Class: AWS.Comprehend

var params = {
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  TextList: [ /* required */
    'STRING_VALUE',
    /* more items */
  ]
};
comprehend.batchDetectEntities(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • TextList — (Array<String>)

    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.

  • LanguageCode — (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.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • ResultList — (Array<map>)

      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.

      • Index — (Integer)

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

      • Entities — (Array<map>)

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

        • Score — (Float)

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

        • 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.

          Possible values include:
          • "PERSON"
          • "LOCATION"
          • "ORGANIZATION"
          • "COMMERCIAL_ITEM"
          • "EVENT"
          • "DATE"
          • "QUANTITY"
          • "TITLE"
          • "OTHER"
        • Text — (String)

          The text of the entity.

        • BeginOffset — (Integer)

          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.

        • EndOffset — (Integer)

          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.

        • BlockReferences — (Array<map>)

          A reference to each block for this entity. This field is empty for plain-text input.

          • BlockId — (String)

            Unique identifier for the block.

          • BeginOffset — (Integer)

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

          • EndOffset — (Integer)

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

          • ChildBlocks — (Array<map>)

            List of child blocks within this block.

            • ChildBlockId — (String)

              Unique identifier for the child block.

            • BeginOffset — (Integer)

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

            • EndOffset — (Integer)

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

    • ErrorList — (Array<map>)

      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.

      • Index — (Integer)

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

      • ErrorCode — (String)

        The numeric error code of the error.

      • ErrorMessage — (String)

        A text description of the error.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  TextList: [ /* required */
    'STRING_VALUE',
    /* more items */
  ]
};
comprehend.batchDetectKeyPhrases(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • TextList — (Array<String>)

    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.

  • LanguageCode — (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.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • ResultList — (Array<map>)

      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.

      • Index — (Integer)

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

      • KeyPhrases — (Array<map>)

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

        • Score — (Float)

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

        • Text — (String)

          The text of a key noun phrase.

        • BeginOffset — (Integer)

          The zero-based offset from the beginning of the source text to the first character in the key phrase.

        • EndOffset — (Integer)

          The zero-based offset from the beginning of the source text to the last character in the key phrase.

    • ErrorList — (Array<map>)

      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.

      • Index — (Integer)

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

      • ErrorCode — (String)

        The numeric error code of the error.

      • ErrorMessage — (String)

        A text description of the error.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  TextList: [ /* required */
    'STRING_VALUE',
    /* more items */
  ]
};
comprehend.batchDetectSentiment(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • TextList — (Array<String>)

    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.

  • LanguageCode — (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.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • ResultList — (Array<map>)

      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.

      • Index — (Integer)

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

      • Sentiment — (String)

        The sentiment detected in the document.

        Possible values include:
        • "POSITIVE"
        • "NEGATIVE"
        • "NEUTRAL"
        • "MIXED"
      • SentimentScore — (map)

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

        • Positive — (Float)

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

        • Negative — (Float)

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

        • Neutral — (Float)

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

        • Mixed — (Float)

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

    • ErrorList — (Array<map>)

      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.

      • Index — (Integer)

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

      • ErrorCode — (String)

        The numeric error code of the error.

      • ErrorMessage — (String)

        A text description of the error.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  LanguageCode: en | es | fr | de | it | pt, /* required */
  TextList: [ /* required */
    'STRING_VALUE',
    /* more items */
  ]
};
comprehend.batchDetectSyntax(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • TextList — (Array<String>)

    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.

  • LanguageCode — (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.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • ResultList — (Array<map>)

      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.

      • Index — (Integer)

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

      • SyntaxTokens — (Array<map>)

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

        • TokenId — (Integer)

          A unique identifier for a token.

        • Text — (String)

          The word that was recognized in the source text.

        • BeginOffset — (Integer)

          The zero-based offset from the beginning of the source text to the first character in the word.

        • EndOffset — (Integer)

          The zero-based offset from the beginning of the source text to the last character in the word.

        • PartOfSpeech — (map)

          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.

          • Tag — (String)

            Identifies the part of speech that the token represents.

            Possible values include:
            • "ADJ"
            • "ADP"
            • "ADV"
            • "AUX"
            • "CONJ"
            • "CCONJ"
            • "DET"
            • "INTJ"
            • "NOUN"
            • "NUM"
            • "O"
            • "PART"
            • "PRON"
            • "PROPN"
            • "PUNCT"
            • "SCONJ"
            • "SYM"
            • "VERB"
          • Score — (Float)

            The confidence that Amazon Comprehend has that the part of speech was correctly identified.

    • ErrorList — (Array<map>)

      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.

      • Index — (Integer)

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

      • ErrorCode — (String)

        The numeric error code of the error.

      • ErrorMessage — (String)

        A text description of the error.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  TextList: [ /* required */
    'STRING_VALUE',
    /* more items */
  ]
};
comprehend.batchDetectTargetedSentiment(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • TextList — (Array<String>)

    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.

  • LanguageCode — (String)

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

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • ResultList — (Array<map>)

      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.

      • Index — (Integer)

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

      • Entities — (Array<map>)

        An array of targeted sentiment entities.

        • DescriptiveMentionIndex — (Array<Integer>)

          One or more index into the Mentions array that provides the best name for the entity group.

        • Mentions — (Array<map>)

          An array of mentions of the entity in the document. The array represents a co-reference group. See Co-reference group for an example.

          • Score — (Float)

            Model confidence that the entity is relevant. Value range is zero to one, where one is highest confidence.

          • GroupScore — (Float)

            The confidence that all the entities mentioned in the group relate to the same entity.

          • Text — (String)

            The text in the document that identifies the entity.

          • Type — (String)

            The type of the entity. Amazon Comprehend supports a variety of entity types.

            Possible values include:
            • "PERSON"
            • "LOCATION"
            • "ORGANIZATION"
            • "FACILITY"
            • "BRAND"
            • "COMMERCIAL_ITEM"
            • "MOVIE"
            • "MUSIC"
            • "BOOK"
            • "SOFTWARE"
            • "GAME"
            • "PERSONAL_TITLE"
            • "EVENT"
            • "DATE"
            • "QUANTITY"
            • "ATTRIBUTE"
            • "OTHER"
          • MentionSentiment — (map)

            Contains the sentiment and sentiment score for the mention.

            • Sentiment — (String)

              The sentiment of the mention.

              Possible values include:
              • "POSITIVE"
              • "NEGATIVE"
              • "NEUTRAL"
              • "MIXED"
            • SentimentScore — (map)

              Describes the level of confidence that Amazon Comprehend has in the accuracy of its detection of sentiments.

              • Positive — (Float)

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

              • Negative — (Float)

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

              • Neutral — (Float)

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

              • Mixed — (Float)

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

          • BeginOffset — (Integer)

            The offset into the document text where the mention begins.

          • EndOffset — (Integer)

            The offset into the document text where the mention ends.

    • ErrorList — (Array<map>)

      List of errors that the operation can return.

