Docs Home Pulumi IaC Pulumi ESC Pulumi Cloud Packages Tutorials
  1. Packages
  2. AWS
  3. API Docs
  4. comprehend
  5. DocumentClassifier
AWS v6.71.0 published on Friday, Mar 7, 2025 by Pulumi
pulumi/pulumi-aws

aws.comprehend.DocumentClassifier

Explore with Pulumi AI

aws logo
AWS v6.71.0 published on Friday, Mar 7, 2025 by Pulumi
pulumi/pulumi-aws

    Resource for managing an AWS Comprehend Document Classifier.

    Example Usage

    Basic Usage

    import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const documents = new aws.s3.BucketObjectv2("documents", {});
const example = new aws.comprehend.DocumentClassifier("example", {
    name: "example",
    dataAccessRoleArn: exampleAwsIamRole.arn,
    languageCode: "en",
    inputDataConfig: {
        s3Uri: pulumi.interpolate`s3://${test.bucket}/${documents.id}`,
    },
}, {
    dependsOn: [exampleAwsIamRolePolicy],
});
const entities = new aws.s3.BucketObjectv2("entities", {});

    import pulumi
import pulumi_aws as aws

documents = aws.s3.BucketObjectv2("documents")
example = aws.comprehend.DocumentClassifier("example",
    name="example",
    data_access_role_arn=example_aws_iam_role["arn"],
    language_code="en",
    input_data_config={
        "s3_uri": documents.id.apply(lambda id: f"s3://{test['bucket']}/{id}"),
    },
    opts = pulumi.ResourceOptions(depends_on=[example_aws_iam_role_policy]))
entities = aws.s3.BucketObjectv2("entities")

    package main

import (
	"fmt"

	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/comprehend"
	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/s3"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		documents, err := s3.NewBucketObjectv2(ctx, "documents", nil)
		if err != nil {
			return err
		}
		_, err = comprehend.NewDocumentClassifier(ctx, "example", &comprehend.DocumentClassifierArgs{
			Name:              pulumi.String("example"),
			DataAccessRoleArn: pulumi.Any(exampleAwsIamRole.Arn),
			LanguageCode:      pulumi.String("en"),
			InputDataConfig: &comprehend.DocumentClassifierInputDataConfigArgs{
				S3Uri: documents.ID().ApplyT(func(id string) (string, error) {
					return fmt.Sprintf("s3://%v/%v", test.Bucket, id), nil
				}).(pulumi.StringOutput),
			},
		}, pulumi.DependsOn([]pulumi.Resource{
			exampleAwsIamRolePolicy,
		}))
		if err != nil {
			return err
		}
		_, err = s3.NewBucketObjectv2(ctx, "entities", nil)
		if err != nil {
			return err
		}
		return nil
	})
}

    using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;

return await Deployment.RunAsync(() => 
{
    var documents = new Aws.S3.BucketObjectv2("documents");

    var example = new Aws.Comprehend.DocumentClassifier("example", new()
    {
        Name = "example",
        DataAccessRoleArn = exampleAwsIamRole.Arn,
        LanguageCode = "en",
        InputDataConfig = new Aws.Comprehend.Inputs.DocumentClassifierInputDataConfigArgs
        {
            S3Uri = documents.Id.Apply(id => $"s3://{test.Bucket}/{id}"),
        },
    }, new CustomResourceOptions
    {
        DependsOn =
        {
            exampleAwsIamRolePolicy,
        },
    });

    var entities = new Aws.S3.BucketObjectv2("entities");

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.s3.BucketObjectv2;
import com.pulumi.aws.comprehend.DocumentClassifier;
import com.pulumi.aws.comprehend.DocumentClassifierArgs;
import com.pulumi.aws.comprehend.inputs.DocumentClassifierInputDataConfigArgs;
import com.pulumi.resources.CustomResourceOptions;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var documents = new BucketObjectv2("documents");

        var example = new DocumentClassifier("example", DocumentClassifierArgs.builder()
            .name("example")
            .dataAccessRoleArn(exampleAwsIamRole.arn())
            .languageCode("en")
            .inputDataConfig(DocumentClassifierInputDataConfigArgs.builder()
                .s3Uri(documents.id().applyValue(id -> String.format("s3://%s/%s", test.bucket(),id)))
                .build())
            .build(), CustomResourceOptions.builder()
                .dependsOn(exampleAwsIamRolePolicy)
                .build());

        var entities = new BucketObjectv2("entities");

