new model version. For more information about flywheels, see Flywheel overview in the Amazon Comprehend Developer Guide.

Parameter Syntax

$result = $client->startFlywheelIteration([
    'ClientRequestToken' => '<string>',
    'FlywheelArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

FlywheelArn
Required: Yes
Type: string

The ARN of the flywheel.

Result Syntax

[
    'FlywheelArn' => '<string>',
    'FlywheelIterationId' => '<string>',
]

Result Details

Members
FlywheelArn
Type: string

FlywheelIterationId
Type: string

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartKeyPhrasesDetectionJob

$result = $client->startKeyPhrasesDetectionJob([/* ... */]);
$promise = $client->startKeyPhrasesDetectionJobAsync([/* ... */]);

Starts an asynchronous key phrase detection job for a collection of documents. Use the operation to track the status of a job.

Parameter Syntax

$result = $client->startKeyPhrasesDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

The identifier of the job.

LanguageCode
Required: Yes
Type: string

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.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of a job, use this identifier with the operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartPiiEntitiesDetectionJob

$result = $client->startPiiEntitiesDetectionJob([/* ... */]);
$promise = $client->startPiiEntitiesDetectionJobAsync([/* ... */]);

Starts an asynchronous PII entity detection job for a collection of documents.

Parameter Syntax

$result = $client->startPiiEntitiesDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'Mode' => 'ONLY_REDACTION|ONLY_OFFSETS', // REQUIRED
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'RedactionConfig' => [
        'MaskCharacter' => '<string>',
        'MaskMode' => 'MASK|REPLACE_WITH_PII_ENTITY_TYPE',
        'PiiEntityTypes' => ['<string>', ...],
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

The input properties for a PII entities detection job.

JobName
Type: string

The identifier of the job.

LanguageCode
Required: Yes
Type: string

The language of the input documents. Enter the language code for English (en) or Spanish (es).

Mode
Required: Yes
Type: string

Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Provides configuration parameters for the output of PII entity detection jobs.

RedactionConfig
Type: RedactionConfig structure

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.

Tags
Type: Array of Tag structures

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.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job.

JobStatus
Type: string

The status of the job.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartSentimentDetectionJob

$result = $client->startSentimentDetectionJob([/* ... */]);
$promise = $client->startSentimentDetectionJobAsync([/* ... */]);

Starts an asynchronous sentiment detection job for a collection of documents. Use the operation to track the status of a job.

Parameter Syntax

$result = $client->startSentimentDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

The identifier of the job.

LanguageCode
Required: Yes
Type: string

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.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of a job, use this identifier with the operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartTargetedSentimentDetectionJob

$result = $client->startTargetedSentimentDetectionJob([/* ... */]);
$promise = $client->startTargetedSentimentDetectionJobAsync([/* ... */]);

Starts an asynchronous targeted sentiment detection job for a collection of documents. Use the DescribeTargetedSentimentDetectionJob operation to track the status of a job.

Parameter Syntax

$result = $client->startTargetedSentimentDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW', // REQUIRED
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

The input properties for an inference job. The document reader config field applies only to non-text inputs for custom analysis.

JobName
Type: string

The identifier of the job.

LanguageCode
Required: Yes
Type: string

The language of the input documents. Currently, English is the only supported language.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

Specifies where to send the output files.

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for the job. For more information, see Amazon VPC.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of a job, use this identifier with the DescribeTargetedSentimentDetectionJob operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StartTopicsDetectionJob

$result = $client->startTopicsDetectionJob([/* ... */]);
$promise = $client->startTopicsDetectionJobAsync([/* ... */]);

Starts an asynchronous topic detection job. Use the DescribeTopicDetectionJob operation to track the status of a job.

Parameter Syntax

$result = $client->startTopicsDetectionJob([
    'ClientRequestToken' => '<string>',
    'DataAccessRoleArn' => '<string>', // REQUIRED
    'InputDataConfig' => [ // REQUIRED
        'DocumentReaderConfig' => [
            'DocumentReadAction' => 'TEXTRACT_DETECT_DOCUMENT_TEXT|TEXTRACT_ANALYZE_DOCUMENT', // REQUIRED
            'DocumentReadMode' => 'SERVICE_DEFAULT|FORCE_DOCUMENT_READ_ACTION',
            'FeatureTypes' => ['<string>', ...],
        ],
        'InputFormat' => 'ONE_DOC_PER_FILE|ONE_DOC_PER_LINE',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'JobName' => '<string>',
    'NumberOfTopics' => <integer>,
    'OutputDataConfig' => [ // REQUIRED
        'KmsKeyId' => '<string>',
        'S3Uri' => '<string>', // REQUIRED
    ],
    'Tags' => [
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
    'VolumeKmsKeyId' => '<string>',
    'VpcConfig' => [
        'SecurityGroupIds' => ['<string>', ...], // REQUIRED
        'Subnets' => ['<string>', ...], // REQUIRED
    ],
]);

Parameter Details

Members
ClientRequestToken
Type: string

A unique identifier for the request. If you do not set the client request token, Amazon Comprehend generates one.

DataAccessRoleArn
Required: Yes
Type: string

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.

InputDataConfig
Required: Yes
Type: InputDataConfig structure

Specifies the format and location of the input data for the job.

JobName
Type: string

The identifier of the job.

NumberOfTopics
Type: int

The number of topics to detect.

OutputDataConfig
Required: Yes
Type: OutputDataConfig structure

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

Tags
Type: Array of Tag structures

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.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Result Syntax

[
    'JobArn' => '<string>',
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobArn
Type: string

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

JobId
Type: string

The identifier generated for the job. To get the status of the job, use this identifier with the DescribeTopicDetectionJob operation.

JobStatus
Type: string

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.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StopDominantLanguageDetectionJob

$result = $client->stopDominantLanguageDetectionJob([/* ... */]);
$promise = $client->stopDominantLanguageDetectionJobAsync([/* ... */]);

Stops a dominant language detection job in progress.

If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

When a job is stopped, any documents already processed are written to the output location.

Parameter Syntax

$result = $client->stopDominantLanguageDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the dominant language detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the dominant language detection job to stop.

JobStatus
Type: string

Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopDominantLanguageDetectionJob operation.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopEntitiesDetectionJob

$result = $client->stopEntitiesDetectionJob([/* ... */]);
$promise = $client->stopEntitiesDetectionJobAsync([/* ... */]);

Stops an entities detection job in progress.

If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

When a job is stopped, any documents already processed are written to the output location.

Parameter Syntax

$result = $client->stopEntitiesDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the entities detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the entities detection job to stop.

JobStatus
Type: string

Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopEntitiesDetectionJob operation.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopEventsDetectionJob

$result = $client->stopEventsDetectionJob([/* ... */]);
$promise = $client->stopEventsDetectionJobAsync([/* ... */]);

Stops an events detection job in progress.

Parameter Syntax

$result = $client->stopEventsDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the events detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the events detection job to stop.

JobStatus
Type: string

The status of the events detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopKeyPhrasesDetectionJob

$result = $client->stopKeyPhrasesDetectionJob([/* ... */]);
$promise = $client->stopKeyPhrasesDetectionJobAsync([/* ... */]);

Stops a key phrases detection job in progress.

If the job state is IN_PROGRESS the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

When a job is stopped, any documents already processed are written to the output location.