      • Index — (Integer)

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

      • ErrorCode — (String)

        The numeric error code of the error.

      • ErrorMessage — (String)

        A text description of the error.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  EndpointArn: 'STRING_VALUE', /* required */
  Bytes: Buffer.from('...') || 'STRING_VALUE' /* Strings will be Base-64 encoded on your behalf */,
  DocumentReaderConfig: {
    DocumentReadAction: TEXTRACT_DETECT_DOCUMENT_TEXT | TEXTRACT_ANALYZE_DOCUMENT, /* required */
    DocumentReadMode: SERVICE_DEFAULT | FORCE_DOCUMENT_READ_ACTION,
    FeatureTypes: [
      TABLES | FORMS,
      /* more items */
    ]
  },
  Text: 'STRING_VALUE'
};
comprehend.classifyDocument(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • Text — (String)

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

  • EndpointArn — (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.

  • Bytes — (Buffer, Typed Array, Blob, String)

    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 — (map)

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

    • DocumentReadAction — required — (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.

      Possible values include:
      • "TEXTRACT_DETECT_DOCUMENT_TEXT"
      • "TEXTRACT_ANALYZE_DOCUMENT"
    • DocumentReadMode — (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.

      Possible values include:
      • "SERVICE_DEFAULT"
      • "FORCE_DOCUMENT_READ_ACTION"
    • FeatureTypes — (Array<String>)

      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.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • Classes — (Array<map>)

      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.

      • Name — (String)

        The name of the class.

      • Score — (Float)

        The confidence score that Amazon Comprehend has this class correctly attributed.

      • Page — (Integer)

        Page number in the input document. This field is present in the response only if your request includes the Byte parameter.

    • Labels — (Array<map>)

      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.

      • Name — (String)

        The name of the label.

      • Score — (Float)

        The confidence score that Amazon Comprehend has this label correctly attributed.

      • Page — (Integer)

        Page number where the label occurs. This field is present in the response only if your request includes the Byte parameter.

    • DocumentMetadata — (map)

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

      • Pages — (Integer)

        Number of pages in the document.

      • ExtractedCharacters — (Array<map>)

        List of pages in the document, with the number of characters extracted from each page.

        • Page — (Integer)

          Page number.

        • Count — (Integer)

          Number of characters extracted from each page.

    • DocumentType — (Array<map>)

      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.

      • Page — (Integer)

        Page number.

      • Type — (String)

        Document type.

        Possible values include:
        • "NATIVE_PDF"
        • "SCANNED_PDF"
        • "MS_WORD"
        • "IMAGE"
        • "PLAIN_TEXT"
        • "TEXTRACT_DETECT_DOCUMENT_TEXT_JSON"
        • "TEXTRACT_ANALYZE_DOCUMENT_JSON"
    • Errors — (Array<map>)

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

      • Page — (Integer)

        Page number where the error occurred.

      • ErrorCode — (String)

        Error code for the cause of the error.

        Possible values include:
        • "TEXTRACT_BAD_PAGE"
        • "TEXTRACT_PROVISIONED_THROUGHPUT_EXCEEDED"
        • "PAGE_CHARACTERS_EXCEEDED"
        • "PAGE_SIZE_EXCEEDED"
        • "INTERNAL_SERVER_ERROR"
      • ErrorMessage — (String)

        Text message explaining the reason for the error.

    • Warnings — (Array<map>)

      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.

      • Page — (Integer)

        Page number in the input document.

      • WarnCode — (String)

        The type of warning.

        Possible values include:
        • "INFERENCING_PLAINTEXT_WITH_NATIVE_TRAINED_MODEL"
        • "INFERENCING_NATIVE_DOCUMENT_WITH_PLAINTEXT_TRAINED_MODEL"
      • WarnMessage — (String)

        Text message associated with the warning.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  Text: 'STRING_VALUE' /* required */
};
comprehend.containsPiiEntities(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • Text — (String)

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

  • LanguageCode — (String)

    The language of the input documents.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • Labels — (Array<map>)

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

      • Name — (String)

        The name of the label.

        Possible values include:
        • "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)

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

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DatasetName: 'STRING_VALUE', /* required */
  FlywheelArn: 'STRING_VALUE', /* required */
  InputDataConfig: { /* required */
    AugmentedManifests: [
      {
        AttributeNames: [ /* required */
          'STRING_VALUE',
          /* more items */
        ],
        S3Uri: 'STRING_VALUE', /* required */
        AnnotationDataS3Uri: 'STRING_VALUE',
        DocumentType: PLAIN_TEXT_DOCUMENT | SEMI_STRUCTURED_DOCUMENT,
        SourceDocumentsS3Uri: 'STRING_VALUE'
      },
      /* more items */
    ],
    DataFormat: COMPREHEND_CSV | AUGMENTED_MANIFEST,
    DocumentClassifierInputDataConfig: {
      S3Uri: 'STRING_VALUE', /* required */
      LabelDelimiter: 'STRING_VALUE'
    },
    EntityRecognizerInputDataConfig: {
      Documents: { /* required */
        S3Uri: 'STRING_VALUE', /* required */
        InputFormat: ONE_DOC_PER_FILE | ONE_DOC_PER_LINE
      },
      Annotations: {
        S3Uri: 'STRING_VALUE' /* required */
      },
      EntityList: {
        S3Uri: 'STRING_VALUE' /* required */
      }
    }
  },
  ClientRequestToken: 'STRING_VALUE',
  DatasetType: TRAIN | TEST,
  Description: 'STRING_VALUE',
  Tags: [
    {
      Key: 'STRING_VALUE', /* required */
      Value: 'STRING_VALUE'
    },
    /* more items */
  ]
};
comprehend.createDataset(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • FlywheelArn — (String)

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

  • DatasetName — (String)

    Name of the dataset.

  • DatasetType — (String)

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

    Possible values include:
    • "TRAIN"
    • "TEST"
  • Description — (String)

    Description of the dataset.

  • InputDataConfig — (map)

    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.

    • AugmentedManifests — (Array<map>)

      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.

      • AttributeNames — required — (Array<String>)

        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.

      • S3Uri — required — (String)

        The Amazon S3 location of the augmented manifest file.

      • AnnotationDataS3Uri — (String)

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

      • SourceDocumentsS3Uri — (String)

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

      • DocumentType — (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.

        Possible values include:
        • "PLAIN_TEXT_DOCUMENT"
        • "SEMI_STRUCTURED_DOCUMENT"
    • DataFormat — (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

      Possible values include:
      • "COMPREHEND_CSV"
      • "AUGMENTED_MANIFEST"
    • DocumentClassifierInputDataConfig — (map)

      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.

      • S3Uri — required — (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.

      • LabelDelimiter — (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.

    • EntityRecognizerInputDataConfig — (map)

      The input properties for training an entity recognizer model.

      • Annotations — (map)

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

        • S3Uri — required — (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.

      • Documents — required — (map)

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

        • S3Uri — required — (String)

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

        • InputFormat — (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.