    }
}

    resources:
  example:
    type: aws:comprehend:DocumentClassifier
    properties:
      name: example
      dataAccessRoleArn: ${exampleAwsIamRole.arn}
      languageCode: en
      inputDataConfig:
        s3Uri: s3://${test.bucket}/${documents.id}
    options:
      dependsOn:
        - ${exampleAwsIamRolePolicy}
  documents:
    type: aws:s3:BucketObjectv2
  entities:
    type: aws:s3:BucketObjectv2

    Create DocumentClassifier Resource

    Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

    Constructor syntax

    new DocumentClassifier(name: string, args: DocumentClassifierArgs, opts?: CustomResourceOptions);
    @overload
def DocumentClassifier(resource_name: str,
                       args: DocumentClassifierArgs,
                       opts: Optional[ResourceOptions] = None)

@overload
def DocumentClassifier(resource_name: str,
                       opts: Optional[ResourceOptions] = None,
                       data_access_role_arn: Optional[str] = None,
                       input_data_config: Optional[DocumentClassifierInputDataConfigArgs] = None,
                       language_code: Optional[str] = None,
                       mode: Optional[str] = None,
                       model_kms_key_id: Optional[str] = None,
                       name: Optional[str] = None,
                       output_data_config: Optional[DocumentClassifierOutputDataConfigArgs] = None,
                       tags: Optional[Mapping[str, str]] = None,
                       version_name: Optional[str] = None,
                       version_name_prefix: Optional[str] = None,
                       volume_kms_key_id: Optional[str] = None,
                       vpc_config: Optional[DocumentClassifierVpcConfigArgs] = None)
    func NewDocumentClassifier(ctx *Context, name string, args DocumentClassifierArgs, opts ...ResourceOption) (*DocumentClassifier, error)
    public DocumentClassifier(string name, DocumentClassifierArgs args, CustomResourceOptions? opts = null)
    public DocumentClassifier(String name, DocumentClassifierArgs args)
public DocumentClassifier(String name, DocumentClassifierArgs args, CustomResourceOptions options)

    type: aws:comprehend:DocumentClassifier
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

    Parameters

    name string
    The unique name of the resource.
    args DocumentClassifierArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    resource_name str
    The unique name of the resource.
    args DocumentClassifierArgs
    The arguments to resource properties.
    opts ResourceOptions
    Bag of options to control resource's behavior.
    ctx Context
    Context object for the current deployment.
    name string
    The unique name of the resource.
    args DocumentClassifierArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args DocumentClassifierArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args DocumentClassifierArgs
    The arguments to resource properties.
    options CustomResourceOptions
    Bag of options to control resource's behavior.

    Constructor example

    The following reference example uses placeholder values for all input properties.

    var documentClassifierResource = new Aws.Comprehend.DocumentClassifier("documentClassifierResource", new()
{
    DataAccessRoleArn = "string",
    InputDataConfig = new Aws.Comprehend.Inputs.DocumentClassifierInputDataConfigArgs
    {
        AugmentedManifests = new[]
        {
            new Aws.Comprehend.Inputs.DocumentClassifierInputDataConfigAugmentedManifestArgs
            {
                AttributeNames = new[]
                {
                    "string",
                },
                S3Uri = "string",
                AnnotationDataS3Uri = "string",
                DocumentType = "string",
                SourceDocumentsS3Uri = "string",
                Split = "string",
            },
        },
        DataFormat = "string",
        LabelDelimiter = "string",
        S3Uri = "string",
        TestS3Uri = "string",
    },
    LanguageCode = "string",
    Mode = "string",
    ModelKmsKeyId = "string",
    Name = "string",
    OutputDataConfig = new Aws.Comprehend.Inputs.DocumentClassifierOutputDataConfigArgs
    {
        S3Uri = "string",
        KmsKeyId = "string",
        OutputS3Uri = "string",
    },
    Tags = 
    {
        { "string", "string" },
    },
    VersionName = "string",
    VersionNamePrefix = "string",
    VolumeKmsKeyId = "string",
    VpcConfig = new Aws.Comprehend.Inputs.DocumentClassifierVpcConfigArgs
    {
        SecurityGroupIds = new[]
        {
            "string",
        },
        Subnets = new[]
        {
            "string",
        },
    },
});

