AWS Classic

v5.16.0 published on Saturday, Sep 24, 2022 by Pulumi

DataSource

Import

Kendra Data Source can be imported using the unique identifiers of the data_source and index separated by a slash (/) e.g.,

 $ pulumi import aws:kendra/dataSource:DataSource example 1045d08d-66ef-4882-b3ed-dfb7df183e90/b34dfdf7-1f2b-4704-9581-79e00296845f

Example Usage

Basic Usage

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Description = "example",
        LanguageCode = "en",
        Type = "CUSTOM",
        Tags = 
        {
            { "hello", "world" },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId:      pulumi.Any(aws_kendra_index.Example.Id),
			Description:  pulumi.String("example"),
			LanguageCode: pulumi.String("en"),
			Type:         pulumi.String("CUSTOM"),
			Tags: pulumi.StringMap{
				"hello": pulumi.String("world"),
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .description("example")
            .languageCode("en")
            .type("CUSTOM")
            .tags(Map.of("hello", "world"))
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    description="example",
    language_code="en",
    type="CUSTOM",
    tags={
        "hello": "world",
    })
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    description: "example",
    languageCode: "en",
    type: "CUSTOM",
    tags: {
        hello: "world",
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      description: example
      languageCode: en
      type: CUSTOM
      tags:
        hello: world

With Schedule

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "S3",
        RoleArn = aws_iam_role.Example.Arn,
        Schedule = "cron(9 10 1 * ? *)",
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            S3Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationArgs
            {
                BucketName = aws_s3_bucket.Example.Id,
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId:  pulumi.Any(aws_kendra_index.Example.Id),
			Type:     pulumi.String("S3"),
			RoleArn:  pulumi.Any(aws_iam_role.Example.Arn),
			Schedule: pulumi.String("cron(9 10 1 * ? *)"),
			Configuration: &kendra.DataSourceConfigurationArgs{
				S3Configuration: &kendra.DataSourceConfigurationS3ConfigurationArgs{
					BucketName: pulumi.Any(aws_s3_bucket.Example.Id),
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationS3ConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("S3")
            .roleArn(aws_iam_role.example().arn())
            .schedule("cron(9 10 1 * ? *)")
            .configuration(DataSourceConfigurationArgs.builder()
                .s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
                    .bucketName(aws_s3_bucket.example().id())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="S3",
    role_arn=aws_iam_role["example"]["arn"],
    schedule="cron(9 10 1 * ? *)",
    configuration=aws.kendra.DataSourceConfigurationArgs(
        s3_configuration=aws.kendra.DataSourceConfigurationS3ConfigurationArgs(
            bucket_name=aws_s3_bucket["example"]["id"],
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "S3",
    roleArn: aws_iam_role.example.arn,
    schedule: "cron(9 10 1 * ? *)",
    configuration: {
        s3Configuration: {
            bucketName: aws_s3_bucket.example.id,
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: S3
      roleArn: ${aws_iam_role.example.arn}
      schedule: cron(9 10 1 * ? *)
      configuration:
        s3Configuration:
          bucketName: ${aws_s3_bucket.example.id}

With Access Control List

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "S3",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            S3Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationArgs
            {
                AccessControlListConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs
                {
                    KeyPath = $"s3://{aws_s3_bucket.Example.Id}/path-1",
                },
                BucketName = aws_s3_bucket.Example.Id,
            },
        },
    });

});
package main

import (
	"fmt"