          Possible values include:
          • "ONE_DOC_PER_FILE"
          • "ONE_DOC_PER_LINE"
      • EntityList — (map)

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

        • S3Uri — required — (String)

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

  • ClientRequestToken — (String)

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

    If a token is not provided, the SDK will use a version 4 UUID.
  • Tags — (Array<map>)

    Tags for the dataset.

    • Key — required — (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 — (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.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • DatasetArn — (String)

      The ARN of the dataset.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DataAccessRoleArn: 'STRING_VALUE', /* required */
  DocumentClassifierName: 'STRING_VALUE', /* required */
  InputDataConfig: { /* required */
    AugmentedManifests: [
      {
        AttributeNames: [ /* required */
          'STRING_VALUE',
          /* more items */
        ],
        S3Uri: 'STRING_VALUE', /* required */
        AnnotationDataS3Uri: 'STRING_VALUE',
        DocumentType: PLAIN_TEXT_DOCUMENT | SEMI_STRUCTURED_DOCUMENT,
        SourceDocumentsS3Uri: 'STRING_VALUE',
        Split: TRAIN | TEST
      },
      /* more items */
    ],
    DataFormat: COMPREHEND_CSV | AUGMENTED_MANIFEST,
    DocumentReaderConfig: {
      DocumentReadAction: TEXTRACT_DETECT_DOCUMENT_TEXT | TEXTRACT_ANALYZE_DOCUMENT, /* required */
      DocumentReadMode: SERVICE_DEFAULT | FORCE_DOCUMENT_READ_ACTION,
      FeatureTypes: [
        TABLES | FORMS,
        /* more items */
      ]
    },
    DocumentType: PLAIN_TEXT_DOCUMENT | SEMI_STRUCTURED_DOCUMENT,
    Documents: {
      S3Uri: 'STRING_VALUE', /* required */
      TestS3Uri: 'STRING_VALUE'
    },
    LabelDelimiter: 'STRING_VALUE',
    S3Uri: 'STRING_VALUE',
    TestS3Uri: 'STRING_VALUE'
  },
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  ClientRequestToken: 'STRING_VALUE',
  Mode: MULTI_CLASS | MULTI_LABEL,
  ModelKmsKeyId: 'STRING_VALUE',
  ModelPolicy: 'STRING_VALUE',
  OutputDataConfig: {
    FlywheelStatsS3Prefix: 'STRING_VALUE',
    KmsKeyId: 'STRING_VALUE',
    S3Uri: 'STRING_VALUE'
  },
  Tags: [
    {
      Key: 'STRING_VALUE', /* required */
      Value: 'STRING_VALUE'
    },
    /* more items */
  ],
  VersionName: 'STRING_VALUE',
  VolumeKmsKeyId: 'STRING_VALUE',
  VpcConfig: {
    SecurityGroupIds: [ /* required */
      'STRING_VALUE',
      /* more items */
    ],
    Subnets: [ /* required */
      'STRING_VALUE',
      /* more items */
    ]
  }
};
comprehend.createDocumentClassifier(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • DocumentClassifierName — (String)

    The name of the document classifier.

  • VersionName — (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.

  • DataAccessRoleArn — (String)

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

  • Tags — (Array<map>)

    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.

    • Key — required — (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 — (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.

  • InputDataConfig — (map)

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

    • DataFormat — (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.

      Possible values include:
      • "COMPREHEND_CSV"
      • "AUGMENTED_MANIFEST"
    • S3Uri — (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 — (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.

    • LabelDelimiter — (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.

    • AugmentedManifests — (Array<map>)

      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.

      • S3Uri — required — (String)

        The Amazon S3 location of the augmented manifest file.

      • Split — (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.

        Possible values include:
        • "TRAIN"
        • "TEST"
      • AttributeNames — required — (Array<String>)

        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.

      • AnnotationDataS3Uri — (String)

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

      • SourceDocumentsS3Uri — (String)

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

      • DocumentType — (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.

        Possible values include:
        • "PLAIN_TEXT_DOCUMENT"
        • "SEMI_STRUCTURED_DOCUMENT"
    • DocumentType — (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.

      Possible values include:
      • "PLAIN_TEXT_DOCUMENT"
      • "SEMI_STRUCTURED_DOCUMENT"
    • Documents — (map)

      The S3 location of the training documents. This parameter is required in a request to create a native document model.

      • S3Uri — required — (String)

        The S3 URI location of the training documents specified in the S3Uri CSV file.

      • TestS3Uri — (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.

    • DocumentReaderConfig — (map)

      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.

      • DocumentReadAction — required — (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.

        Possible values include:
        • "TEXTRACT_DETECT_DOCUMENT_TEXT"
        • "TEXTRACT_ANALYZE_DOCUMENT"
      • DocumentReadMode — (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.

        Possible values include:
        • "SERVICE_DEFAULT"
        • "FORCE_DOCUMENT_READ_ACTION"
      • FeatureTypes — (Array<String>)

        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.

  • OutputDataConfig — (map)

    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.

    • S3Uri — (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.

    • KmsKeyId — (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"

    • FlywheelStatsS3Prefix — (String)

      The Amazon S3 prefix for the data lake location of the flywheel statistics.

  • ClientRequestToken — (String)

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

    If a token is not provided, the SDK will use a version 4 UUID.
  • LanguageCode — (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.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"
  • VolumeKmsKeyId — (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 — (map)

    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.

    • SecurityGroupIds — required — (Array<String>)

      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 — (Array<String>)

      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.

  • Mode — (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 (|).

    Possible values include:
    • "MULTI_CLASS"
    • "MULTI_LABEL"
  • ModelKmsKeyId — (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 — (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"]}'

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • DocumentClassifierArn — (String)

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

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DesiredInferenceUnits: 'NUMBER_VALUE', /* required */
  EndpointName: 'STRING_VALUE', /* required */
  ClientRequestToken: 'STRING_VALUE',
  DataAccessRoleArn: 'STRING_VALUE',
  FlywheelArn: 'STRING_VALUE',
  ModelArn: 'STRING_VALUE',
  Tags: [
    {
      Key: 'STRING_VALUE', /* required */
      Value: 'STRING_VALUE'
    },
    /* more items */
  ]
};
comprehend.createEndpoint(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • EndpointName — (String)

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

  • ModelArn — (String)

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

  • DesiredInferenceUnits — (Integer)

    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.

  • ClientRequestToken — (String)

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

    If a token is not provided, the SDK will use a version 4 UUID.
  • Tags — (Array<map>)

    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.

    • Key — required — (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 — (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.

  • DataAccessRoleArn — (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).

  • FlywheelArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • EndpointArn — (String)

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

    • ModelArn — (String)

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

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DataAccessRoleArn: 'STRING_VALUE', /* required */
  InputDataConfig: { /* required */
    EntityTypes: [ /* required */
      {
        Type: 'STRING_VALUE' /* required */
      },
      /* more items */
    ],
    Annotations: {
      S3Uri: 'STRING_VALUE', /* required */
      TestS3Uri: 'STRING_VALUE'
    },
    AugmentedManifests: [
      {
        AttributeNames: [ /* required */
          'STRING_VALUE',
          /* more items */
        ],
        S3Uri: 'STRING_VALUE', /* required */
        AnnotationDataS3Uri: 'STRING_VALUE',
        DocumentType: PLAIN_TEXT_DOCUMENT | SEMI_STRUCTURED_DOCUMENT,
        SourceDocumentsS3Uri: 'STRING_VALUE',
        Split: TRAIN | TEST
      },
      /* more items */
    ],
    DataFormat: COMPREHEND_CSV | AUGMENTED_MANIFEST,
    Documents: {
      S3Uri: 'STRING_VALUE', /* required */
      InputFormat: ONE_DOC_PER_FILE | ONE_DOC_PER_LINE,
      TestS3Uri: 'STRING_VALUE'
    },
    EntityList: {
      S3Uri: 'STRING_VALUE' /* required */
    }
  },
  LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
  RecognizerName: 'STRING_VALUE', /* required */
  ClientRequestToken: 'STRING_VALUE',
  ModelKmsKeyId: 'STRING_VALUE',
  ModelPolicy: 'STRING_VALUE',
  Tags: [
    {
      Key: 'STRING_VALUE', /* required */
      Value: 'STRING_VALUE'
    },
    /* more items */
  ],
  VersionName: 'STRING_VALUE',
  VolumeKmsKeyId: 'STRING_VALUE',
  VpcConfig: {
    SecurityGroupIds: [ /* required */
      'STRING_VALUE',
      /* more items */
    ],
    Subnets: [ /* required */
      'STRING_VALUE',
      /* more items */
    ]
  }
};
comprehend.createEntityRecognizer(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • RecognizerName — (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.

  • VersionName — (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.

  • DataAccessRoleArn — (String)

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

  • Tags — (Array<map>)

    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.

    • Key — required — (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 — (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.

  • InputDataConfig — (map)

    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.

    • DataFormat — (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.

      Possible values include:
      • "COMPREHEND_CSV"
      • "AUGMENTED_MANIFEST"
    • EntityTypes — required — (Array<map>)

      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).

      • Type — required — (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).

    • Documents — (map)

      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.

      • S3Uri — required — (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 — (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.

      • InputFormat — (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.

        Possible values include:
        • "ONE_DOC_PER_FILE"
        • "ONE_DOC_PER_LINE"
    • Annotations — (map)

      The S3 location of the CSV file that annotates your training documents.

      • S3Uri — required — (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 — (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.

    • EntityList — (map)

      The S3 location of the CSV file that has the entity list for your custom entity recognizer.

      • S3Uri — required — (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.

    • AugmentedManifests — (Array<map>)

      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.

      • S3Uri — required — (String)

        The Amazon S3 location of the augmented manifest file.

      • Split — (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.

        Possible values include:
        • "TRAIN"
        • "TEST"
      • AttributeNames — required — (Array<String>)

        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.

      • AnnotationDataS3Uri — (String)

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

      • SourceDocumentsS3Uri — (String)

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

      • DocumentType — (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.

        Possible values include:
        • "PLAIN_TEXT_DOCUMENT"
        • "SEMI_STRUCTURED_DOCUMENT"
  • ClientRequestToken — (String)

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

    If a token is not provided, the SDK will use a version 4 UUID.
  • LanguageCode — (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.

    Possible values include:
    • "en"
    • "es"
    • "fr"
    • "de"
    • "it"
    • "pt"
    • "ar"
    • "hi"
    • "ja"
    • "ko"
    • "zh"
    • "zh-TW"
  • VolumeKmsKeyId — (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 — (map)

    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.

    • SecurityGroupIds — required — (Array<String>)

      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 — (Array<String>)

      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.

  • ModelKmsKeyId — (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 — (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"]}'

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • EntityRecognizerArn — (String)

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

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DataAccessRoleArn: 'STRING_VALUE', /* required */
  DataLakeS3Uri: 'STRING_VALUE', /* required */
  FlywheelName: 'STRING_VALUE', /* required */
  ActiveModelArn: 'STRING_VALUE',
  ClientRequestToken: 'STRING_VALUE',
  DataSecurityConfig: {
    DataLakeKmsKeyId: 'STRING_VALUE',
    ModelKmsKeyId: 'STRING_VALUE',
    VolumeKmsKeyId: 'STRING_VALUE',
    VpcConfig: {
      SecurityGroupIds: [ /* required */
        'STRING_VALUE',
        /* more items */
      ],
      Subnets: [ /* required */
        'STRING_VALUE',
        /* more items */
      ]
    }
  },
  ModelType: DOCUMENT_CLASSIFIER | ENTITY_RECOGNIZER,
  Tags: [
    {
      Key: 'STRING_VALUE', /* required */
      Value: 'STRING_VALUE'
    },
    /* more items */
  ],
  TaskConfig: {
    LanguageCode: en | es | fr | de | it | pt | ar | hi | ja | ko | zh | zh-TW, /* required */
    DocumentClassificationConfig: {
      Mode: MULTI_CLASS | MULTI_LABEL, /* required */
      Labels: [
        'STRING_VALUE',
        /* more items */
      ]
    },
    EntityRecognitionConfig: {
      EntityTypes: [ /* required */
        {
          Type: 'STRING_VALUE' /* required */
        },
        /* more items */
      ]
    }
  }
};
comprehend.createFlywheel(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • FlywheelName — (String)

    Name for the flywheel.

  • ActiveModelArn — (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.

  • DataAccessRoleArn — (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.

  • TaskConfig — (map)

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

    • LanguageCode — required — (String)

      Language code for the language that the model supports.

      Possible values include:
      • "en"
      • "es"
      • "fr"
      • "de"
      • "it"
      • "pt"
      • "ar"
      • "hi"
      • "ja"
      • "ko"
      • "zh"
      • "zh-TW"
    • DocumentClassificationConfig — (map)

      Configuration required for a document classification model.

      • Mode — required — (String)

        Classification mode indicates whether the documents are MULTI_CLASS or MULTI_LABEL.

        Possible values include:
        • "MULTI_CLASS"
        • "MULTI_LABEL"
      • Labels — (Array<String>)

        One or more labels to associate with the custom classifier.

    • EntityRecognitionConfig — (map)

      Configuration required for an entity recognition model.

      • EntityTypes — required — (Array<map>)

        Up to 25 entity types that the model is trained to recognize.

        • Type — required — (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).

  • ModelType — (String)

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

    Possible values include:
    • "DOCUMENT_CLASSIFIER"
    • "ENTITY_RECOGNIZER"
  • DataLakeS3Uri — (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 — (map)

    Data security configurations.

    • ModelKmsKeyId — (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 — (String)

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

    • DataLakeKmsKeyId — (String)

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

    • VpcConfig — (map)

      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.

