aws logo
AWS Classic v5.41.0, May 15 23

aws.comprehend.DocumentClassifier

Explore with Pulumi AI

Resource for managing an AWS Comprehend Document Classifier.

Example Usage

Basic Usage

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()
    {
        DataAccessRoleArn = aws_iam_role.Example.Arn,
        LanguageCode = "en",
        InputDataConfig = new Aws.Comprehend.Inputs.DocumentClassifierInputDataConfigArgs
        {
            S3Uri = documents.Id.Apply(id => $"s3://{aws_s3_bucket.Test.Bucket}/{id}"),
        },
    }, new CustomResourceOptions
    {
        DependsOn = new[]
        {
            aws_iam_role_policy.Example,
        },
    });

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

    // ...
});
package main

import (
	"fmt"

	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/comprehend"
	"github.com/pulumi/pulumi-aws/sdk/v5/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{
			DataAccessRoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			LanguageCode:      pulumi.String("en"),
			InputDataConfig: &comprehend.DocumentClassifierInputDataConfigArgs{
				S3Uri: documents.ID().ApplyT(func(id string) (string, error) {
					return fmt.Sprintf("s3://%v/%v", aws_s3_bucket.Test.Bucket, id), nil
				}).(pulumi.StringOutput),
			},
		}, pulumi.DependsOn([]pulumi.Resource{
			aws_iam_role_policy.Example,
		}))
		if err != nil {
			return err
		}
		_, err = s3.NewBucketObjectv2(ctx, "entities", nil)
		if err != nil {
			return err
		}
		return nil
	})
}
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()        
            .dataAccessRoleArn(aws_iam_role.example().arn())
            .languageCode("en")
            .inputDataConfig(DocumentClassifierInputDataConfigArgs.builder()
                .s3Uri(documents.id().applyValue(id -> String.format("s3://%s/%s", aws_s3_bucket.test().bucket(),id)))
                .build())
            .build(), CustomResourceOptions.builder()
                .dependsOn(aws_iam_role_policy.example())
                .build());

        var entities = new BucketObjectv2("entities");

    }
}
import pulumi
import pulumi_aws as aws

documents = aws.s3.BucketObjectv2("documents")
# ...
example = aws.comprehend.DocumentClassifier("example",
    data_access_role_arn=aws_iam_role["example"]["arn"],
    language_code="en",
    input_data_config=aws.comprehend.DocumentClassifierInputDataConfigArgs(
        s3_uri=documents.id.apply(lambda id: f"s3://{aws_s3_bucket['test']['bucket']}/{id}"),
    ),
    opts=pulumi.ResourceOptions(depends_on=[aws_iam_role_policy["example"]]))
entities = aws.s3.BucketObjectv2("entities")
# ...
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", {
    dataAccessRoleArn: aws_iam_role.example.arn,
    languageCode: "en",
    inputDataConfig: {
        s3Uri: pulumi.interpolate`s3://${aws_s3_bucket.test.bucket}/${documents.id}`,
    },
}, {
    dependsOn: [aws_iam_role_policy.example],
});
const entities = new aws.s3.BucketObjectv2("entities", {});
// ...
resources:
  example:
    type: aws:comprehend:DocumentClassifier
    properties:
      dataAccessRoleArn: ${aws_iam_role.example.arn}
      languageCode: en
      inputDataConfig:
        s3Uri: s3://${aws_s3_bucket.test.bucket}/${documents.id}
    options:
      dependson:
        - ${aws_iam_role_policy.example}
  documents:
    type: aws:s3:BucketObjectv2
  entities:
    type: aws:s3:BucketObjectv2

Create DocumentClassifier Resource

new DocumentClassifier(name: string, args: DocumentClassifierArgs, opts?: CustomResourceOptions);
@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)
@overload
def DocumentClassifier(resource_name: str,
                       args: DocumentClassifierArgs,
                       opts: Optional[ResourceOptions] = 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.

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.

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

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 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 (-).

OutputDataConfig DocumentClassifierOutputDataConfigArgs

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 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 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 (-).

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 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 (-).

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 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 (-).

outputDataConfig DocumentClassifierOutputDataConfigArgs

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 DocumentClassifierVpcConfigArgs

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 (-).

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 (-).

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.

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.

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.

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.

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.

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.

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)
Resource lookup is not supported in YAML
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 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 (-).

OutputDataConfig DocumentClassifierOutputDataConfigArgs

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.

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 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 (-).

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.

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 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 (-).

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.

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 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 (-).

outputDataConfig DocumentClassifierOutputDataConfigArgs

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.

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 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 (-).

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.

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 (-).

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.

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

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

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

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

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

Comprehend Document Classifier can be imported using the ARN, e.g.,

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

Package Details

Repository
AWS Classic pulumi/pulumi-aws
License
Apache-2.0
Notes

This Pulumi package is based on the aws Terraform Provider.