	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("S3"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				S3Configuration: &kendra.DataSourceConfigurationS3ConfigurationArgs{
					AccessControlListConfiguration: &kendra.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs{
						KeyPath: pulumi.String(fmt.Sprintf("s3://%v/path-1", aws_s3_bucket.Example.Id)),
					},
					BucketName: pulumi.Any(aws_s3_bucket.Example.Id),
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationS3ConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("S3")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
                    .accessControlListConfiguration(DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs.builder()
                        .keyPath(String.format("s3://%s/path-1", aws_s3_bucket.example().id()))
                        .build())
                    .bucketName(aws_s3_bucket.example().id())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="S3",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        s3_configuration=aws.kendra.DataSourceConfigurationS3ConfigurationArgs(
            access_control_list_configuration=aws.kendra.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs(
                key_path=f"s3://{aws_s3_bucket['example']['id']}/path-1",
            ),
            bucket_name=aws_s3_bucket["example"]["id"],
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "S3",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        s3Configuration: {
            accessControlListConfiguration: {
                keyPath: `s3://${aws_s3_bucket.example.id}/path-1`,
            },
            bucketName: aws_s3_bucket.example.id,
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: S3
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        s3Configuration:
          accessControlListConfiguration:
            keyPath: s3://${aws_s3_bucket.example.id}/path-1
          bucketName: ${aws_s3_bucket.example.id}

With Documents Metadata Configuration

Coming soon!

Coming soon!

package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationS3ConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("S3")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
                    .bucketName(aws_s3_bucket.example().id())
                    .s3Prefix("example")
                    .exclusionPatterns("example")
                    .inclusionPatterns("hello")
                    .inclusionPrefixes("world")
                    .build())
                .build())
            .build());

    }
}

Coming soon!

Coming soon!

resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: S3
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        s3Configuration:
          bucketName: ${aws_s3_bucket.example.id}
          s3Prefix: example
          exclusionPatterns:
            - example
          inclusionPatterns:
            - hello
          inclusionPrefixes:
            - world

With Seed URLs

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL

With Site Maps

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SiteMapsConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs
                    {
                        SiteMaps = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SiteMapsConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs{
							SiteMaps: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .siteMapsConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs.builder()
                            .siteMaps("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                site_maps_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs(
                    site_maps=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            urls: {
                siteMapsConfiguration: {
                    siteMaps: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          urls:
            siteMapsConfiguration:
              siteMaps:
                - REPLACE_WITH_YOUR_URL

With Web Crawler Mode

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        WebCrawlerMode = "SUBDOMAINS",
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							WebCrawlerMode: pulumi.String("SUBDOMAINS"),
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .webCrawlerMode("SUBDOMAINS")
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    web_crawler_mode="SUBDOMAINS",
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            urls: {
                seedUrlConfiguration: {
                    webCrawlerMode: "SUBDOMAINS",
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          urls:
            seedUrlConfiguration:
              webCrawlerMode: SUBDOMAINS
              seedUrls:
                - REPLACE_WITH_YOUR_URL

With Authentication Configuration

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                AuthenticationConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs
                {
                    BasicAuthentications = new[]
                    {
                        new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs
                        {
                            Credentials = aws_secretsmanager_secret.Example.Arn,
                            Host = "a.example.com",
                            Port = 443,
                        },
                    },
                },
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    }, new CustomResourceOptions
    {
        DependsOn = new[]
        {
            aws_secretsmanager_secret_version.Example,
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					AuthenticationConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs{
						BasicAuthentications: kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArray{
							&kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs{
								Credentials: pulumi.Any(aws_secretsmanager_secret.Example.Arn),
								Host:        pulumi.String("a.example.com"),
								Port:        pulumi.Int(443),
							},
						},
					},
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		}, pulumi.DependsOn([]pulumi.Resource{
			aws_secretsmanager_secret_version.Example,
		}))
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .authenticationConfiguration(DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs.builder()
                        .basicAuthentications(DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs.builder()
                            .credentials(aws_secretsmanager_secret.example().arn())
                            .host("a.example.com")
                            .port("443")
                            .build())
                        .build())
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build(), CustomResourceOptions.builder()
                .dependsOn(aws_secretsmanager_secret_version.example())
                .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            authentication_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs(
                basic_authentications=[aws.kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs(
                    credentials=aws_secretsmanager_secret["example"]["arn"],
                    host="a.example.com",
                    port=443,
                )],
            ),
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ),
    opts=pulumi.ResourceOptions(depends_on=[aws_secretsmanager_secret_version["example"]]))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            authenticationConfiguration: {
                basicAuthentications: [{
                    credentials: aws_secretsmanager_secret.example.arn,
                    host: "a.example.com",
                    port: 443,
                }],
            },
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
}, {
    dependsOn: [aws_secretsmanager_secret_version.example],
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          authenticationConfiguration:
            basicAuthentications:
              - credentials: ${aws_secretsmanager_secret.example.arn}
                host: a.example.com
                port: 443
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL
    options:
      dependson:
        - ${aws_secretsmanager_secret_version.example}