      • SecurityGroupIds — required — (Array<String>)

        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 — (Array<String>)

        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.

  • ClientRequestToken — (String)

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

    If a token is not provided, the SDK will use a version 4 UUID.
  • Tags — (Array<map>)

    The tags to associate with this flywheel.

    • Key — required — (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 — (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.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • FlywheelArn — (String)

      The Amazon Resource Number (ARN) of the flywheel.

    • ActiveModelArn — (String)

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

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DocumentClassifierArn: 'STRING_VALUE' /* required */
};
comprehend.deleteDocumentClassifier(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • DocumentClassifierArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  EndpointArn: 'STRING_VALUE' /* required */
};
comprehend.deleteEndpoint(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • EndpointArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  EntityRecognizerArn: 'STRING_VALUE' /* required */
};
comprehend.deleteEntityRecognizer(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • EntityRecognizerArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  FlywheelArn: 'STRING_VALUE' /* required */
};
comprehend.deleteFlywheel(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • FlywheelArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  ResourceArn: 'STRING_VALUE', /* required */
  PolicyRevisionId: 'STRING_VALUE'
};
comprehend.deleteResourcePolicy(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • ResourceArn — (String)

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

  • PolicyRevisionId — (String)

    The revision ID of the policy to delete.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DatasetArn: 'STRING_VALUE' /* required */
};
comprehend.describeDataset(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • DatasetArn — (String)

    The ARN of the dataset.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • DatasetProperties — (map)

      The dataset properties.

      • DatasetArn — (String)

        The ARN of the dataset.

      • DatasetName — (String)

        The name of the dataset.

      • DatasetType — (String)

        The dataset type (training data or test data).

        Possible values include:
        • "TRAIN"
        • "TEST"
      • DatasetS3Uri — (String)

        The S3 URI where the dataset is stored.

      • Description — (String)

        Description of the dataset.

      • Status — (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.

        Possible values include:
        • "CREATING"
        • "COMPLETED"
        • "FAILED"
      • Message — (String)

        A description of the status of the dataset.

      • NumberOfDocuments — (Integer)

        The number of documents in the dataset.

      • CreationTime — (Date)

        Creation time of the dataset.

      • EndTime — (Date)

        Time when the data from the dataset becomes available in the data lake.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  JobId: 'STRING_VALUE' /* required */
};
comprehend.describeDocumentClassificationJob(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • JobId — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • DocumentClassificationJobProperties — (map)

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

      • JobId — (String)

        The identifier assigned to the document classification job.

      • JobArn — (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

      • JobName — (String)

        The name that you assigned to the document classification job.

      • JobStatus — (String)

        The current status of the document classification job. If the status is FAILED, the Message field shows the reason for the failure.

        Possible values include:
        • "SUBMITTED"
        • "IN_PROGRESS"
        • "COMPLETED"
        • "FAILED"
        • "STOP_REQUESTED"
        • "STOPPED"
      • Message — (String)

        A description of the status of the job.

      • SubmitTime — (Date)

        The time that the document classification job was submitted for processing.

      • EndTime — (Date)

        The time that the document classification job completed.

      • DocumentClassifierArn — (String)

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

      • InputDataConfig — (map)

        The input data configuration that you supplied when you created the document classification job.

        • S3Uri — required — (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.

        • InputFormat — (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.

          Possible values include:
          • "ONE_DOC_PER_FILE"
          • "ONE_DOC_PER_LINE"
        • DocumentReaderConfig — (map)

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

          • DocumentReadAction — required — (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.

            Possible values include:
            • "TEXTRACT_DETECT_DOCUMENT_TEXT"
            • "TEXTRACT_ANALYZE_DOCUMENT"
          • DocumentReadMode — (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.

            Possible values include:
            • "SERVICE_DEFAULT"
            • "FORCE_DOCUMENT_READ_ACTION"
          • FeatureTypes — (Array<String>)

            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.

      • OutputDataConfig — (map)

        The output data configuration that you supplied when you created the document classification job.

        • S3Uri — required — (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.

        • KmsKeyId — (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"

      • DataAccessRoleArn — (String)

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

      • VolumeKmsKeyId — (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 — (map)

        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.

        • SecurityGroupIds — required — (Array<String>)

          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 — (Array<String>)

          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.

      • FlywheelArn — (String)

        The Amazon Resource Number (ARN) of the flywheel

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  DocumentClassifierArn: 'STRING_VALUE' /* required */
};
comprehend.describeDocumentClassifier(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • DocumentClassifierArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • DocumentClassifierProperties — (map)

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

      • DocumentClassifierArn — (String)

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

      • LanguageCode — (String)

        The language code for the language of the documents that the classifier was trained on.

        Possible values include:
        • "en"
        • "es"
        • "fr"
        • "de"
        • "it"
        • "pt"
        • "ar"
        • "hi"
        • "ja"
        • "ko"
        • "zh"
        • "zh-TW"
      • Status — (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.

        Possible values include:
        • "SUBMITTED"
        • "TRAINING"
        • "DELETING"
        • "STOP_REQUESTED"
        • "STOPPED"
        • "IN_ERROR"
        • "TRAINED"
        • "TRAINED_WITH_WARNING"
      • Message — (String)

        Additional information about the status of the classifier.

      • SubmitTime — (Date)

        The time that the document classifier was submitted for training.

      • EndTime — (Date)

        The time that training the document classifier completed.

      • TrainingStartTime — (Date)

        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.

      • TrainingEndTime — (Date)

        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.

      • InputDataConfig — (map)

        The input data configuration that you supplied when you created the document classifier for training.

        • DataFormat — (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.

          Possible values include:
          • "COMPREHEND_CSV"
          • "AUGMENTED_MANIFEST"
        • S3Uri — (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 — (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.

        • LabelDelimiter — (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.

        • AugmentedManifests — (Array<map>)

          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.

          • S3Uri — required — (String)

            The Amazon S3 location of the augmented manifest file.

          • Split — (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.

            Possible values include:
            • "TRAIN"
            • "TEST"
          • AttributeNames — required — (Array<String>)

            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.

          • AnnotationDataS3Uri — (String)

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

          • SourceDocumentsS3Uri — (String)

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

          • DocumentType — (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.

            Possible values include:
            • "PLAIN_TEXT_DOCUMENT"
            • "SEMI_STRUCTURED_DOCUMENT"
        • DocumentType — (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.

          Possible values include:
          • "PLAIN_TEXT_DOCUMENT"
          • "SEMI_STRUCTURED_DOCUMENT"
        • Documents — (map)

          The S3 location of the training documents. This parameter is required in a request to create a native document model.

          • S3Uri — required — (String)

            The S3 URI location of the training documents specified in the S3Uri CSV file.

          • TestS3Uri — (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.

        • DocumentReaderConfig — (map)

          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.

          • DocumentReadAction — required — (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.

            Possible values include:
            • "TEXTRACT_DETECT_DOCUMENT_TEXT"
            • "TEXTRACT_ANALYZE_DOCUMENT"
          • DocumentReadMode — (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.