Parameter Syntax

$result = $client->stopKeyPhrasesDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the key phrases detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the key phrases detection job to stop.

JobStatus
Type: string

Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopKeyPhrasesDetectionJob operation.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopPiiEntitiesDetectionJob

$result = $client->stopPiiEntitiesDetectionJob([/* ... */]);
$promise = $client->stopPiiEntitiesDetectionJobAsync([/* ... */]);

Stops a PII entities detection job in progress.

Parameter Syntax

$result = $client->stopPiiEntitiesDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the PII entities detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the PII entities detection job to stop.

JobStatus
Type: string

The status of the PII entities detection job.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopSentimentDetectionJob

$result = $client->stopSentimentDetectionJob([/* ... */]);
$promise = $client->stopSentimentDetectionJobAsync([/* ... */]);

Stops a sentiment detection job in progress.

If the job state is IN_PROGRESS, the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is be stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

When a job is stopped, any documents already processed are written to the output location.

Parameter Syntax

$result = $client->stopSentimentDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the sentiment detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the sentiment detection job to stop.

JobStatus
Type: string

Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopSentimentDetectionJob operation.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopTargetedSentimentDetectionJob

$result = $client->stopTargetedSentimentDetectionJob([/* ... */]);
$promise = $client->stopTargetedSentimentDetectionJobAsync([/* ... */]);

Stops a targeted sentiment detection job in progress.

If the job state is IN_PROGRESS, the job is marked for termination and put into the STOP_REQUESTED state. If the job completes before it can be stopped, it is put into the COMPLETED state; otherwise the job is be stopped and put into the STOPPED state.

If the job is in the COMPLETED or FAILED state when you call the StopDominantLanguageDetectionJob operation, the operation returns a 400 Internal Request Exception.

When a job is stopped, any documents already processed are written to the output location.

Parameter Syntax

$result = $client->stopTargetedSentimentDetectionJob([
    'JobId' => '<string>', // REQUIRED
]);

Parameter Details

Members
JobId
Required: Yes
Type: string

The identifier of the targeted sentiment detection job to stop.

Result Syntax

[
    'JobId' => '<string>',
    'JobStatus' => 'SUBMITTED|IN_PROGRESS|COMPLETED|FAILED|STOP_REQUESTED|STOPPED',
]

Result Details

Members
JobId
Type: string

The identifier of the targeted sentiment detection job to stop.

JobStatus
Type: string

Either STOP_REQUESTED if the job is currently running, or STOPPED if the job was previously stopped with the StopSentimentDetectionJob operation.

Errors

InvalidRequestException:

The request is invalid.

JobNotFoundException:

The specified job was not found. Check the job ID and try again.

InternalServerException:

An internal server error occurred. Retry your request.

StopTrainingDocumentClassifier

$result = $client->stopTrainingDocumentClassifier([/* ... */]);
$promise = $client->stopTrainingDocumentClassifierAsync([/* ... */]);

Stops a document classifier training job while in progress.

If the training job state is TRAINING, the job is marked for termination and put into the STOP_REQUESTED state. If the training job completes before it can be stopped, it is put into the TRAINED; otherwise the training job is stopped and put into the STOPPED state and the service sends back an HTTP 200 response with an empty HTTP body.

Parameter Syntax

$result = $client->stopTrainingDocumentClassifier([
    'DocumentClassifierArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
DocumentClassifierArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) that identifies the document classifier currently being trained.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

StopTrainingEntityRecognizer

$result = $client->stopTrainingEntityRecognizer([/* ... */]);
$promise = $client->stopTrainingEntityRecognizerAsync([/* ... */]);

Stops an entity recognizer training job while in progress.

If the training job state is TRAINING, the job is marked for termination and put into the STOP_REQUESTED state. If the training job completes before it can be stopped, it is put into the TRAINED; otherwise the training job is stopped and putted into the STOPPED state and the service sends back an HTTP 200 response with an empty HTTP body.

Parameter Syntax

$result = $client->stopTrainingEntityRecognizer([
    'EntityRecognizerArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
EntityRecognizerArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) that identifies the entity recognizer currently being trained.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

TagResource

$result = $client->tagResource([/* ... */]);
$promise = $client->tagResourceAsync([/* ... */]);

Associates a specific tag with an Amazon Comprehend resource. 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.

Parameter Syntax

$result = $client->tagResource([
    'ResourceArn' => '<string>', // REQUIRED
    'Tags' => [ // REQUIRED
        [
            'Key' => '<string>', // REQUIRED
            'Value' => '<string>',
        ],
        // ...
    ],
]);

Parameter Details

Members
ResourceArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the given Amazon Comprehend resource to which you want to associate the tags.

Tags
Required: Yes
Type: Array of Tag structures

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.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

InvalidRequestException:

The request is invalid.

ConcurrentModificationException:

Concurrent modification of the tags associated with an Amazon Comprehend resource is not supported.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

TooManyTagsException:

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

InternalServerException:

An internal server error occurred. Retry your request.

UntagResource

$result = $client->untagResource([/* ... */]);
$promise = $client->untagResourceAsync([/* ... */]);

Removes a specific tag associated with an Amazon Comprehend resource.

Parameter Syntax

$result = $client->untagResource([
    'ResourceArn' => '<string>', // REQUIRED
    'TagKeys' => ['<string>', ...], // REQUIRED
]);

Parameter Details

Members
ResourceArn
Required: Yes
Type: string

The Amazon Resource Name (ARN) of the given Amazon Comprehend resource from which you want to remove the tags.

TagKeys
Required: Yes
Type: Array of strings

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.

Result Syntax

[]

Result Details

The results for this operation are always empty.

Errors

TooManyTagKeysException:

The request contains more tag keys than can be associated with a resource (50 tag keys per resource).

InvalidRequestException:

The request is invalid.

ConcurrentModificationException:

Concurrent modification of the tags associated with an Amazon Comprehend resource is not supported.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

UpdateEndpoint

$result = $client->updateEndpoint([/* ... */]);
$promise = $client->updateEndpointAsync([/* ... */]);

Updates information about the specified endpoint. For information about endpoints, see Managing endpoints.

Parameter Syntax

$result = $client->updateEndpoint([
    'DesiredDataAccessRoleArn' => '<string>',
    'DesiredInferenceUnits' => <integer>,
    'DesiredModelArn' => '<string>',
    'EndpointArn' => '<string>', // REQUIRED
    'FlywheelArn' => '<string>',
]);

Parameter Details

Members
DesiredDataAccessRoleArn
Type: string

Data access role ARN to use in case the new model is encrypted with a customer CMK.

DesiredInferenceUnits
Type: int

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.

DesiredModelArn
Type: string

The ARN of the new model to use when updating an existing endpoint.

EndpointArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the endpoint being updated.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel

Result Syntax

[
    'DesiredModelArn' => '<string>',
]

Result Details

Members
DesiredModelArn
Type: string

The Amazon Resource Number (ARN) of the new model.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

ResourceInUseException:

The specified resource name is already in use. Use a different name and try your request again.

ResourceLimitExceededException:

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

ResourceUnavailableException:

The specified resource is not available. Check the resource and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

UpdateFlywheel

$result = $client->updateFlywheel([/* ... */]);
$promise = $client->updateFlywheelAsync([/* ... */]);

Update the configuration information for an existing flywheel.