    example, err := comprehend.NewDocumentClassifier(ctx, "documentClassifierResource", &comprehend.DocumentClassifierArgs{
	DataAccessRoleArn: pulumi.String("string"),
	InputDataConfig: &comprehend.DocumentClassifierInputDataConfigArgs{
		AugmentedManifests: comprehend.DocumentClassifierInputDataConfigAugmentedManifestArray{
			&comprehend.DocumentClassifierInputDataConfigAugmentedManifestArgs{
				AttributeNames: pulumi.StringArray{
					pulumi.String("string"),
				},
				S3Uri:                pulumi.String("string"),
				AnnotationDataS3Uri:  pulumi.String("string"),
				DocumentType:         pulumi.String("string"),
				SourceDocumentsS3Uri: pulumi.String("string"),
				Split:                pulumi.String("string"),
			},
		},
		DataFormat:     pulumi.String("string"),
		LabelDelimiter: pulumi.String("string"),
		S3Uri:          pulumi.String("string"),
		TestS3Uri:      pulumi.String("string"),
	},
	LanguageCode:  pulumi.String("string"),
	Mode:          pulumi.String("string"),
	ModelKmsKeyId: pulumi.String("string"),
	Name:          pulumi.String("string"),
	OutputDataConfig: &comprehend.DocumentClassifierOutputDataConfigArgs{
		S3Uri:       pulumi.String("string"),
		KmsKeyId:    pulumi.String("string"),
		OutputS3Uri: pulumi.String("string"),
	},
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
	VersionName:       pulumi.String("string"),
	VersionNamePrefix: pulumi.String("string"),
	VolumeKmsKeyId:    pulumi.String("string"),
	VpcConfig: &comprehend.DocumentClassifierVpcConfigArgs{
		SecurityGroupIds: pulumi.StringArray{
			pulumi.String("string"),
		},
		Subnets: pulumi.StringArray{
			pulumi.String("string"),
		},
	},
})

    var documentClassifierResource = new DocumentClassifier("documentClassifierResource", DocumentClassifierArgs.builder()
    .dataAccessRoleArn("string")
    .inputDataConfig(DocumentClassifierInputDataConfigArgs.builder()
        .augmentedManifests(DocumentClassifierInputDataConfigAugmentedManifestArgs.builder()
            .attributeNames("string")
            .s3Uri("string")
            .annotationDataS3Uri("string")
            .documentType("string")
            .sourceDocumentsS3Uri("string")
            .split("string")
            .build())
        .dataFormat("string")
        .labelDelimiter("string")
        .s3Uri("string")
        .testS3Uri("string")
        .build())
    .languageCode("string")
    .mode("string")
    .modelKmsKeyId("string")
    .name("string")
    .outputDataConfig(DocumentClassifierOutputDataConfigArgs.builder()
        .s3Uri("string")
        .kmsKeyId("string")
        .outputS3Uri("string")
        .build())
    .tags(Map.of("string", "string"))
    .versionName("string")
    .versionNamePrefix("string")
    .volumeKmsKeyId("string")
    .vpcConfig(DocumentClassifierVpcConfigArgs.builder()
        .securityGroupIds("string")
        .subnets("string")
        .build())
    .build());

    document_classifier_resource = aws.comprehend.DocumentClassifier("documentClassifierResource",
    data_access_role_arn="string",
    input_data_config={
        "augmented_manifests": [{
            "attribute_names": ["string"],
            "s3_uri": "string",
            "annotation_data_s3_uri": "string",
            "document_type": "string",
            "source_documents_s3_uri": "string",
            "split": "string",
        }],
        "data_format": "string",
        "label_delimiter": "string",
        "s3_uri": "string",
        "test_s3_uri": "string",
    },
    language_code="string",
    mode="string",
    model_kms_key_id="string",
    name="string",
    output_data_config={
        "s3_uri": "string",
        "kms_key_id": "string",
        "output_s3_uri": "string",
    },
    tags={
        "string": "string",
    },
    version_name="string",
    version_name_prefix="string",
    volume_kms_key_id="string",
    vpc_config={
        "security_group_ids": ["string"],
        "subnets": ["string"],
    })