            Possible values include:
            • "SERVICE_DEFAULT"
            • "FORCE_DOCUMENT_READ_ACTION"
          • FeatureTypes — (Array<String>)

            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.

      • OutputDataConfig — (map)

        Provides output results configuration parameters for custom classifier jobs.

        • S3Uri — (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.

        • KmsKeyId — (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"

        • FlywheelStatsS3Prefix — (String)

          The Amazon S3 prefix for the data lake location of the flywheel statistics.

      • ClassifierMetadata — (map)

        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.

        • NumberOfLabels — (Integer)

          The number of labels in the input data.

        • NumberOfTrainedDocuments — (Integer)

          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.

        • NumberOfTestDocuments — (Integer)

          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.

        • EvaluationMetrics — (map)

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

          • Accuracy — (Float)

            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.

          • Precision — (Float)

            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 — (Float)

            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.

          • F1Score — (Float)

            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.

          • MicroPrecision — (Float)

            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 — (Float)

            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.

          • MicroF1Score — (Float)

            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.

          • HammingLoss — (Float)

            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.

      • DataAccessRoleArn — (String)

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

      • VolumeKmsKeyId — (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 — (map)

        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.

        • SecurityGroupIds — required — (Array<String>)

          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 — (Array<String>)

          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.

      • Mode — (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.

        Possible values include:
        • "MULTI_CLASS"
        • "MULTI_LABEL"
      • ModelKmsKeyId — (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"

      • VersionName — (String)

        The version name that you assigned to the document classifier.

      • SourceModelArn — (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.

      • FlywheelArn — (String)

        The Amazon Resource Number (ARN) of the flywheel

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  JobId: 'STRING_VALUE' /* required */
};
comprehend.describeDominantLanguageDetectionJob(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • JobId — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • DominantLanguageDetectionJobProperties — (map)

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

      • JobId — (String)

        The identifier assigned to the dominant language detection job.

      • JobArn — (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

      • JobName — (String)

        The name that you assigned to the dominant language detection job.

      • JobStatus — (String)

        The current status of the dominant language detection job. If the status is FAILED, the Message field shows the reason for the failure.

        Possible values include:
        • "SUBMITTED"
        • "IN_PROGRESS"
        • "COMPLETED"
        • "FAILED"
        • "STOP_REQUESTED"
        • "STOPPED"
      • Message — (String)

        A description for the status of a job.

      • SubmitTime — (Date)

        The time that the dominant language detection job was submitted for processing.

      • EndTime — (Date)

        The time that the dominant language detection job completed.

      • InputDataConfig — (map)

        The input data configuration that you supplied when you created the dominant language detection job.

        • S3Uri — required — (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.

        • InputFormat — (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.

          Possible values include:
          • "ONE_DOC_PER_FILE"
          • "ONE_DOC_PER_LINE"
        • DocumentReaderConfig — (map)

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

          • DocumentReadAction — required — (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.

            Possible values include:
            • "TEXTRACT_DETECT_DOCUMENT_TEXT"
            • "TEXTRACT_ANALYZE_DOCUMENT"
          • DocumentReadMode — (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.

            Possible values include:
            • "SERVICE_DEFAULT"
            • "FORCE_DOCUMENT_READ_ACTION"
          • FeatureTypes — (Array<String>)

            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.

      • OutputDataConfig — (map)

        The output data configuration that you supplied when you created the dominant language detection job.

        • S3Uri — required — (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.

        • KmsKeyId — (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"

      • DataAccessRoleArn — (String)

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

      • VolumeKmsKeyId — (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 — (map)

        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.

        • SecurityGroupIds — required — (Array<String>)

          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 — (Array<String>)

          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.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  EndpointArn: 'STRING_VALUE' /* required */
};
comprehend.describeEndpoint(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • EndpointArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • EndpointProperties — (map)

      Describes information associated with the specific endpoint.

      • EndpointArn — (String)

        The Amazon Resource Number (ARN) of the endpoint.

      • Status — (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.

        Possible values include:
        • "CREATING"
        • "DELETING"
        • "FAILED"
        • "IN_SERVICE"
        • "UPDATING"
      • Message — (String)

        Specifies a reason for failure in cases of Failed status.

      • ModelArn — (String)

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

      • DesiredModelArn — (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

      • DesiredInferenceUnits — (Integer)

        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.

      • CurrentInferenceUnits — (Integer)

        The number of inference units currently used by the model using this endpoint.

      • CreationTime — (Date)

        The creation date and time of the endpoint.

      • LastModifiedTime — (Date)

        The date and time that the endpoint was last modified.

      • DataAccessRoleArn — (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 — (String)

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

      • FlywheelArn — (String)

        The Amazon Resource Number (ARN) of the flywheel

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  JobId: 'STRING_VALUE' /* required */
};
comprehend.describeEntitiesDetectionJob(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • JobId — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • EntitiesDetectionJobProperties — (map)

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

      • JobId — (String)

        The identifier assigned to the entities detection job.

      • JobArn — (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

      • JobName — (String)

        The name that you assigned the entities detection job.

      • JobStatus — (String)

        The current status of the entities detection job. If the status is FAILED, the Message field shows the reason for the failure.

        Possible values include:
        • "SUBMITTED"
        • "IN_PROGRESS"
        • "COMPLETED"
        • "FAILED"
        • "STOP_REQUESTED"
        • "STOPPED"
      • Message — (String)

        A description of the status of a job.

      • SubmitTime — (Date)

        The time that the entities detection job was submitted for processing.

      • EndTime — (Date)

        The time that the entities detection job completed

      • EntityRecognizerArn — (String)

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

      • InputDataConfig — (map)

        The input data configuration that you supplied when you created the entities detection job.

        • S3Uri — required — (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.

        • InputFormat — (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.

          Possible values include:
          • "ONE_DOC_PER_FILE"
          • "ONE_DOC_PER_LINE"
        • DocumentReaderConfig — (map)

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

          • DocumentReadAction — required — (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.

            Possible values include:
            • "TEXTRACT_DETECT_DOCUMENT_TEXT"
            • "TEXTRACT_ANALYZE_DOCUMENT"
          • DocumentReadMode — (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.

            Possible values include:
            • "SERVICE_DEFAULT"
            • "FORCE_DOCUMENT_READ_ACTION"
          • FeatureTypes — (Array<String>)

            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.

      • OutputDataConfig — (map)

        The output data configuration that you supplied when you created the entities detection job.

        • S3Uri — required — (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.

        • KmsKeyId — (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"

      • LanguageCode — (String)

        The language code of the input documents.

        Possible values include:
        • "en"
        • "es"
        • "fr"
        • "de"
        • "it"
        • "pt"
        • "ar"
        • "hi"
        • "ja"
        • "ko"
        • "zh"
        • "zh-TW"
      • DataAccessRoleArn — (String)

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

      • VolumeKmsKeyId — (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 — (map)

        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.