Parameter Syntax

$result = $client->updateFlywheel([
    'ActiveModelArn' => '<string>',
    'DataAccessRoleArn' => '<string>',
    'DataSecurityConfig' => [
        'ModelKmsKeyId' => '<string>',
        'VolumeKmsKeyId' => '<string>',
        'VpcConfig' => [
            'SecurityGroupIds' => ['<string>', ...], // REQUIRED
            'Subnets' => ['<string>', ...], // REQUIRED
        ],
    ],
    'FlywheelArn' => '<string>', // REQUIRED
]);

Parameter Details

Members
ActiveModelArn
Type: string

The Amazon Resource Number (ARN) of the active model version.

DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to access the flywheel data.

DataSecurityConfig
Type: UpdateDataSecurityConfig structure

Flywheel data security configuration.

FlywheelArn
Required: Yes
Type: string

The Amazon Resource Number (ARN) of the flywheel to update.

Result Syntax

[
    'FlywheelProperties' => [
        'ActiveModelArn' => '<string>',
        'CreationTime' => <DateTime>,
        'DataAccessRoleArn' => '<string>',
        'DataLakeS3Uri' => '<string>',
        'DataSecurityConfig' => [
            'DataLakeKmsKeyId' => '<string>',
            'ModelKmsKeyId' => '<string>',
            'VolumeKmsKeyId' => '<string>',
            'VpcConfig' => [
                'SecurityGroupIds' => ['<string>', ...],
                'Subnets' => ['<string>', ...],
            ],
        ],
        'FlywheelArn' => '<string>',
        'LastModifiedTime' => <DateTime>,
        'LatestFlywheelIteration' => '<string>',
        'Message' => '<string>',
        'ModelType' => 'DOCUMENT_CLASSIFIER|ENTITY_RECOGNIZER',
        'Status' => 'CREATING|ACTIVE|UPDATING|DELETING|FAILED',
        'TaskConfig' => [
            'DocumentClassificationConfig' => [
                'Labels' => ['<string>', ...],
                'Mode' => 'MULTI_CLASS|MULTI_LABEL',
            ],
            'EntityRecognitionConfig' => [
                'EntityTypes' => [
                    [
                        'Type' => '<string>',
                    ],
                    // ...
                ],
            ],
            'LanguageCode' => 'en|es|fr|de|it|pt|ar|hi|ja|ko|zh|zh-TW',
        ],
    ],
]

Result Details

Members
FlywheelProperties
Type: FlywheelProperties structure

The flywheel properties.

Errors

InvalidRequestException:

The request is invalid.

TooManyRequestsException:

The number of requests exceeds the limit. Resubmit your request later.

KmsKeyValidationException:

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

ResourceNotFoundException:

The specified resource ARN was not found. Check the ARN and try your request again.

InternalServerException:

An internal server error occurred. Retry your request.

Shapes

AugmentedManifestsListItem

Description

An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

Members
AnnotationDataS3Uri
Type: string

The S3 prefix to the annotation files that are referred in the augmented manifest file.

AttributeNames
Required: Yes
Type: Array of strings

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.

DocumentType
Type: string

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.

S3Uri
Required: Yes
Type: string

The Amazon S3 location of the augmented manifest file.

SourceDocumentsS3Uri
Type: string

The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file.

Split
Type: string

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.

BatchDetectDominantLanguageItemResult

Description

The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.

Members
Index
Type: int

The zero-based index of the document in the input list.

Languages
Type: Array of DominantLanguage structures

One or more DominantLanguage objects describing the dominant languages in the document.

BatchDetectEntitiesItemResult

Description

The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.

Members
Entities
Type: Array of Entity structures

One or more Entity objects, one for each entity detected in the document.

Index
Type: int

The zero-based index of the document in the input list.

BatchDetectKeyPhrasesItemResult

Description

The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.

Members
Index
Type: int

The zero-based index of the document in the input list.

KeyPhrases
Type: Array of KeyPhrase structures

One or more KeyPhrase objects, one for each key phrase detected in the document.

BatchDetectSentimentItemResult

Description

The result of calling the operation. The operation returns one object for each document that is successfully processed by the operation.

Members
Index
Type: int

The zero-based index of the document in the input list.

Sentiment
Type: string

The sentiment detected in the document.

SentimentScore
Type: SentimentScore structure

The level of confidence that Amazon Comprehend has in the accuracy of its sentiment detection.

BatchDetectSyntaxItemResult

Description

The result of calling the operation. The operation returns one object that is successfully processed by the operation.

Members
Index
Type: int

The zero-based index of the document in the input list.

SyntaxTokens
Type: Array of SyntaxToken structures

The syntax tokens for the words in the document, one token for each word.

BatchDetectTargetedSentimentItemResult

Description

Analysis results for one of the documents in the batch.

Members
Entities
Type: Array of TargetedSentimentEntity structures

An array of targeted sentiment entities.

Index
Type: int

The zero-based index of this result in the input list.

BatchItemError

Description

Describes an error that occurred while processing a document in a batch. The operation returns on BatchItemError object for each document that contained an error.

Members
ErrorCode
Type: string

The numeric error code of the error.

ErrorMessage
Type: string

A text description of the error.

Index
Type: int

The zero-based index of the document in the input list.

BatchSizeLimitExceededException

Description

The number of documents in the request exceeds the limit of 25. Try your request again with fewer documents.

Members
Message
Type: string

Block

Description

Information about each word or line of text in the input document.

For additional information, see Block in the Amazon Textract API reference.

Members
BlockType
Type: string

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

Geometry
Type: Geometry structure

Co-ordinates of the rectangle or polygon that contains the text.

Id
Type: string

Unique identifier for the block.

Page
Type: int

Page number where the block appears.

Relationships
Type: Array of RelationshipsListItem structures

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.

Text
Type: string

The word or line of text extracted from the block.

BlockReference

Description

A reference to a block.

Members
BeginOffset
Type: int

Offset of the start of the block within its parent block.

BlockId
Type: string

Unique identifier for the block.

ChildBlocks
Type: Array of ChildBlock structures

List of child blocks within this block.

EndOffset
Type: int

Offset of the end of the block within its parent block.

BoundingBox

Description

The bounding box around the detected page or around an element on a document page. The left (x-coordinate) and top (y-coordinate) are coordinates that represent the top and left sides of the bounding box. Note that the upper-left corner of the image is the origin (0,0).

For additional information, see BoundingBox in the Amazon Textract API reference.

Members
Height
Type: float

The height of the bounding box as a ratio of the overall document page height.

Left
Type: float

The left coordinate of the bounding box as a ratio of overall document page width.

Top
Type: float

The top coordinate of the bounding box as a ratio of overall document page height.

Width
Type: float

The width of the bounding box as a ratio of the overall document page width.

ChildBlock

Description

Nested block contained within a block.

Members
BeginOffset
Type: int

Offset of the start of the child block within its parent block.

ChildBlockId
Type: string

Unique identifier for the child block.

EndOffset
Type: int

Offset of the end of the child block within its parent block.

ClassifierEvaluationMetrics

Description

Describes the result metrics for the test data associated with an documentation classifier.

Members
Accuracy
Type: double

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.

F1Score
Type: double

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.

HammingLoss
Type: double

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.

MicroF1Score
Type: double

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.

MicroPrecision
Type: double

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.

MicroRecall
Type: double

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.

Precision
Type: double

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.

Recall
Type: double

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.