    const documentClassifierResource = new aws.comprehend.DocumentClassifier("documentClassifierResource", {
    dataAccessRoleArn: "string",
    inputDataConfig: {
        augmentedManifests: [{
            attributeNames: ["string"],
            s3Uri: "string",
            annotationDataS3Uri: "string",
            documentType: "string",
            sourceDocumentsS3Uri: "string",
            split: "string",
        }],
        dataFormat: "string",
        labelDelimiter: "string",
        s3Uri: "string",
        testS3Uri: "string",
    },
    languageCode: "string",
    mode: "string",
    modelKmsKeyId: "string",
    name: "string",
    outputDataConfig: {
        s3Uri: "string",
        kmsKeyId: "string",
        outputS3Uri: "string",
    },
    tags: {
        string: "string",
    },
    versionName: "string",
    versionNamePrefix: "string",
    volumeKmsKeyId: "string",
    vpcConfig: {
        securityGroupIds: ["string"],
        subnets: ["string"],
    },
});

    type: aws:comprehend:DocumentClassifier
properties:
    dataAccessRoleArn: string
    inputDataConfig:
        augmentedManifests:
            - annotationDataS3Uri: string
              attributeNames:
                - string
              documentType: string
              s3Uri: string
              sourceDocumentsS3Uri: string
              split: string
        dataFormat: string
        labelDelimiter: string
        s3Uri: string
        testS3Uri: string
    languageCode: string
    mode: string
    modelKmsKeyId: string
    name: string
    outputDataConfig:
        kmsKeyId: string
        outputS3Uri: string
        s3Uri: string
    tags:
        string: string
    versionName: string
    versionNamePrefix: string
    volumeKmsKeyId: string
    vpcConfig:
        securityGroupIds:
            - string
        subnets:
            - string

    DocumentClassifier Resource Properties

    To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

    Inputs

    In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

    The DocumentClassifier resource accepts the following input properties:

    DataAccessRoleArn string
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    InputDataConfig DocumentClassifierInputDataConfig
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    LanguageCode string
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    Mode string
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    ModelKmsKeyId string
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    Name string

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    OutputDataConfig DocumentClassifierOutputDataConfig
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    Tags Dictionary<string, string>
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    VersionName string
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    VersionNamePrefix string
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    VolumeKmsKeyId string
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    VpcConfig DocumentClassifierVpcConfig
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    DataAccessRoleArn string
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    InputDataConfig DocumentClassifierInputDataConfigArgs
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    LanguageCode string
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    Mode string
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    ModelKmsKeyId string
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    Name string

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    OutputDataConfig DocumentClassifierOutputDataConfigArgs
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    Tags map[string]string
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    VersionName string
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    VersionNamePrefix string
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    VolumeKmsKeyId string
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    VpcConfig DocumentClassifierVpcConfigArgs
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    dataAccessRoleArn String
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    inputDataConfig DocumentClassifierInputDataConfig
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    languageCode String
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode String
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    modelKmsKeyId String
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name String

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    outputDataConfig DocumentClassifierOutputDataConfig
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags Map<String,String>
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    versionName String
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    versionNamePrefix String
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volumeKmsKeyId String
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpcConfig DocumentClassifierVpcConfig
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    dataAccessRoleArn string
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    inputDataConfig DocumentClassifierInputDataConfig
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    languageCode string
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode string
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    modelKmsKeyId string
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name string

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    outputDataConfig DocumentClassifierOutputDataConfig
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags {[key: string]: string}
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    versionName string
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    versionNamePrefix string
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volumeKmsKeyId string
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpcConfig DocumentClassifierVpcConfig
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    data_access_role_arn str
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    input_data_config DocumentClassifierInputDataConfigArgs
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    language_code str
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode str
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    model_kms_key_id str
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name str

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    output_data_config DocumentClassifierOutputDataConfigArgs
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags Mapping[str, str]
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    version_name str
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    version_name_prefix str
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volume_kms_key_id str
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpc_config DocumentClassifierVpcConfigArgs
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    dataAccessRoleArn String
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    inputDataConfig Property Map
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    languageCode String
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode String
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    modelKmsKeyId String
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name String

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    outputDataConfig Property Map
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags Map<String>
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    versionName String
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    versionNamePrefix String
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volumeKmsKeyId String
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpcConfig Property Map
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.