        • SecurityGroupIds — required — (Array<String>)

          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 — (Array<String>)

          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.

      • FlywheelArn — (String)

        The Amazon Resource Name (ARN) of the flywheel associated with this job.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  EntityRecognizerArn: 'STRING_VALUE' /* required */
};
comprehend.describeEntityRecognizer(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • EntityRecognizerArn — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • EntityRecognizerProperties — (map)

      Describes information associated with an entity recognizer.

      • EntityRecognizerArn — (String)

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

      • LanguageCode — (String)

        The language of the input documents. All documents must be in the same language. Only English ("en") is currently supported.

        Possible values include:
        • "en"
        • "es"
        • "fr"
        • "de"
        • "it"
        • "pt"
        • "ar"
        • "hi"
        • "ja"
        • "ko"
        • "zh"
        • "zh-TW"
      • Status — (String)

        Provides the status of the entity recognizer.

        Possible values include:
        • "SUBMITTED"
        • "TRAINING"
        • "DELETING"
        • "STOP_REQUESTED"
        • "STOPPED"
        • "IN_ERROR"
        • "TRAINED"
        • "TRAINED_WITH_WARNING"
      • Message — (String)

        A description of the status of the recognizer.

      • SubmitTime — (Date)

        The time that the recognizer was submitted for processing.

      • EndTime — (Date)

        The time that the recognizer creation completed.

      • TrainingStartTime — (Date)

        The time that training of the entity recognizer started.

      • TrainingEndTime — (Date)

        The time that training of the entity recognizer was completed.

      • InputDataConfig — (map)

        The input data properties of an entity recognizer.

        • DataFormat — (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.

          Possible values include:
          • "COMPREHEND_CSV"
          • "AUGMENTED_MANIFEST"
        • EntityTypes — required — (Array<map>)

          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).

          • Type — required — (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).

        • Documents — (map)

          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.

          • S3Uri — required — (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 — (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.

          • InputFormat — (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.

            Possible values include:
            • "ONE_DOC_PER_FILE"
            • "ONE_DOC_PER_LINE"
        • Annotations — (map)

          The S3 location of the CSV file that annotates your training documents.

          • S3Uri — required — (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 — (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.

        • EntityList — (map)

          The S3 location of the CSV file that has the entity list for your custom entity recognizer.

          • S3Uri — required — (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.

        • AugmentedManifests — (Array<map>)

          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.

          • S3Uri — required — (String)

            The Amazon S3 location of the augmented manifest file.

          • Split — (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.

            Possible values include:
            • "TRAIN"
            • "TEST"
          • AttributeNames — required — (Array<String>)

            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.

          • AnnotationDataS3Uri — (String)

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

          • SourceDocumentsS3Uri — (String)

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

          • DocumentType — (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.

            Possible values include:
            • "PLAIN_TEXT_DOCUMENT"
            • "SEMI_STRUCTURED_DOCUMENT"
      • RecognizerMetadata — (map)

        Provides information about an entity recognizer.

        • NumberOfTrainedDocuments — (Integer)

          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.

        • NumberOfTestDocuments — (Integer)

          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.

        • EvaluationMetrics — (map)

          Detailed information about the accuracy of an entity recognizer.

          • Precision — (Float)

            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 — (Float)

            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.

          • F1Score — (Float)

            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.

        • EntityTypes — (Array<map>)

          Entity types from the metadata of an entity recognizer.

          • Type — (String)

            Type of entity from the list of entity types in the metadata of an entity recognizer.

          • EvaluationMetrics — (map)

            Detailed information about the accuracy of the entity recognizer for a specific item on the list of entity types.

            • Precision — (Float)

              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 — (Float)

              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.

            • F1Score — (Float)

              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.

          • NumberOfTrainMentions — (Integer)

            Indicates the number of times the given entity type was seen in the training data.

      • DataAccessRoleArn — (String)

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

      • VolumeKmsKeyId — (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 — (map)

        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.

        • SecurityGroupIds — required — (Array<String>)

          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 — (Array<String>)

          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.

      • ModelKmsKeyId — (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"

      • VersionName — (String)

        The version name you assigned to the entity recognizer.

      • SourceModelArn — (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.

      • FlywheelArn — (String)

        The Amazon Resource Number (ARN) of the flywheel

      • OutputDataConfig — (map)

        Output data configuration.

        • FlywheelStatsS3Prefix — (String)

          The Amazon S3 prefix for the data lake location of the flywheel statistics.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  JobId: 'STRING_VALUE' /* required */
};
comprehend.describeEventsDetectionJob(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • JobId — (String)

    The identifier of the events detection job.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • EventsDetectionJobProperties — (map)

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

      • JobId — (String)

        The identifier assigned to the events detection job.

      • JobArn — (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

      • JobName — (String)

        The name you assigned the events detection job.

      • JobStatus — (String)

        The current status of the events detection job.

        Possible values include:
        • "SUBMITTED"
        • "IN_PROGRESS"
        • "COMPLETED"
        • "FAILED"
        • "STOP_REQUESTED"
        • "STOPPED"
      • Message — (String)

        A description of the status of the events detection job.

      • SubmitTime — (Date)

        The time that the events detection job was submitted for processing.

      • EndTime — (Date)

        The time that the events detection job completed.

      • InputDataConfig — (map)

        The input data configuration that you supplied when you created the events detection job.

        • S3Uri — required — (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.

        • InputFormat — (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.

          Possible values include:
          • "ONE_DOC_PER_FILE"
          • "ONE_DOC_PER_LINE"
        • DocumentReaderConfig — (map)

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

          • DocumentReadAction — required — (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.

            Possible values include:
            • "TEXTRACT_DETECT_DOCUMENT_TEXT"
            • "TEXTRACT_ANALYZE_DOCUMENT"
          • DocumentReadMode — (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.

            Possible values include:
            • "SERVICE_DEFAULT"
            • "FORCE_DOCUMENT_READ_ACTION"
          • FeatureTypes — (Array<String>)

            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.

      • OutputDataConfig — (map)

        The output data configuration that you supplied when you created the events detection job.

        • S3Uri — required — (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.

        • KmsKeyId — (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"

      • LanguageCode — (String)

        The language code of the input documents.

        Possible values include:
        • "en"
        • "es"
        • "fr"
        • "de"
        • "it"
        • "pt"
        • "ar"
        • "hi"
        • "ja"
        • "ko"
        • "zh"
        • "zh-TW"
      • DataAccessRoleArn — (String)

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

      • TargetEventTypes — (Array<String>)

        The types of events that are detected by the job.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  FlywheelArn: 'STRING_VALUE' /* required */
};
comprehend.describeFlywheel(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • FlywheelArn — (String)

    The Amazon Resource Number (ARN) of the flywheel.

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • FlywheelProperties — (map)

      The flywheel properties.

      • FlywheelArn — (String)

        The Amazon Resource Number (ARN) of the flywheel.