ClassifierMetadata

Description

Provides information about a document classifier.

Members
EvaluationMetrics
Type: ClassifierEvaluationMetrics structure

Describes the result metrics for the test data associated with an documentation classifier.

NumberOfLabels
Type: int

The number of labels in the input data.

NumberOfTestDocuments
Type: int

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.

NumberOfTrainedDocuments
Type: int

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.

ConcurrentModificationException

Description

Concurrent modification of the tags associated with an Amazon Comprehend resource is not supported.

Members
Message
Type: string

DataSecurityConfig

Description

Data security configuration.

Members
DataLakeKmsKeyId
Type: string

ID for the KMS key that Amazon Comprehend uses to encrypt the data in the data lake.

ModelKmsKeyId
Type: string

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"

VolumeKmsKeyId
Type: string

ID for the KMS key that Amazon Comprehend uses to encrypt the volume.

VpcConfig
Type: VpcConfig structure

Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for the job. For more information, see Amazon VPC.

DatasetAugmentedManifestsListItem

Description

An augmented manifest file that provides training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth.

Members
AnnotationDataS3Uri
Type: string

The S3 prefix to the annotation files that are referred in the augmented manifest file.

AttributeNames
Required: Yes
Type: Array of strings

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.

DocumentType
Type: string

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.

S3Uri
Required: Yes
Type: string

The Amazon S3 location of the augmented manifest file.

SourceDocumentsS3Uri
Type: string

The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file.

DatasetDocumentClassifierInputDataConfig

Description

Describes the dataset input data configuration for a document classifier model.

For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.

Members
LabelDelimiter
Type: string

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.

S3Uri
Required: Yes
Type: string

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.

DatasetEntityRecognizerAnnotations

Description

Describes the annotations associated with a entity recognizer.

Members
S3Uri
Required: Yes
Type: string

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.

DatasetEntityRecognizerDocuments

Description

Describes the documents submitted with a dataset for an entity recognizer model.

Members
InputFormat
Type: string

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.

S3Uri
Required: Yes
Type: string

Specifies the Amazon S3 location where the documents for the dataset are located.

DatasetEntityRecognizerEntityList

Description

Describes the dataset entity list for an entity recognizer model.

For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.

Members
S3Uri
Required: Yes
Type: string

Specifies the Amazon S3 location where the entity list is located.

DatasetEntityRecognizerInputDataConfig

Description

Specifies the format and location of the input data. You must provide either the Annotations parameter or the EntityList parameter.

Members
Annotations

The S3 location of the annotation documents for your custom entity recognizer.

Documents
Required: Yes
Type: DatasetEntityRecognizerDocuments structure

The format and location of the training documents for your custom entity recognizer.

EntityList

The S3 location of the entity list for your custom entity recognizer.

DatasetFilter

Description

Filter the datasets based on creation time or dataset status.

Members
CreationTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

Filter the datasets to include datasets created after the specified time.

CreationTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

Filter the datasets to include datasets created before the specified time.

DatasetType
Type: string

Filter the datasets based on the dataset type.

Status
Type: string

Filter the datasets based on the dataset status.

DatasetInputDataConfig

Description

Specifies the format and location of the input data for the dataset.

Members
AugmentedManifests
Type: Array of DatasetAugmentedManifestsListItem structures

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.

DataFormat
Type: string

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

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.

EntityRecognizerInputDataConfig

The input properties for training an entity recognizer model.

DatasetProperties

Description

Properties associated with the dataset.

Members
CreationTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

Creation time of the dataset.

DatasetArn
Type: string

The ARN of the dataset.

DatasetName
Type: string

The name of the dataset.

DatasetS3Uri
Type: string

The S3 URI where the dataset is stored.

DatasetType
Type: string

The dataset type (training data or test data).

Description
Type: string

Description of the dataset.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

Time when the data from the dataset becomes available in the data lake.

Message
Type: string

A description of the status of the dataset.

NumberOfDocuments
Type: long (int|float)

The number of documents in the dataset.

Status
Type: string

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.

DocumentClass

Description

Specifies the class that categorizes the document being analyzed

Members
Name
Type: string

The name of the class.

Page
Type: int

Page number in the input document. This field is present in the response only if your request includes the Byte parameter.

Score
Type: float

The confidence score that Amazon Comprehend has this class correctly attributed.

DocumentClassificationConfig

Description

Configuration required for a document classification model.

Members
Labels
Type: Array of strings

One or more labels to associate with the custom classifier.

Mode
Required: Yes
Type: string

Classification mode indicates whether the documents are MULTI_CLASS or MULTI_LABEL.

DocumentClassificationJobFilter

Description

Provides information for filtering a list of document classification jobs. For more information, see the operation. You can provide only one filter parameter in each request.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

DocumentClassificationJobProperties

Description

Provides information about a document classification job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

DocumentClassifierArn
Type: string

The Amazon Resource Name (ARN) that identifies the document classifier.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the document classification job completed.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel

InputDataConfig
Type: InputDataConfig structure

The input data configuration that you supplied when you created the document classification job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the document classification job.

JobName
Type: string

The name that you assigned to the document classification job.

JobStatus
Type: string

The current status of the document classification job. If the status is FAILED, the Message field shows the reason for the failure.

Message
Type: string

A description of the status of the job.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration that you supplied when you created the document classification job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the document classification job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

DocumentClassifierDocuments

Description

The location of the training documents. This parameter is required in a request to create a semi-structured document classification model.

Members
S3Uri
Required: Yes
Type: string

The S3 URI location of the training documents specified in the S3Uri CSV file.

TestS3Uri
Type: string

The S3 URI location of the test documents included in the TestS3Uri CSV file. This field is not required if you do not specify a test CSV file.

DocumentClassifierFilter

Description

Provides information for filtering a list of document classifiers. You can only specify one filtering parameter in a request. For more information, see the ListDocumentClassifiers operation.

Members
DocumentClassifierName
Type: string

The name that you assigned to the document classifier

Status
Type: string

Filters the list of classifiers based on status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

DocumentClassifierInputDataConfig

Description

The input properties for training a document classifier.

For more information on how the input file is formatted, see Preparing training data in the Comprehend Developer Guide.

Members
AugmentedManifests
Type: Array of AugmentedManifestsListItem structures

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.

DataFormat
Type: string

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.

DocumentReaderConfig
Type: DocumentReaderConfig structure

Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

By default, Amazon Comprehend performs the following actions to extract text from files, based on the input file type:

  • Word files - Amazon Comprehend parser extracts the text.

  • Digital PDF files - Amazon Comprehend parser extracts the text.

  • Image files and scanned PDF files - Amazon Comprehend uses the Amazon Textract DetectDocumentText API to extract the text.

DocumentReaderConfig does not apply to plain text files or Word files.

For image files and PDF documents, you can override these default actions using the fields listed below. For more information, see Setting text extraction options in the Comprehend Developer Guide.

DocumentType
Type: string

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.

Documents
Type: DocumentClassifierDocuments structure

The S3 location of the training documents. This parameter is required in a request to create a native document model.

LabelDelimiter
Type: string

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.

S3Uri
Type: string

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.

TestS3Uri
Type: string

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.

DocumentClassifierOutputDataConfig

Description

Provide the location for output data from a custom classifier job. This field is mandatory if you are training a native document model.

Members
FlywheelStatsS3Prefix
Type: string

The Amazon S3 prefix for the data lake location of the flywheel statistics.