    Outputs

    All input properties are implicitly available as output properties. Additionally, the DocumentClassifier resource produces the following output properties:

    Arn string
    ARN of the Document Classifier version.
    Id string
    The provider-assigned unique ID for this managed resource.
    TagsAll Dictionary<string, string>
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    Arn string
    ARN of the Document Classifier version.
    Id string
    The provider-assigned unique ID for this managed resource.
    TagsAll map[string]string
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    arn String
    ARN of the Document Classifier version.
    id String
    The provider-assigned unique ID for this managed resource.
    tagsAll Map<String,String>
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    arn string
    ARN of the Document Classifier version.
    id string
    The provider-assigned unique ID for this managed resource.
    tagsAll {[key: string]: string}
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    arn str
    ARN of the Document Classifier version.
    id str
    The provider-assigned unique ID for this managed resource.
    tags_all Mapping[str, str]
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    arn String
    ARN of the Document Classifier version.
    id String
    The provider-assigned unique ID for this managed resource.
    tagsAll Map<String>
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    Look up Existing DocumentClassifier Resource

    Get an existing DocumentClassifier resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

    public static get(name: string, id: Input<ID>, state?: DocumentClassifierState, opts?: CustomResourceOptions): DocumentClassifier
    @staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        data_access_role_arn: Optional[str] = None,
        input_data_config: Optional[DocumentClassifierInputDataConfigArgs] = None,
        language_code: Optional[str] = None,
        mode: Optional[str] = None,
        model_kms_key_id: Optional[str] = None,
        name: Optional[str] = None,
        output_data_config: Optional[DocumentClassifierOutputDataConfigArgs] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None,
        version_name: Optional[str] = None,
        version_name_prefix: Optional[str] = None,
        volume_kms_key_id: Optional[str] = None,
        vpc_config: Optional[DocumentClassifierVpcConfigArgs] = None) -> DocumentClassifier
    func GetDocumentClassifier(ctx *Context, name string, id IDInput, state *DocumentClassifierState, opts ...ResourceOption) (*DocumentClassifier, error)
    public static DocumentClassifier Get(string name, Input<string> id, DocumentClassifierState? state, CustomResourceOptions? opts = null)
    public static DocumentClassifier get(String name, Output<String> id, DocumentClassifierState state, CustomResourceOptions options)
    resources:  _:    type: aws:comprehend:DocumentClassifier    get:      id: ${id}
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    resource_name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    The following state arguments are supported:
    Arn string
    ARN of the Document Classifier version.
    DataAccessRoleArn string
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    InputDataConfig DocumentClassifierInputDataConfig
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    LanguageCode string
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    Mode string
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    ModelKmsKeyId string
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    Name string

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    OutputDataConfig DocumentClassifierOutputDataConfig
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    Tags Dictionary<string, string>
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    TagsAll Dictionary<string, string>
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    VersionName string
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    VersionNamePrefix string
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    VolumeKmsKeyId string
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    VpcConfig DocumentClassifierVpcConfig
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    Arn string
    ARN of the Document Classifier version.
    DataAccessRoleArn string
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    InputDataConfig DocumentClassifierInputDataConfigArgs
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    LanguageCode string
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    Mode string
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    ModelKmsKeyId string
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    Name string

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    OutputDataConfig DocumentClassifierOutputDataConfigArgs
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    Tags map[string]string
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    TagsAll map[string]string
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    VersionName string
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    VersionNamePrefix string
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    VolumeKmsKeyId string
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    VpcConfig DocumentClassifierVpcConfigArgs
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    arn String
    ARN of the Document Classifier version.
    dataAccessRoleArn String
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    inputDataConfig DocumentClassifierInputDataConfig
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    languageCode String
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode String
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    modelKmsKeyId String
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name String

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    outputDataConfig DocumentClassifierOutputDataConfig
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags Map<String,String>
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    tagsAll Map<String,String>
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    versionName String
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    versionNamePrefix String
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volumeKmsKeyId String
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpcConfig DocumentClassifierVpcConfig
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    arn string
    ARN of the Document Classifier version.
    dataAccessRoleArn string
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    inputDataConfig DocumentClassifierInputDataConfig
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    languageCode string
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode string
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    modelKmsKeyId string
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name string

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    outputDataConfig DocumentClassifierOutputDataConfig
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags {[key: string]: string}
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    tagsAll {[key: string]: string}
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    versionName string
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    versionNamePrefix string
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volumeKmsKeyId string
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpcConfig DocumentClassifierVpcConfig
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    arn str
    ARN of the Document Classifier version.
    data_access_role_arn str
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    input_data_config DocumentClassifierInputDataConfigArgs
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    language_code str
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode str
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    model_kms_key_id str
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name str