      • ActiveModelArn — (String)

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

      • DataAccessRoleArn — (String)

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

      • TaskConfig — (map)

        Configuration about the model associated with a flywheel.

        • LanguageCode — required — (String)

          Language code for the language that the model supports.

          Possible values include:
          • "en"
          • "es"
          • "fr"
          • "de"
          • "it"
          • "pt"
          • "ar"
          • "hi"
          • "ja"
          • "ko"
          • "zh"
          • "zh-TW"
        • DocumentClassificationConfig — (map)

          Configuration required for a document classification model.

          • Mode — required — (String)

            Classification mode indicates whether the documents are MULTI_CLASS or MULTI_LABEL.

            Possible values include:
            • "MULTI_CLASS"
            • "MULTI_LABEL"
          • Labels — (Array<String>)

            One or more labels to associate with the custom classifier.

        • EntityRecognitionConfig — (map)

          Configuration required for an entity recognition model.

          • EntityTypes — required — (Array<map>)

            Up to 25 entity types that the model is trained to recognize.

            • Type — required — (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).

      • DataLakeS3Uri — (String)

        Amazon S3 URI of the data lake location.

      • DataSecurityConfig — (map)

        Data security configuration.

        • ModelKmsKeyId — (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 — (String)

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

        • DataLakeKmsKeyId — (String)

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

        • VpcConfig — (map)

          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.

          • SecurityGroupIds — required — (Array<String>)

            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 — (Array<String>)

            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.

      • Status — (String)

        The status of the flywheel.

        Possible values include:
        • "CREATING"
        • "ACTIVE"
        • "UPDATING"
        • "DELETING"
        • "FAILED"
      • ModelType — (String)

        Model type of the flywheel's model.

        Possible values include:
        • "DOCUMENT_CLASSIFIER"
        • "ENTITY_RECOGNIZER"
      • Message — (String)

        A description of the status of the flywheel.

      • CreationTime — (Date)

        Creation time of the flywheel.

      • LastModifiedTime — (Date)

        Last modified time for the flywheel.

      • LatestFlywheelIteration — (String)

        The most recent flywheel iteration.

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  FlywheelArn: 'STRING_VALUE', /* required */
  FlywheelIterationId: 'STRING_VALUE' /* required */
};
comprehend.describeFlywheelIteration(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • FlywheelArn — (String)

  • FlywheelIterationId — (String)

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • FlywheelIterationProperties — (map)

      The configuration properties of a flywheel iteration.

      • FlywheelArn — (String)

      • FlywheelIterationId — (String)

      • CreationTime — (Date)

        The creation start time of the flywheel iteration.

      • EndTime — (Date)

        The completion time of this flywheel iteration.

      • Status — (String)

        The status of the flywheel iteration.

        Possible values include:
        • "TRAINING"
        • "EVALUATING"
        • "COMPLETED"
        • "FAILED"
        • "STOP_REQUESTED"
        • "STOPPED"
      • Message — (String)

        A description of the status of the flywheel iteration.

      • EvaluatedModelArn — (String)

        The ARN of the evaluated model associated with this flywheel iteration.

      • EvaluatedModelMetrics — (map)

        The evaluation metrics associated with the evaluated model.

        • AverageF1Score — (Float)

          The average F1 score from the evaluation metrics.

        • AveragePrecision — (Float)

          Average precision metric for the model.

        • AverageRecall — (Float)

          Average recall metric for the model.

        • AverageAccuracy — (Float)

          Average accuracy metric for the model.

      • TrainedModelArn — (String)

        The ARN of the trained model associated with this flywheel iteration.

      • TrainedModelMetrics — (map)

        The metrics associated with the trained model.

        • AverageF1Score — (Float)

          The average F1 score from the evaluation metrics.

        • AveragePrecision — (Float)

          Average precision metric for the model.

        • AverageRecall — (Float)

          Average recall metric for the model.

        • AverageAccuracy — (Float)

          Average accuracy metric for the model.

      • EvaluationManifestS3Prefix — (String)

Returns:

• (AWS.Request) —

  a handle to the operation request for subsequent event callback registration.

var params = {
  JobId: 'STRING_VALUE' /* required */
};
comprehend.describeKeyPhrasesDetectionJob(params, function(err, data) {
  if (err) console.log(err, err.stack); // an error occurred
  else     console.log(data);           // successful response
});

Parameters:

• params (Object) (defaults to: {}) —
  • JobId — (String)

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

Callback (callback):

• function(err, data) { ... }

  Called when a response from the service is returned. If a callback is not supplied, you must call AWS.Request.send() on the returned request object to initiate the request.

  Context (this):

  • (AWS.Response) —

    the response object containing error, data properties, and the original request object.

  Parameters:

  • err (Error) —

    the error object returned from the request. Set to null if the request is successful.

  • data (Object) —

    the de-serialized data returned from the request. Set to null if a request error occurs. The data object has the following properties:

    • KeyPhrasesDetectionJobProperties — (map)

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

      • JobId — (String)

        The identifier assigned to the key phrases detection job.

      • JobArn — (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

      • JobName — (String)

        The name that you assigned the key phrases detection job.

      • JobStatus — (String)

        The current status of the key phrases detection job. If the status is FAILED, the Message field shows the reason for the failure.

        Possible values include:
        • "SUBMITTED"
        • "IN_PROGRESS"
        • "COMPLETED"
        • "FAILED"
        • "STOP_REQUESTED"
        • "STOPPED"
      • Message — (String)

        A description of the status of a job.

      • SubmitTime — (Date)

        The time that the key phrases detection job was submitted for processing.

      • EndTime — (Date)

        The time that the key phrases detection job completed.

      • InputDataConfig — (map)

        The input data configuration that you supplied when you created the key phrases detection job.

        • S3Uri — required — (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.

        • InputFormat — (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.

          Possible values include:
          • "ONE_DOC_PER_FILE"
          • "ONE_DOC_PER_LINE"
        • DocumentReaderConfig — (map)

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

          • DocumentReadAction — required — (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.

            Possible values include:
            • "TEXTRACT_DETECT_DOCUMENT_TEXT"
            • "TEXTRACT_ANALYZE_DOCUMENT"
          • DocumentReadMode — (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.

            Possible values include:
            • "SERVICE_DEFAULT"
            • "FORCE_DOCUMENT_READ_ACTION"
          • FeatureTypes — (Array<String>)

            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.

      • OutputDataConfig — (map)

        The output data configuration that you supplied when you created the key phrases detection job.

        • S3Uri — required — (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.

        • KmsKeyId — (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"

      • LanguageCode — (String)

        The language code of the input documents.

        Possible values include:
        • "en"
        • "es"
        • "fr"
        • "de"
        • "it"
        • "pt"
        • "ar"
        • "hi"
        • "ja"
        • "ko"
        • "zh"
        • "zh-TW"
      • DataAccessRoleArn — (String)

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

      • VolumeKmsKeyId — (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 — (map)

        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.

        • SecurityGroupIds — required — (Array<String>)

          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 — (Array<String>)

          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.