KmsKeyId
Type: string

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"

S3Uri
Type: string

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.

DocumentClassifierProperties

Description

Provides information about a document classifier.

Members
ClassifierMetadata
Type: ClassifierMetadata structure

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.

DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

DocumentClassifierArn
Type: string

The Amazon Resource Name (ARN) that identifies the document classifier.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that training the document classifier completed.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel

InputDataConfig

The input data configuration that you supplied when you created the document classifier for training.

LanguageCode
Type: string

The language code for the language of the documents that the classifier was trained on.

Message
Type: string

Additional information about the status of the classifier.

Mode
Type: string

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.

ModelKmsKeyId
Type: string

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"

OutputDataConfig

Provides output results configuration parameters for custom classifier jobs.

SourceModelArn
Type: string

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.

Status
Type: string

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.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the document classifier was submitted for training.

TrainingEndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

TrainingStartTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

VersionName
Type: string

The version name that you assigned to the document classifier.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

DocumentClassifierSummary

Description

Describes information about a document classifier and its versions.

Members
DocumentClassifierName
Type: string

The name that you assigned the document classifier.

LatestVersionCreatedAt
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the latest document classifier version was submitted for processing.

LatestVersionName
Type: string

The version name you assigned to the latest document classifier version.

LatestVersionStatus
Type: string

Provides the status of the latest document classifier version.

NumberOfVersions
Type: int

The number of versions you created.

DocumentLabel

Description

Specifies one of the label or labels that categorize the document being analyzed.

Members
Name
Type: string

The name of the label.

Page
Type: int

Page number where the label occurs. This field is present in the response only if your request includes the Byte parameter.

Score
Type: float

The confidence score that Amazon Comprehend has this label correctly attributed.

DocumentMetadata

Description

Information about the document, discovered during text extraction.

Members
ExtractedCharacters
Type: Array of ExtractedCharactersListItem structures

List of pages in the document, with the number of characters extracted from each page.

Pages
Type: int

Number of pages in the document.

DocumentReaderConfig

Description

Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

By default, Amazon Comprehend performs the following actions to extract text from files, based on the input file type:

  • Word files - Amazon Comprehend parser extracts the text.

  • Digital PDF files - Amazon Comprehend parser extracts the text.

  • Image files and scanned PDF files - Amazon Comprehend uses the Amazon Textract DetectDocumentText API to extract the text.

DocumentReaderConfig does not apply to plain text files or Word files.

For image files and PDF documents, you can override these default actions using the fields listed below. For more information, see Setting text extraction options in the Comprehend Developer Guide.

Members
DocumentReadAction
Required: Yes
Type: string

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.

DocumentReadMode
Type: string

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.

FeatureTypes
Type: Array of strings

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.

DocumentTypeListItem

Description

Document type for each page in the document.

Members
Page
Type: int

Page number.

Type
Type: string

Document type.

DominantLanguage

Description

Returns the code for the dominant language in the input text and the level of confidence that Amazon Comprehend has in the accuracy of the detection.

Members
LanguageCode
Type: string

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.

Score
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of the detection.

DominantLanguageDetectionJobFilter

Description

Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

DominantLanguageDetectionJobProperties

Description

Provides information about a dominant language detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the dominant language detection job completed.

InputDataConfig
Type: InputDataConfig structure

The input data configuration that you supplied when you created the dominant language detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the dominant language detection job.

JobName
Type: string

The name that you assigned to the dominant language detection job.

JobStatus
Type: string

The current status of the dominant language detection job. If the status is FAILED, the Message field shows the reason for the failure.

Message
Type: string

A description for the status of a job.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration that you supplied when you created the dominant language detection job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the dominant language detection job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

EndpointFilter

Description

The filter used to determine which endpoints are returned. You can filter jobs on their name, model, status, or the date and time that they were created. You can only set one filter at a time.

Members
CreationTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

Specifies a date after which the returned endpoint or endpoints were created.

CreationTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

Specifies a date before which the returned endpoint or endpoints were created.

ModelArn
Type: string

The Amazon Resource Number (ARN) of the model to which the endpoint is attached.

Status
Type: string

Specifies the status of the endpoint being returned. Possible values are: Creating, Ready, Updating, Deleting, Failed.

EndpointProperties

Description

Specifies information about the specified endpoint. For information about endpoints, see Managing endpoints.

Members
CreationTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The creation date and time of the endpoint.

CurrentInferenceUnits
Type: int

The number of inference units currently used by the model using this endpoint.

DataAccessRoleArn
Type: string

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).

DesiredDataAccessRoleArn
Type: string

Data access role ARN to use in case the new model is encrypted with a customer KMS key.

DesiredInferenceUnits
Type: int

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.

DesiredModelArn
Type: string

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

EndpointArn
Type: string

The Amazon Resource Number (ARN) of the endpoint.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel

LastModifiedTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The date and time that the endpoint was last modified.

Message
Type: string

Specifies a reason for failure in cases of Failed status.

ModelArn
Type: string

The Amazon Resource Number (ARN) of the model to which the endpoint is attached.

Status
Type: string

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.

EntitiesDetectionJobFilter

Description

Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

EntitiesDetectionJobProperties

Description

Provides information about an entities detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the entities detection job completed

EntityRecognizerArn
Type: string

The Amazon Resource Name (ARN) that identifies the entity recognizer.

FlywheelArn
Type: string

The Amazon Resource Name (ARN) of the flywheel associated with this job.

InputDataConfig
Type: InputDataConfig structure

The input data configuration that you supplied when you created the entities detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the entities detection job.

JobName
Type: string

The name that you assigned the entities detection job.

JobStatus
Type: string

The current status of the entities detection job. If the status is FAILED, the Message field shows the reason for the failure.

LanguageCode
Type: string

The language code of the input documents.

Message
Type: string

A description of the status of a job.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration that you supplied when you created the entities detection job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the entities detection job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

Entity

Description

Provides information about an entity.

Members
BeginOffset
Type: int

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.

BlockReferences
Type: Array of BlockReference structures

A reference to each block for this entity. This field is empty for plain-text input.

EndOffset
Type: int

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.

Score
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of the detection.

Text
Type: string

The text of the entity.

Type
Type: string

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.

EntityLabel

Description

Specifies one of the label or labels that categorize the personally identifiable information (PII) entity being analyzed.

Members
Name
Type: string

The name of the label.

Score
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of the detection.

EntityRecognitionConfig

Description

Configuration required for an entity recognition model.

Members
EntityTypes
Required: Yes
Type: Array of EntityTypesListItem structures

Up to 25 entity types that the model is trained to recognize.

EntityRecognizerAnnotations

Description

Describes the annotations associated with a entity recognizer.

Members
S3Uri
Required: Yes
Type: string

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.

TestS3Uri
Type: string

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.

EntityRecognizerDocuments

Description

Describes the training documents submitted with an entity recognizer.

Members
InputFormat
Type: string

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.

S3Uri
Required: Yes
Type: string

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.

TestS3Uri
Type: string

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.

EntityRecognizerEntityList

Description

Describes the entity list submitted with an entity recognizer.

Members
S3Uri
Required: Yes
Type: string

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.

EntityRecognizerEvaluationMetrics

Description

Detailed information about the accuracy of an entity recognizer.

Members
F1Score
Type: double

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.

Precision
Type: double

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.