With Crawl Depth

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                CrawlDepth = 3,
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					CrawlDepth: pulumi.Int(3),
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .crawlDepth(3)
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            crawl_depth=3,
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            crawlDepth: 3,
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          crawlDepth: 3
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL
using System.Collections.Generic;
using Pulumi;
using Aws = Pulumi.Aws;

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                MaxLinksPerPage = 100,
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					MaxLinksPerPage: pulumi.Int(100),
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .maxLinksPerPage(100)
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            max_links_per_page=100,
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            maxLinksPerPage: 100,
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          maxLinksPerPage: 100
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL

With Max Urls Per Minute Crawl Rate

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                MaxUrlsPerMinuteCrawlRate = 300,
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					MaxUrlsPerMinuteCrawlRate: pulumi.Int(300),
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .maxUrlsPerMinuteCrawlRate(300)
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            max_urls_per_minute_crawl_rate=300,
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            maxUrlsPerMinuteCrawlRate: 300,
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          maxUrlsPerMinuteCrawlRate: 300
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL

With Proxy Configuration

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                ProxyConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs
                {
                    Credentials = aws_secretsmanager_secret.Example.Arn,
                    Host = "a.example.com",
                    Port = 443,
                },
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    }, new CustomResourceOptions
    {
        DependsOn = new[]
        {
            aws_secretsmanager_secret_version.Example,
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					ProxyConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs{
						Credentials: pulumi.Any(aws_secretsmanager_secret.Example.Arn),
						Host:        pulumi.String("a.example.com"),
						Port:        pulumi.Int(443),
					},
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		}, pulumi.DependsOn([]pulumi.Resource{
			aws_secretsmanager_secret_version.Example,
		}))
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .proxyConfiguration(DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs.builder()
                        .credentials(aws_secretsmanager_secret.example().arn())
                        .host("a.example.com")
                        .port("443")
                        .build())
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build(), CustomResourceOptions.builder()
                .dependsOn(aws_secretsmanager_secret_version.example())
                .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            proxy_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs(
                credentials=aws_secretsmanager_secret["example"]["arn"],
                host="a.example.com",
                port=443,
            ),
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ),
    opts=pulumi.ResourceOptions(depends_on=[aws_secretsmanager_secret_version["example"]]))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            proxyConfiguration: {
                credentials: aws_secretsmanager_secret.example.arn,
                host: "a.example.com",
                port: 443,
            },
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
}, {
    dependsOn: [aws_secretsmanager_secret_version.example],
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          proxyConfiguration:
            credentials: ${aws_secretsmanager_secret.example.arn}
            host: a.example.com
            port: 443
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL
    options:
      dependson:
        - ${aws_secretsmanager_secret_version.example}

With URL Exclusion and Inclusion Patterns

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

return await Deployment.RunAsync(() => 
{
    var example = new Aws.Kendra.DataSource("example", new()
    {
        IndexId = aws_kendra_index.Example.Id,
        Type = "WEBCRAWLER",
        RoleArn = aws_iam_role.Example.Arn,
        Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
        {
            WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
            {
                UrlExclusionPatterns = new[]
                {
                    "example",
                },
                UrlInclusionPatterns = new[]
                {
                    "hello",
                },
                Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
                {
                    SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
                    {
                        SeedUrls = new[]
                        {
                            "REPLACE_WITH_YOUR_URL",
                        },
                    },
                },
            },
        },
    });

