CreateDocumentClassifierCommand

Suggest an Edit

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

Example Syntax

Use a bare-bones client and the command you need to make an API call.

import { ComprehendClient, CreateDocumentClassifierCommand } from "@aws-sdk/client-comprehend"; // ES Modules import
// const { ComprehendClient, CreateDocumentClassifierCommand } = require("@aws-sdk/client-comprehend"); // CommonJS import
const client = new ComprehendClient(config);
const input = { // CreateDocumentClassifierRequest
  DocumentClassifierName: "STRING_VALUE", // required
  VersionName: "STRING_VALUE",
  DataAccessRoleArn: "STRING_VALUE", // required
  Tags: [ // TagList
    { // Tag
      Key: "STRING_VALUE", // required
      Value: "STRING_VALUE",
    },
  ],
  InputDataConfig: { // DocumentClassifierInputDataConfig
    DataFormat: "COMPREHEND_CSV" || "AUGMENTED_MANIFEST",
    S3Uri: "STRING_VALUE",
    TestS3Uri: "STRING_VALUE",
    LabelDelimiter: "STRING_VALUE",
    AugmentedManifests: [ // DocumentClassifierAugmentedManifestsList
      { // AugmentedManifestsListItem
        S3Uri: "STRING_VALUE", // required
        Split: "TRAIN" || "TEST",
        AttributeNames: [ // AttributeNamesList // required
          "STRING_VALUE",
        ],
        AnnotationDataS3Uri: "STRING_VALUE",
        SourceDocumentsS3Uri: "STRING_VALUE",
        DocumentType: "PLAIN_TEXT_DOCUMENT" || "SEMI_STRUCTURED_DOCUMENT",
      },
    ],
    DocumentType: "PLAIN_TEXT_DOCUMENT" || "SEMI_STRUCTURED_DOCUMENT",
    Documents: { // DocumentClassifierDocuments
      S3Uri: "STRING_VALUE", // required
      TestS3Uri: "STRING_VALUE",
    },
    DocumentReaderConfig: { // DocumentReaderConfig
      DocumentReadAction: "TEXTRACT_DETECT_DOCUMENT_TEXT" || "TEXTRACT_ANALYZE_DOCUMENT", // required
      DocumentReadMode: "SERVICE_DEFAULT" || "FORCE_DOCUMENT_READ_ACTION",
      FeatureTypes: [ // ListOfDocumentReadFeatureTypes
        "TABLES" || "FORMS",
      ],
    },
  },
  OutputDataConfig: { // DocumentClassifierOutputDataConfig
    S3Uri: "STRING_VALUE",
    KmsKeyId: "STRING_VALUE",
    FlywheelStatsS3Prefix: "STRING_VALUE",
  },
  ClientRequestToken: "STRING_VALUE",
  LanguageCode: "en" || "es" || "fr" || "de" || "it" || "pt" || "ar" || "hi" || "ja" || "ko" || "zh" || "zh-TW", // required
  VolumeKmsKeyId: "STRING_VALUE",
  VpcConfig: { // VpcConfig
    SecurityGroupIds: [ // SecurityGroupIds // required
      "STRING_VALUE",
    ],
    Subnets: [ // Subnets // required
      "STRING_VALUE",
    ],
  },
  Mode: "MULTI_CLASS" || "MULTI_LABEL",
  ModelKmsKeyId: "STRING_VALUE",
  ModelPolicy: "STRING_VALUE",
};
const command = new CreateDocumentClassifierCommand(input);
const response = await client.send(command);
// { // CreateDocumentClassifierResponse
//   DocumentClassifierArn: "STRING_VALUE",
// };

CreateDocumentClassifierCommand Input

See CreateDocumentClassifierCommandInput for more details

Parameter
Type
Description
DataAccessRoleArn
Required
string | undefined

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

DocumentClassifierName
Required
string | undefined

The name of the document classifier.

InputDataConfig
Required
DocumentClassifierInputDataConfig | undefined

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

LanguageCode
Required
LanguageCode | undefined

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.

ClientRequestToken
string | undefined

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

Mode
DocumentClassifierMode | undefined

Indicates the mode in which the classifier will be trained. The classifier can be trained in multi-class (single-label) mode or multi-label mode. Multi-class mode identifies a single class label for each document and multi-label mode identifies one or more class labels for each document. Multiple labels for an individual document are separated by a delimiter. The default delimiter between labels is a pipe (|).

ModelKmsKeyId
string | undefined

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 | undefined

The resource-based policy to attach to your custom document classifier model. You can use this policy to allow another Amazon Web Services account to import your custom model.

Provide your policy as a JSON body that you enter as a UTF-8 encoded string without line breaks. To provide valid JSON, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy:

"{"attribute": "value", "attribute": ["value"]}"

To avoid escaping quotes, you can use single quotes to enclose the policy and double quotes to enclose the JSON names and values:

'{"attribute": "value", "attribute": ["value"]}'

OutputDataConfig
DocumentClassifierOutputDataConfig | undefined

Specifies the location for the output files from a custom classifier job. This parameter is required for a request that creates a native document model.

Tags
Tag[] | undefined

Tags to associate with the document classifier. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.

VersionName
string | undefined

The version name given to the newly created classifier. Version names can have a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same classifier name in the Amazon Web Services account/Amazon Web Services Region.

VolumeKmsKeyId
string | undefined

ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats:

  • KMS Key ID: "1234abcd-12ab-34cd-56ef-1234567890ab"

  • Amazon Resource Name (ARN) of a KMS Key: "arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"

VpcConfig
VpcConfig | undefined

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 .

CreateDocumentClassifierCommand Output

See CreateDocumentClassifierCommandOutput for details

Parameter
Type
Description
$metadata
Required
ResponseMetadata
Metadata pertaining to this request.
DocumentClassifierArn
string | undefined

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

Throws

Name
Fault
Details
InternalServerException
server

An internal server error occurred. Retry your request.

InvalidRequestException
client

The request is invalid.

KmsKeyValidationException
client

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

ResourceInUseException
client

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

ResourceLimitExceededException
client

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

TooManyRequestsException
client

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

TooManyTagsException
client

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

UnsupportedLanguageException
client

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

ComprehendServiceException
Base exception class for all service exceptions from Comprehend service.