Recall
Type: double

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.

EntityRecognizerFilter

Description

Provides information for filtering a list of entity recognizers. You can only specify one filtering parameter in a request. For more information, see the ListEntityRecognizers operation./>

Members
RecognizerName
Type: string

The name that you assigned the entity recognizer.

Status
Type: string

The status of an entity recognizer.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

EntityRecognizerInputDataConfig

Description

Specifies the format and location of the input data.

Members
Annotations
Type: EntityRecognizerAnnotations structure

The S3 location of the CSV file that annotates your training documents.

AugmentedManifests
Type: Array of AugmentedManifestsListItem structures

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.

DataFormat
Type: string

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.

Documents
Type: EntityRecognizerDocuments structure

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.

EntityList
Type: EntityRecognizerEntityList structure

The S3 location of the CSV file that has the entity list for your custom entity recognizer.

EntityTypes
Required: Yes
Type: Array of EntityTypesListItem structures

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).

EntityRecognizerMetadata

Description

Detailed information about an entity recognizer.

Members
EntityTypes

Entity types from the metadata of an entity recognizer.

EvaluationMetrics

Detailed information about the accuracy of an entity recognizer.

NumberOfTestDocuments
Type: int

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.

NumberOfTrainedDocuments
Type: int

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.

EntityRecognizerMetadataEntityTypesListItem

Description

Individual item from the list of entity types in the metadata of an entity recognizer.

Members
EvaluationMetrics

Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.

NumberOfTrainMentions
Type: int

Indicates the number of times the given entity type was seen in the training data.

Type
Type: string

Type of entity from the list of entity types in the metadata of an entity recognizer.

EntityRecognizerOutputDataConfig

Description

Output data configuration.

Members
FlywheelStatsS3Prefix
Type: string

The Amazon S3 prefix for the data lake location of the flywheel statistics.

EntityRecognizerProperties

Description

Describes information about an entity recognizer.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the recognizer creation completed.

EntityRecognizerArn
Type: string

The Amazon Resource Name (ARN) that identifies the entity recognizer.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel

InputDataConfig

The input data properties of an entity recognizer.

LanguageCode
Type: string

The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.

Message
Type: string

A description of the status of the recognizer.

ModelKmsKeyId
Type: string

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"

OutputDataConfig

Output data configuration.

RecognizerMetadata
Type: EntityRecognizerMetadata structure

Provides information about an entity recognizer.

SourceModelArn
Type: string

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.

Status
Type: string

Provides the status of the entity recognizer.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the recognizer was submitted for processing.

TrainingEndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that training of the entity recognizer was completed.

TrainingStartTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that training of the entity recognizer started.

VersionName
Type: string

The version name you assigned to the entity recognizer.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

EntityRecognizerSummary

Description

Describes the information about an entity recognizer and its versions.

Members
LatestVersionCreatedAt
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the latest entity recognizer version was submitted for processing.

LatestVersionName
Type: string

The version name you assigned to the latest entity recognizer version.

LatestVersionStatus
Type: string

Provides the status of the latest entity recognizer version.

NumberOfVersions
Type: int

The number of versions you created.

RecognizerName
Type: string

The name that you assigned the entity recognizer.

EntityTypesEvaluationMetrics

Description

Detailed information about the accuracy of an entity recognizer for a specific entity type.

Members
F1Score
Type: double

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.

Precision
Type: double

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.

Recall
Type: double

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.

EntityTypesListItem

Description

An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer.

Members
Type
Required: Yes
Type: string

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).

ErrorsListItem

Description

Text extraction encountered one or more page-level errors in the input document.

The ErrorCode contains one of the following values:

  • TEXTRACT_BAD_PAGE - Amazon Textract cannot read the page. For more information about page limits in Amazon Textract, see Page Quotas in Amazon Textract.

  • TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED - The number of requests exceeded your throughput limit. For more information about throughput quotas in Amazon Textract, see Default quotas in Amazon Textract.

  • PAGE_CHARACTERS_EXCEEDED - Too many text characters on the page (10,000 characters maximum).

  • PAGE_SIZE_EXCEEDED - The maximum page size is 10 MB.

  • INTERNAL_SERVER_ERROR - The request encountered a service issue. Try the API request again.

Members
ErrorCode
Type: string

Error code for the cause of the error.

ErrorMessage
Type: string

Text message explaining the reason for the error.

Page
Type: int

Page number where the error occurred.

EventsDetectionJobFilter

Description

Provides information for filtering a list of event detection jobs.

Members
JobName
Type: string

Filters on the name of the events detection job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

EventsDetectionJobProperties

Description

Provides information about an events detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the events detection job completed.

InputDataConfig
Type: InputDataConfig structure

The input data configuration that you supplied when you created the events detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the events detection job.

JobName
Type: string

The name you assigned the events detection job.

JobStatus
Type: string

The current status of the events detection job.

LanguageCode
Type: string

The language code of the input documents.

Message
Type: string

A description of the status of the events detection job.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration that you supplied when you created the events detection job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the events detection job was submitted for processing.

TargetEventTypes
Type: Array of strings

The types of events that are detected by the job.

ExtractedCharactersListItem

Description

Array of the number of characters extracted from each page.

Members
Count
Type: int

Number of characters extracted from each page.

Page
Type: int

Page number.

FlywheelFilter

Description

Filter the flywheels based on creation time or flywheel status.

Members
CreationTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

Filter the flywheels to include flywheels created after the specified time.

CreationTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

Filter the flywheels to include flywheels created before the specified time.

Status
Type: string

Filter the flywheels based on the flywheel status.

FlywheelIterationFilter

Description

Filter the flywheel iterations based on creation time.

Members
CreationTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

Filter the flywheel iterations to include iterations created after the specified time.

CreationTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

Filter the flywheel iterations to include iterations created before the specified time.

FlywheelIterationProperties

Description

The configuration properties of a flywheel iteration.

Members
CreationTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The creation start time of the flywheel iteration.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The completion time of this flywheel iteration.

EvaluatedModelArn
Type: string

The ARN of the evaluated model associated with this flywheel iteration.

EvaluatedModelMetrics

The evaluation metrics associated with the evaluated model.

EvaluationManifestS3Prefix
Type: string

FlywheelArn
Type: string

FlywheelIterationId
Type: string

Message
Type: string

A description of the status of the flywheel iteration.

Status
Type: string

The status of the flywheel iteration.

TrainedModelArn
Type: string

The ARN of the trained model associated with this flywheel iteration.

TrainedModelMetrics

The metrics associated with the trained model.

FlywheelModelEvaluationMetrics

Description

The evaluation metrics associated with the evaluated model.

Members
AverageAccuracy
Type: double

Average accuracy metric for the model.

AverageF1Score
Type: double

The average F1 score from the evaluation metrics.

AveragePrecision
Type: double

Average precision metric for the model.

AverageRecall
Type: double

Average recall metric for the model.

FlywheelProperties

Description

The flywheel properties.

Members
ActiveModelArn
Type: string

The Amazon Resource Number (ARN) of the active model version.

CreationTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

Creation time of the flywheel.

DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend permission to access the flywheel data.

DataLakeS3Uri
Type: string

Amazon S3 URI of the data lake location.

DataSecurityConfig
Type: DataSecurityConfig structure

Data security configuration.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel.

LastModifiedTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

Last modified time for the flywheel.