});
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v5/go/aws/kendra"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := kendra.NewDataSource(ctx, "example", &kendra.DataSourceArgs{
			IndexId: pulumi.Any(aws_kendra_index.Example.Id),
			Type:    pulumi.String("WEBCRAWLER"),
			RoleArn: pulumi.Any(aws_iam_role.Example.Arn),
			Configuration: &kendra.DataSourceConfigurationArgs{
				WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
					UrlExclusionPatterns: pulumi.StringArray{
						pulumi.String("example"),
					},
					UrlInclusionPatterns: pulumi.StringArray{
						pulumi.String("hello"),
					},
					Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
						SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
							SeedUrls: pulumi.StringArray{
								pulumi.String("REPLACE_WITH_YOUR_URL"),
							},
						},
					},
				},
			},
		})
		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.kendra.DataSource;
import com.pulumi.aws.kendra.DataSourceArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs;
import com.pulumi.aws.kendra.inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs;
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 example = new DataSource("example", DataSourceArgs.builder()        
            .indexId(aws_kendra_index.example().id())
            .type("WEBCRAWLER")
            .roleArn(aws_iam_role.example().arn())
            .configuration(DataSourceConfigurationArgs.builder()
                .webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
                    .urlExclusionPatterns("example")
                    .urlInclusionPatterns("hello")
                    .urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
                        .seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
                            .seedUrls("REPLACE_WITH_YOUR_URL")
                            .build())
                        .build())
                    .build())
                .build())
            .build());

    }
}
import pulumi
import pulumi_aws as aws

example = aws.kendra.DataSource("example",
    index_id=aws_kendra_index["example"]["id"],
    type="WEBCRAWLER",
    role_arn=aws_iam_role["example"]["arn"],
    configuration=aws.kendra.DataSourceConfigurationArgs(
        web_crawler_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationArgs(
            url_exclusion_patterns=["example"],
            url_inclusion_patterns=["hello"],
            urls=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs(
                seed_url_configuration=aws.kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs(
                    seed_urls=["REPLACE_WITH_YOUR_URL"],
                ),
            ),
        ),
    ))
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const example = new aws.kendra.DataSource("example", {
    indexId: aws_kendra_index.example.id,
    type: "WEBCRAWLER",
    roleArn: aws_iam_role.example.arn,
    configuration: {
        webCrawlerConfiguration: {
            urlExclusionPatterns: ["example"],
            urlInclusionPatterns: ["hello"],
            urls: {
                seedUrlConfiguration: {
                    seedUrls: ["REPLACE_WITH_YOUR_URL"],
                },
            },
        },
    },
});
resources:
  example:
    type: aws:kendra:DataSource
    properties:
      indexId: ${aws_kendra_index.example.id}
      type: WEBCRAWLER
      roleArn: ${aws_iam_role.example.arn}
      configuration:
        webCrawlerConfiguration:
          urlExclusionPatterns:
            - example
          urlInclusionPatterns:
            - hello
          urls:
            seedUrlConfiguration:
              seedUrls:
                - REPLACE_WITH_YOUR_URL

Create a DataSource Resource

new DataSource(name: string, args: DataSourceArgs, opts?: CustomResourceOptions);
@overload
def DataSource(resource_name: str,
               opts: Optional[ResourceOptions] = None,
               configuration: Optional[DataSourceConfigurationArgs] = None,
               custom_document_enrichment_configuration: Optional[DataSourceCustomDocumentEnrichmentConfigurationArgs] = None,
               description: Optional[str] = None,
               index_id: Optional[str] = None,
               language_code: Optional[str] = None,
               name: Optional[str] = None,
               role_arn: Optional[str] = None,
               schedule: Optional[str] = None,
               tags: Optional[Mapping[str, str]] = None,
               type: Optional[str] = None)
@overload
def DataSource(resource_name: str,
               args: DataSourceArgs,
               opts: Optional[ResourceOptions] = None)
func NewDataSource(ctx *Context, name string, args DataSourceArgs, opts ...ResourceOption) (*DataSource, error)
public DataSource(string name, DataSourceArgs args, CustomResourceOptions? opts = null)
public DataSource(String name, DataSourceArgs args)
public DataSource(String name, DataSourceArgs args, CustomResourceOptions options)
type: aws:kendra:DataSource
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

name string
The unique name of the resource.
args DataSourceArgs
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 DataSourceArgs
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 DataSourceArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name string
The unique name of the resource.
args DataSourceArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name String
The unique name of the resource.
args DataSourceArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

DataSource 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 DataSource resource accepts the following input properties:

IndexId string

The identifier of the index for your Amazon Kendra data_source.