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    output_data_config DocumentClassifierOutputDataConfigArgs
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags Mapping[str, str]
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    tags_all Mapping[str, str]
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    version_name str
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    version_name_prefix str
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volume_kms_key_id str
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpc_config DocumentClassifierVpcConfigArgs
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.
    arn String
    ARN of the Document Classifier version.
    dataAccessRoleArn String
    The ARN for an IAM Role which allows Comprehend to read the training and testing data.
    inputDataConfig Property Map
    Configuration for the training and testing data. See the input_data_config Configuration Block section below.
    languageCode String
    Two-letter language code for the language. One of en, es, fr, it, de, or pt.
    mode String
    The document classification mode. One of MULTI_CLASS or MULTI_LABEL. MULTI_CLASS is also known as "Single Label" in the AWS Console.
    modelKmsKeyId String
    KMS Key used to encrypt trained Document Classifiers. Can be a KMS Key ID or a KMS Key ARN.
    name String

    Name for the Document Classifier. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-).

    The following arguments are optional:

    outputDataConfig Property Map
    Configuration for the output results of training. See the output_data_config Configuration Block section below.
    tags Map<String>
    A map of tags to assign to the resource. If configured with a provider default_tags Configuration Block present, tags with matching keys will overwrite those defined at the provider-level.
    tagsAll Map<String>
    A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

    Deprecated: Please use tags instead.

    versionName String
    Name for the version of the Document Classifier. Each version must have a unique name within the Document Classifier. If omitted, the provider will assign a random, unique version name. If explicitly set to "", no version name will be set. Has a maximum length of 63 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name_prefix.
    versionNamePrefix String
    Creates a unique version name beginning with the specified prefix. Has a maximum length of 37 characters. Can contain upper- and lower-case letters, numbers, and hypen (-). Conflicts with version_name.
    volumeKmsKeyId String
    KMS Key used to encrypt storage volumes during job processing. Can be a KMS Key ID or a KMS Key ARN.
    vpcConfig Property Map
    Configuration parameters for VPC to contain Document Classifier resources. See the vpc_config Configuration Block section below.