LatestFlywheelIteration
Type: string

The most recent flywheel iteration.

Message
Type: string

A description of the status of the flywheel.

ModelType
Type: string

Model type of the flywheel's model.

Status
Type: string

The status of the flywheel.

TaskConfig
Type: TaskConfig structure

Configuration about the model associated with a flywheel.

FlywheelSummary

Description

Flywheel summary information.

Members
ActiveModelArn
Type: string

ARN of the active model version for the flywheel.

CreationTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

Creation time of the flywheel.

DataLakeS3Uri
Type: string

Amazon S3 URI of the data lake location.

FlywheelArn
Type: string

The Amazon Resource Number (ARN) of the flywheel

LastModifiedTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

Last modified time for the flywheel.

LatestFlywheelIteration
Type: string

The most recent flywheel iteration.

Message
Type: string

A description of the status of the flywheel.

ModelType
Type: string

Model type of the flywheel's model.

Status
Type: string

The status of the flywheel.

Geometry

Description

Information about the location of items on a document page.

For additional information, see Geometry in the Amazon Textract API reference.

Members
BoundingBox
Type: BoundingBox structure

An axis-aligned coarse representation of the location of the recognized item on the document page.

Polygon
Type: Array of Point structures

Within the bounding box, a fine-grained polygon around the recognized item.

InputDataConfig

Description

The input properties for an inference job. The document reader config field applies only to non-text inputs for custom analysis.

Members
DocumentReaderConfig
Type: DocumentReaderConfig structure

Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.

InputFormat
Type: string

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.

S3Uri
Required: Yes
Type: string

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.

InternalServerException

Description

An internal server error occurred. Retry your request.

Members
Message
Type: string

InvalidFilterException

Description

The filter specified for the operation is invalid. Specify a different filter.

Members
Message
Type: string

InvalidRequestDetail

Description

Provides additional detail about why the request failed.

Members
Reason
Type: string

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.

InvalidRequestException

Description

The request is invalid.

Members
Detail
Type: InvalidRequestDetail structure

Provides additional detail about why the request failed.

Message
Type: string
Reason
Type: string

JobNotFoundException

Description

The specified job was not found. Check the job ID and try again.

Members
Message
Type: string

KeyPhrase

Description

Describes a key noun phrase.

Members
BeginOffset
Type: int

The zero-based offset from the beginning of the source text to the first character in the key phrase.

EndOffset
Type: int

The zero-based offset from the beginning of the source text to the last character in the key phrase.

Score
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of the detection.

Text
Type: string

The text of a key noun phrase.

KeyPhrasesDetectionJobFilter

Description

Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

KeyPhrasesDetectionJobProperties

Description

Provides information about a key phrases detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the key phrases detection job completed.

InputDataConfig
Type: InputDataConfig structure

The input data configuration that you supplied when you created the key phrases detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the key phrases detection job.

JobName
Type: string

The name that you assigned the key phrases detection job.

JobStatus
Type: string

The current status of the key phrases detection job. If the status is FAILED, the Message field shows the reason for the failure.

LanguageCode
Type: string

The language code of the input documents.

Message
Type: string

A description of the status of a job.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration that you supplied when you created the key phrases detection job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the key phrases detection job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

KmsKeyValidationException

Description

The KMS customer managed key (CMK) entered cannot be validated. Verify the key and re-enter it.

Members
Message
Type: string

MentionSentiment

Description

Contains the sentiment and sentiment score for one mention of an entity.

For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.

Members
Sentiment
Type: string

The sentiment of the mention.

SentimentScore
Type: SentimentScore structure

Describes the level of confidence that Amazon Comprehend has in the accuracy of its detection of sentiments.

OutputDataConfig

Description

Provides configuration parameters for the output of inference jobs.

Members
KmsKeyId
Type: string

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"

S3Uri
Required: Yes
Type: string

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.

PartOfSpeechTag

Description

Identifies the part of speech represented by the token and gives the confidence that Amazon Comprehend has that the part of speech was correctly identified. For more information about the parts of speech that Amazon Comprehend can identify, see Syntax in the Comprehend Developer Guide.

Members
Score
Type: float

The confidence that Amazon Comprehend has that the part of speech was correctly identified.

Tag
Type: string

Identifies the part of speech that the token represents.

PiiEntitiesDetectionJobFilter

Description

Provides information for filtering a list of PII entity detection jobs.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

PiiEntitiesDetectionJobProperties

Description

Provides information about a PII entities detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the PII entities detection job completed.

InputDataConfig
Type: InputDataConfig structure

The input properties for a PII entities detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the PII entities detection job.

JobName
Type: string

The name that you assigned the PII entities detection job.

JobStatus
Type: string

The current status of the PII entities detection job. If the status is FAILED, the Message field shows the reason for the failure.

LanguageCode
Type: string

The language code of the input documents.

Message
Type: string

A description of the status of a job.

Mode
Type: string

Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.

OutputDataConfig
Type: PiiOutputDataConfig structure

The output data configuration that you supplied when you created the PII entities detection job.

RedactionConfig
Type: RedactionConfig structure

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.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the PII entities detection job was submitted for processing.

PiiEntity

Description

Provides information about a PII entity.

Members
BeginOffset
Type: int

The zero-based offset from the beginning of the source text to the first character in the entity.

EndOffset
Type: int

The zero-based offset from the beginning of the source text to the last character in the entity.

Score
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of the detection.

Type
Type: string

The entity's type.

PiiOutputDataConfig

Description

Provides configuration parameters for the output of PII entity detection jobs.

Members
KmsKeyId
Type: string

ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job.

S3Uri
Required: Yes
Type: string

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.

Point

Description

The X and Y coordinates of a point on a document page.

For additional information, see Point in the Amazon Textract API reference.

Members
X
Type: float

The value of the X coordinate for a point on a polygon

Y
Type: float

The value of the Y coordinate for a point on a polygon

RedactionConfig

Description

Provides configuration parameters for PII entity redaction.

Members
MaskCharacter
Type: string

A character that replaces each character in the redacted PII entity.

MaskMode
Type: string

Specifies whether the PII entity is redacted with the mask character or the entity type.

PiiEntityTypes
Type: Array of strings

An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.

RelationshipsListItem

Description

List of child blocks for the current block.

Members
Ids
Type: Array of strings

Identifers of the child blocks.

Type
Type: string

Only supported relationship is a child relationship.

ResourceInUseException

Description

The specified resource name is already in use. Use a different name and try your request again.

Members
Message
Type: string

ResourceLimitExceededException

Description

The maximum number of resources per account has been exceeded. Review the resources, and then try your request again.

Members
Message
Type: string

ResourceNotFoundException

Description

The specified resource ARN was not found. Check the ARN and try your request again.

Members
Message
Type: string

ResourceUnavailableException

Description

The specified resource is not available. Check the resource and try your request again.

Members
Message
Type: string

SentimentDetectionJobFilter

Description

Provides information for filtering a list of dominant language detection jobs. For more information, see the operation.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SentimentDetectionJobProperties

Description

Provides information about a sentiment detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the sentiment detection job ended.

InputDataConfig
Type: InputDataConfig structure

The input data configuration that you supplied when you created the sentiment detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the sentiment detection job.

JobName
Type: string

The name that you assigned to the sentiment detection job

JobStatus
Type: string

The current status of the sentiment detection job. If the status is FAILED, the Messages field shows the reason for the failure.