Type string

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

Configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

CustomDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

Description string

A description for the Data Source connector.

LanguageCode string

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

Name string

A name for your Data Source connector.

RoleArn string

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

Schedule string

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

Tags Dictionary<string, string>
IndexId string

The identifier of the index for your Amazon Kendra data_source.

Type string

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

Configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

CustomDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

Description string

A description for the Data Source connector.

LanguageCode string

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

Name string

A name for your Data Source connector.

RoleArn string

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

Schedule string

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

Tags map[string]string
indexId String

The identifier of the index for your Amazon Kendra data_source.

type String

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

customDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

description String

A description for the Data Source connector.

languageCode String

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name String

A name for your Data Source connector.

roleArn String

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule String

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

tags Map<String,String>
indexId string

The identifier of the index for your Amazon Kendra data_source.

type string

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

customDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

description string

A description for the Data Source connector.

languageCode string

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name string

A name for your Data Source connector.

roleArn string

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule string

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

tags {[key: string]: string}
index_id str

The identifier of the index for your Amazon Kendra data_source.

type str

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

custom_document_enrichment_configuration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

description str

A description for the Data Source connector.

language_code str

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name str

A name for your Data Source connector.

role_arn str

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule str

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

tags Mapping[str, str]
indexId String

The identifier of the index for your Amazon Kendra data_source.

type String

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

configuration Property Map

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

customDocumentEnrichmentConfiguration Property Map

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

description String

A description for the Data Source connector.

languageCode String

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name String

A name for your Data Source connector.

roleArn String

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule String

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

tags Map<String>

Outputs

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

Arn string

ARN of the Data Source.

CreatedAt string

The Unix timestamp of when the Data Source was created.

DataSourceId string

The unique identifiers of the Data Source.

ErrorMessage string

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

Id string

The provider-assigned unique ID for this managed resource.

Status string

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

TagsAll Dictionary<string, string>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

UpdatedAt string

The Unix timestamp of when the Data Source was last updated.

Arn string

ARN of the Data Source.

CreatedAt string

The Unix timestamp of when the Data Source was created.

DataSourceId string

The unique identifiers of the Data Source.

ErrorMessage string

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

Id string

The provider-assigned unique ID for this managed resource.

Status string

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

TagsAll map[string]string

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

UpdatedAt string

The Unix timestamp of when the Data Source was last updated.

arn String

ARN of the Data Source.

createdAt String

The Unix timestamp of when the Data Source was created.

dataSourceId String

The unique identifiers of the Data Source.

errorMessage String

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

id String

The provider-assigned unique ID for this managed resource.

status String

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tagsAll Map<String,String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

updatedAt String

The Unix timestamp of when the Data Source was last updated.

arn string

ARN of the Data Source.

createdAt string

The Unix timestamp of when the Data Source was created.

dataSourceId string

The unique identifiers of the Data Source.

errorMessage string

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

id string

The provider-assigned unique ID for this managed resource.

status string

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tagsAll {[key: string]: string}

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

updatedAt string

The Unix timestamp of when the Data Source was last updated.

arn str

ARN of the Data Source.

created_at str

The Unix timestamp of when the Data Source was created.

data_source_id str

The unique identifiers of the Data Source.

error_message str

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

id str

The provider-assigned unique ID for this managed resource.

status str

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tags_all Mapping[str, str]

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

updated_at str

The Unix timestamp of when the Data Source was last updated.

arn String

ARN of the Data Source.

createdAt String

The Unix timestamp of when the Data Source was created.

dataSourceId String

The unique identifiers of the Data Source.

errorMessage String

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

id String

The provider-assigned unique ID for this managed resource.

status String

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tagsAll Map<String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

updatedAt String

The Unix timestamp of when the Data Source was last updated.