    Supporting Types

    DocumentClassifierInputDataConfig, DocumentClassifierInputDataConfigArgs

    AugmentedManifests List<DocumentClassifierInputDataConfigAugmentedManifest>
    List of training datasets produced by Amazon SageMaker Ground Truth. Used if data_format is AUGMENTED_MANIFEST. See the augmented_manifests Configuration Block section below.
    DataFormat string
    The format for the training data. One of COMPREHEND_CSV or AUGMENTED_MANIFEST.
    LabelDelimiter string
    Delimiter between labels when training a multi-label classifier. Valid values are |, ~, !, @, #, $, %, ^, *, -, _, +, =, \, :, ;, >, ?, /, <space>, and <tab>. Default is |.
    S3Uri string
    Location of training documents. Used if data_format is COMPREHEND_CSV.
    TestS3Uri string
    AugmentedManifests []DocumentClassifierInputDataConfigAugmentedManifest
    List of training datasets produced by Amazon SageMaker Ground Truth. Used if data_format is AUGMENTED_MANIFEST. See the augmented_manifests Configuration Block section below.
    DataFormat string
    The format for the training data. One of COMPREHEND_CSV or AUGMENTED_MANIFEST.
    LabelDelimiter string
    Delimiter between labels when training a multi-label classifier. Valid values are |, ~, !, @, #, $, %, ^, *, -, _, +, =, \, :, ;, >, ?, /, <space>, and <tab>. Default is |.
    S3Uri string
    Location of training documents. Used if data_format is COMPREHEND_CSV.
    TestS3Uri string
    augmentedManifests List<DocumentClassifierInputDataConfigAugmentedManifest>
    List of training datasets produced by Amazon SageMaker Ground Truth. Used if data_format is AUGMENTED_MANIFEST. See the augmented_manifests Configuration Block section below.
    dataFormat String
    The format for the training data. One of COMPREHEND_CSV or AUGMENTED_MANIFEST.
    labelDelimiter String
    Delimiter between labels when training a multi-label classifier. Valid values are |, ~, !, @, #, $, %, ^, *, -, _, +, =, \, :, ;, >, ?, /, <space>, and <tab>. Default is |.
    s3Uri String
    Location of training documents. Used if data_format is COMPREHEND_CSV.
    testS3Uri String
    augmentedManifests DocumentClassifierInputDataConfigAugmentedManifest[]
    List of training datasets produced by Amazon SageMaker Ground Truth. Used if data_format is AUGMENTED_MANIFEST. See the augmented_manifests Configuration Block section below.
    dataFormat string
    The format for the training data. One of COMPREHEND_CSV or AUGMENTED_MANIFEST.
    labelDelimiter string
    Delimiter between labels when training a multi-label classifier. Valid values are |, ~, !, @, #, $, %, ^, *, -, _, +, =, \, :, ;, >, ?, /, <space>, and <tab>. Default is |.
    s3Uri string
    Location of training documents. Used if data_format is COMPREHEND_CSV.
    testS3Uri string
    augmented_manifests Sequence[DocumentClassifierInputDataConfigAugmentedManifest]
    List of training datasets produced by Amazon SageMaker Ground Truth. Used if data_format is AUGMENTED_MANIFEST. See the augmented_manifests Configuration Block section below.
    data_format str
    The format for the training data. One of COMPREHEND_CSV or AUGMENTED_MANIFEST.
    label_delimiter str
    Delimiter between labels when training a multi-label classifier. Valid values are |, ~, !, @, #, $, %, ^, *, -, _, +, =, \, :, ;, >, ?, /, <space>, and <tab>. Default is |.
    s3_uri str
    Location of training documents. Used if data_format is COMPREHEND_CSV.
    test_s3_uri str
    augmentedManifests List<Property Map>
    List of training datasets produced by Amazon SageMaker Ground Truth. Used if data_format is AUGMENTED_MANIFEST. See the augmented_manifests Configuration Block section below.
    dataFormat String
    The format for the training data. One of COMPREHEND_CSV or AUGMENTED_MANIFEST.
    labelDelimiter String
    Delimiter between labels when training a multi-label classifier. Valid values are |, ~, !, @, #, $, %, ^, *, -, _, +, =, \, :, ;, >, ?, /, <space>, and <tab>. Default is |.
    s3Uri String
    Location of training documents. Used if data_format is COMPREHEND_CSV.
    testS3Uri String

    DocumentClassifierInputDataConfigAugmentedManifest, DocumentClassifierInputDataConfigAugmentedManifestArgs

    AttributeNames List<string>
    The JSON attribute that contains the annotations for the training documents.
    S3Uri string
    Location of augmented manifest file.
    AnnotationDataS3Uri string
    Location of annotation files.
    DocumentType string
    Type of augmented manifest. One of PLAIN_TEXT_DOCUMENT or SEMI_STRUCTURED_DOCUMENT.
    SourceDocumentsS3Uri string
    Location of source PDF files.
    Split string
    Purpose of data in augmented manifest. One of TRAIN or TEST.
    AttributeNames []string
    The JSON attribute that contains the annotations for the training documents.
    S3Uri string
    Location of augmented manifest file.
    AnnotationDataS3Uri string
    Location of annotation files.
    DocumentType string
    Type of augmented manifest. One of PLAIN_TEXT_DOCUMENT or SEMI_STRUCTURED_DOCUMENT.
    SourceDocumentsS3Uri string
    Location of source PDF files.
    Split string
    Purpose of data in augmented manifest. One of TRAIN or TEST.
    attributeNames List<String>
    The JSON attribute that contains the annotations for the training documents.
    s3Uri String
    Location of augmented manifest file.
    annotationDataS3Uri String
    Location of annotation files.
    documentType String
    Type of augmented manifest. One of PLAIN_TEXT_DOCUMENT or SEMI_STRUCTURED_DOCUMENT.
    sourceDocumentsS3Uri String
    Location of source PDF files.
    split String
    Purpose of data in augmented manifest. One of TRAIN or TEST.
    attributeNames string[]
    The JSON attribute that contains the annotations for the training documents.
    s3Uri string
    Location of augmented manifest file.
    annotationDataS3Uri string
    Location of annotation files.
    documentType string
    Type of augmented manifest. One of PLAIN_TEXT_DOCUMENT or SEMI_STRUCTURED_DOCUMENT.
    sourceDocumentsS3Uri string
    Location of source PDF files.
    split string
    Purpose of data in augmented manifest. One of TRAIN or TEST.
    attribute_names Sequence[str]
    The JSON attribute that contains the annotations for the training documents.
    s3_uri str
    Location of augmented manifest file.
    annotation_data_s3_uri str
    Location of annotation files.
    document_type str
    Type of augmented manifest. One of PLAIN_TEXT_DOCUMENT or SEMI_STRUCTURED_DOCUMENT.
    source_documents_s3_uri str
    Location of source PDF files.
    split str
    Purpose of data in augmented manifest. One of TRAIN or TEST.
    attributeNames List<String>
    The JSON attribute that contains the annotations for the training documents.
    s3Uri String
    Location of augmented manifest file.
    annotationDataS3Uri String
    Location of annotation files.
    documentType String
    Type of augmented manifest. One of PLAIN_TEXT_DOCUMENT or SEMI_STRUCTURED_DOCUMENT.
    sourceDocumentsS3Uri String
    Location of source PDF files.
    split String
    Purpose of data in augmented manifest. One of TRAIN or TEST.