LanguageCode
Type: string

The language code of the input documents.

Message
Type: string

A description of the status of a job.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration that you supplied when you created the sentiment detection job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the sentiment detection job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

SentimentScore

Description

Describes the level of confidence that Amazon Comprehend has in the accuracy of its detection of sentiments.

Members
Mixed
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.

Negative
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.

Neutral
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.

Positive
Type: float

The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.

SyntaxToken

Description

Represents a work in the input text that was recognized and assigned a part of speech. There is one syntax token record for each word in the source text.

Members
BeginOffset
Type: int

The zero-based offset from the beginning of the source text to the first character in the word.

EndOffset
Type: int

The zero-based offset from the beginning of the source text to the last character in the word.

PartOfSpeech
Type: PartOfSpeechTag structure

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.

Text
Type: string

The word that was recognized in the source text.

TokenId
Type: int

A unique identifier for a token.

Tag

Description

A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by a particular department.

Members
Key
Required: Yes
Type: string

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.”

Value
Type: string

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.

TargetedSentimentDetectionJobFilter

Description

Provides information for filtering a list of dominant language detection jobs. For more information, see the ListTargetedSentimentDetectionJobs operation.

Members
JobName
Type: string

Filters on the name of the job.

JobStatus
Type: string

Filters the list of jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

TargetedSentimentDetectionJobProperties

Description

Provides information about a targeted sentiment detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the targeted sentiment detection job ended.

InputDataConfig
Type: InputDataConfig structure

The input properties for an inference job. The document reader config field applies only to non-text inputs for custom analysis.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the targeted sentiment detection job.

JobName
Type: string

The name that you assigned to the targeted sentiment detection job.

JobStatus
Type: string

The current status of the targeted sentiment detection job. If the status is FAILED, the Messages field shows the reason for the failure.

LanguageCode
Type: string

The language code of the input documents.

Message
Type: string

A description of the status of a job.

OutputDataConfig
Type: OutputDataConfig structure

Provides configuration parameters for the output of inference jobs.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the targeted sentiment detection job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for the job. For more information, see Amazon VPC.

TargetedSentimentEntity

Description

Information about one of the entities found by targeted sentiment analysis.

For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.

Members
DescriptiveMentionIndex
Type: Array of ints

One or more index into the Mentions array that provides the best name for the entity group.

Mentions
Type: Array of TargetedSentimentMention structures

An array of mentions of the entity in the document. The array represents a co-reference group. See Co-reference group for an example.

TargetedSentimentMention

Description

Information about one mention of an entity. The mention information includes the location of the mention in the text and the sentiment of the mention.

For more information about targeted sentiment, see Targeted sentiment in the Amazon Comprehend Developer Guide.

Members
BeginOffset
Type: int

The offset into the document text where the mention begins.

EndOffset
Type: int

The offset into the document text where the mention ends.

GroupScore
Type: float

The confidence that all the entities mentioned in the group relate to the same entity.

MentionSentiment
Type: MentionSentiment structure

Contains the sentiment and sentiment score for the mention.

Score
Type: float

Model confidence that the entity is relevant. Value range is zero to one, where one is highest confidence.

Text
Type: string

The text in the document that identifies the entity.

Type
Type: string

The type of the entity. Amazon Comprehend supports a variety of entity types.

TaskConfig

Description

Configuration about the model associated with a flywheel.

Members
DocumentClassificationConfig

Configuration required for a document classification model.

EntityRecognitionConfig
Type: EntityRecognitionConfig structure

Configuration required for an entity recognition model.

LanguageCode
Required: Yes
Type: string

Language code for the language that the model supports.

TextSegment

Description

One of the of text strings. Each string has a size limit of 1KB.

Members
Text
Required: Yes
Type: string

The text content.

TextSizeLimitExceededException

Description

The size of the input text exceeds the limit. Use a smaller document.

Members
Message
Type: string

TooManyRequestsException

Description

The number of requests exceeds the limit. Resubmit your request later.

Members
Message
Type: string

TooManyTagKeysException

Description

The request contains more tag keys than can be associated with a resource (50 tag keys per resource).

Members
Message
Type: string

TooManyTagsException

Description

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

Members
Message
Type: string

TopicsDetectionJobFilter

Description

Provides information for filtering topic detection jobs. For more information, see .

Members
JobName
Type: string

JobStatus
Type: string

Filters the list of topic detection jobs based on job status. Returns only jobs with the specified status.

SubmitTimeAfter
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

SubmitTimeBefore
Type: timestamp (string|DateTime or anything parsable by strtotime)

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.

TopicsDetectionJobProperties

Description

Provides information about a topic detection job.

Members
DataAccessRoleArn
Type: string

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your job data.

EndTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the topic detection job was completed.

InputDataConfig
Type: InputDataConfig structure

The input data configuration supplied when you created the topic detection job.

JobArn
Type: string

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

JobId
Type: string

The identifier assigned to the topic detection job.

JobName
Type: string

The name of the topic detection job.

JobStatus
Type: string

The current status of the topic detection job. If the status is Failed, the reason for the failure is shown in the Message field.

Message
Type: string

A description for the status of a job.

NumberOfTopics
Type: int

The number of topics to detect supplied when you created the topic detection job. The default is 10.

OutputDataConfig
Type: OutputDataConfig structure

The output data configuration supplied when you created the topic detection job.

SubmitTime
Type: timestamp (string|DateTime or anything parsable by strtotime)

The time that the topic detection job was submitted for processing.

VolumeKmsKeyId
Type: string

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
Type: VpcConfig structure

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.

ToxicContent

Description

Toxic content analysis result for one string. For more information about toxicity detection, see Toxicity detection in the Amazon Comprehend Developer Guide

Members
Name
Type: string

The name of the toxic content type.

Score
Type: float

Model confidence in the detected content type. Value range is zero to one, where one is highest confidence.

ToxicLabels

Description

Toxicity analysis result for one string. For more information about toxicity detection, see Toxicity detection in the Amazon Comprehend Developer Guide.

Members
Labels
Type: Array of ToxicContent structures

Array of toxic content types identified in the string.

Toxicity
Type: float

Overall toxicity score for the string. Value range is zero to one, where one is the highest confidence.

UnsupportedLanguageException

Description

Amazon Comprehend can't process the language of the input text. For a list of supported languages, Supported languages in the Comprehend Developer Guide.

Members
Message
Type: string

UpdateDataSecurityConfig

Description

Data security configuration.

Members
ModelKmsKeyId
Type: string

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"

VolumeKmsKeyId
Type: string

ID for the KMS key that Amazon Comprehend uses to encrypt the volume.

VpcConfig
Type: VpcConfig structure

Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for the job. For more information, see Amazon VPC.

VpcConfig

Description

Configuration parameters for an optional private Virtual Private Cloud (VPC) containing the resources you are using for the job. For more information, see Amazon VPC.

Members
SecurityGroupIds
Required: Yes
Type: Array of strings

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.

Subnets
Required: Yes
Type: Array of strings

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.

WarningsListItem

Description

The system identified one of the following warnings while processing the input document:

  • The document to classify is plain text, but the classifier is a native document model.

  • The document to classify is semi-structured, but the classifier is a plain-text model.

Members
Page
Type: int

Page number in the input document.

WarnCode
Type: string

The type of warning.

WarnMessage
Type: string

Text message associated with the warning.