Look up an Existing DataSource Resource

Get an existing DataSource 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?: DataSourceState, opts?: CustomResourceOptions): DataSource
@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        configuration: Optional[DataSourceConfigurationArgs] = None,
        created_at: Optional[str] = None,
        custom_document_enrichment_configuration: Optional[DataSourceCustomDocumentEnrichmentConfigurationArgs] = None,
        data_source_id: Optional[str] = None,
        description: Optional[str] = None,
        error_message: Optional[str] = None,
        index_id: Optional[str] = None,
        language_code: Optional[str] = None,
        name: Optional[str] = None,
        role_arn: Optional[str] = None,
        schedule: Optional[str] = None,
        status: Optional[str] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None,
        type: Optional[str] = None,
        updated_at: Optional[str] = None) -> DataSource
func GetDataSource(ctx *Context, name string, id IDInput, state *DataSourceState, opts ...ResourceOption) (*DataSource, error)
public static DataSource Get(string name, Input<string> id, DataSourceState? state, CustomResourceOptions? opts = null)
public static DataSource get(String name, Output<String> id, DataSourceState 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 Data Source.

Configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

CreatedAt string

The Unix timestamp of when the Data Source was created.

CustomDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

DataSourceId string

The unique identifiers of the Data Source.

Description string

A description for the Data Source connector.

ErrorMessage string

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

IndexId string

The identifier of the index for your Amazon Kendra data_source.

LanguageCode string

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

Name string

A name for your Data Source connector.

RoleArn string

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

Schedule string

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

Status string

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

Tags Dictionary<string, string>
TagsAll Dictionary<string, string>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Type string

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

UpdatedAt string

The Unix timestamp of when the Data Source was last updated.

Arn string

ARN of the Data Source.

Configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

CreatedAt string

The Unix timestamp of when the Data Source was created.

CustomDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

DataSourceId string

The unique identifiers of the Data Source.

Description string

A description for the Data Source connector.

ErrorMessage string

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

IndexId string

The identifier of the index for your Amazon Kendra data_source.

LanguageCode string

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

Name string

A name for your Data Source connector.

RoleArn string

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

Schedule string

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

Status string

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

Tags map[string]string
TagsAll map[string]string

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Type string

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

UpdatedAt string

The Unix timestamp of when the Data Source was last updated.

arn String

ARN of the Data Source.

configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

createdAt String

The Unix timestamp of when the Data Source was created.

customDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

dataSourceId String

The unique identifiers of the Data Source.

description String

A description for the Data Source connector.

errorMessage String

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

indexId String

The identifier of the index for your Amazon Kendra data_source.

languageCode String

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name String

A name for your Data Source connector.

roleArn String

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule String

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

status String

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tags Map<String,String>
tagsAll Map<String,String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

type String

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

updatedAt String

The Unix timestamp of when the Data Source was last updated.

arn string

ARN of the Data Source.

configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

createdAt string

The Unix timestamp of when the Data Source was created.

customDocumentEnrichmentConfiguration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

dataSourceId string

The unique identifiers of the Data Source.

description string

A description for the Data Source connector.

errorMessage string

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

indexId string

The identifier of the index for your Amazon Kendra data_source.

languageCode string

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name string

A name for your Data Source connector.

roleArn string

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule string

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

status string

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tags {[key: string]: string}
tagsAll {[key: string]: string}

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

type string

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

updatedAt string

The Unix timestamp of when the Data Source was last updated.

arn str

ARN of the Data Source.

configuration DataSourceConfigurationArgs

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

created_at str

The Unix timestamp of when the Data Source was created.

custom_document_enrichment_configuration DataSourceCustomDocumentEnrichmentConfigurationArgs

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

data_source_id str

The unique identifiers of the Data Source.

description str

A description for the Data Source connector.

error_message str

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

index_id str

The identifier of the index for your Amazon Kendra data_source.

language_code str

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name str

A name for your Data Source connector.

role_arn str

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule str

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

status str

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tags Mapping[str, str]
tags_all Mapping[str, str]

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

type str

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

updated_at str

The Unix timestamp of when the Data Source was last updated.

arn String

ARN of the Data Source.

configuration Property Map

A block with the configuration information to connect to your Data Source repository. You can't specify the configuration argument when the type parameter is set to CUSTOM. Detailed below.