    DocumentClassifierOutputDataConfig, DocumentClassifierOutputDataConfigArgs

    S3Uri string
    Destination path for the output documents. The full path to the output file will be returned in output_s3_uri.
    KmsKeyId string
    KMS Key used to encrypt the output documents. Can be a KMS Key ID, a KMS Key ARN, a KMS Alias name, or a KMS Alias ARN.
    OutputS3Uri string
    Full path for the output documents.
    S3Uri string
    Destination path for the output documents. The full path to the output file will be returned in output_s3_uri.
    KmsKeyId string
    KMS Key used to encrypt the output documents. Can be a KMS Key ID, a KMS Key ARN, a KMS Alias name, or a KMS Alias ARN.
    OutputS3Uri string
    Full path for the output documents.
    s3Uri String
    Destination path for the output documents. The full path to the output file will be returned in output_s3_uri.
    kmsKeyId String
    KMS Key used to encrypt the output documents. Can be a KMS Key ID, a KMS Key ARN, a KMS Alias name, or a KMS Alias ARN.
    outputS3Uri String
    Full path for the output documents.
    s3Uri string
    Destination path for the output documents. The full path to the output file will be returned in output_s3_uri.
    kmsKeyId string
    KMS Key used to encrypt the output documents. Can be a KMS Key ID, a KMS Key ARN, a KMS Alias name, or a KMS Alias ARN.
    outputS3Uri string
    Full path for the output documents.
    s3_uri str
    Destination path for the output documents. The full path to the output file will be returned in output_s3_uri.
    kms_key_id str
    KMS Key used to encrypt the output documents. Can be a KMS Key ID, a KMS Key ARN, a KMS Alias name, or a KMS Alias ARN.
    output_s3_uri str
    Full path for the output documents.
    s3Uri String
    Destination path for the output documents. The full path to the output file will be returned in output_s3_uri.
    kmsKeyId String
    KMS Key used to encrypt the output documents. Can be a KMS Key ID, a KMS Key ARN, a KMS Alias name, or a KMS Alias ARN.
    outputS3Uri String
    Full path for the output documents.

    DocumentClassifierVpcConfig, DocumentClassifierVpcConfigArgs

    SecurityGroupIds List<string>
    List of security group IDs.
    Subnets List<string>
    List of VPC subnets.
    SecurityGroupIds []string
    List of security group IDs.
    Subnets []string
    List of VPC subnets.
    securityGroupIds List<String>
    List of security group IDs.
    subnets List<String>
    List of VPC subnets.
    securityGroupIds string[]
    List of security group IDs.
    subnets string[]
    List of VPC subnets.
    security_group_ids Sequence[str]
    List of security group IDs.
    subnets Sequence[str]
    List of VPC subnets.
    securityGroupIds List<String>
    List of security group IDs.
    subnets List<String>
    List of VPC subnets.

    Import

    Using pulumi import, import Comprehend Document Classifier using the ARN. For example:

    $ pulumi import aws:comprehend/documentClassifier:DocumentClassifier example arn:aws:comprehend:us-west-2:123456789012:document_classifier/example

    To learn more about importing existing cloud resources, see Importing resources.

    Package Details

    Repository
    AWS Classic pulumi/pulumi-aws
    License
    Apache-2.0
    Notes
    This Pulumi package is based on the aws Terraform Provider.
    aws logo
    AWS v6.71.0 published on Friday, Mar 7, 2025 by Pulumi
    pulumi/pulumi-aws