createdAt String

The Unix timestamp of when the Data Source was created.

customDocumentEnrichmentConfiguration Property Map

A block with the configuration information for altering document metadata and content during the document ingestion process. For more information on how to create, modify and delete document metadata, or make other content alterations when you ingest documents into Amazon Kendra, see Customizing document metadata during the ingestion process. Detailed below.

dataSourceId String

The unique identifiers of the Data Source.

description String

A description for the Data Source connector.

errorMessage String

When the Status field value is FAILED, the ErrorMessage field contains a description of the error that caused the Data Source to fail.

indexId String

The identifier of the index for your Amazon Kendra data_source.

languageCode String

The code for a language. This allows you to support a language for all documents when creating the Data Source connector. English is supported by default. For more information on supported languages, including their codes, see Adding documents in languages other than English.

name String

A name for your Data Source connector.

roleArn String

The Amazon Resource Name (ARN) of a role with permission to access the data source connector. For more information, see IAM roles for Amazon Kendra. You can't specify the role_arn parameter when the type parameter is set to CUSTOM. The role_arn parameter is required for all other data sources.

schedule String

Sets the frequency for Amazon Kendra to check the documents in your Data Source repository and update the index. If you don't set a schedule Amazon Kendra will not periodically update the index. You can call the StartDataSourceSyncJob API to update the index.

status String

The current status of the Data Source. When the status is ACTIVE the Data Source is ready to use. When the status is FAILED, the error_message field contains the reason that the Data Source failed.

tags Map<String>
tagsAll Map<String>

A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

type String

The type of data source repository. For an updated list of values, refer to Valid Values for Type.

updatedAt String

The Unix timestamp of when the Data Source was last updated.

Supporting Types

DataSourceConfiguration

S3Configuration DataSourceConfigurationS3Configuration

A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.

WebCrawlerConfiguration DataSourceConfigurationWebCrawlerConfiguration

A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.

S3Configuration DataSourceConfigurationS3Configuration

A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.

WebCrawlerConfiguration DataSourceConfigurationWebCrawlerConfiguration

A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.

s3Configuration DataSourceConfigurationS3Configuration

A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.

webCrawlerConfiguration DataSourceConfigurationWebCrawlerConfiguration

A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.

s3Configuration DataSourceConfigurationS3Configuration

A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.

webCrawlerConfiguration DataSourceConfigurationWebCrawlerConfiguration

A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.

s3_configuration DataSourceConfigurationS3Configuration

A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.

web_crawler_configuration DataSourceConfigurationWebCrawlerConfiguration

A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.

s3Configuration Property Map

A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.

webCrawlerConfiguration Property Map

A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.

DataSourceConfigurationS3Configuration

BucketName string

The name of the bucket that contains the documents.

AccessControlListConfiguration DataSourceConfigurationS3ConfigurationAccessControlListConfiguration

A block that provides the path to the S3 bucket that contains the user context filtering files for the data source. For the format of the file, see Access control for S3 data sources. Detailed below.

DocumentsMetadataConfiguration DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration

A block that defines the Ddcument metadata files that contain information such as the document access control information, source URI, document author, and custom attributes. Each metadata file contains metadata about a single document. Detailed below.

ExclusionPatterns List<string>

A list of glob patterns for documents that should not be indexed. If a document that matches an inclusion prefix or inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Exclusion Patterns for more examples.

InclusionPatterns List<string>

A list of glob patterns for documents that should be indexed. If a document that matches an inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Inclusion Patterns for more examples.

InclusionPrefixes List<string>

A list of S3 prefixes for the documents that should be included in the index.

BucketName string

The name of the bucket that contains the documents.

AccessControlListConfiguration DataSourceConfigurationS3ConfigurationAccessControlListConfiguration

A block that provides the path to the S3 bucket that contains the user context filtering files for the data source. For the format of the file, see Access control for S3 data sources. Detailed below.

DocumentsMetadataConfiguration DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration

A block that defines the Ddcument metadata files that contain information such as the document access control information, source URI, document author, and custom attributes. Each metadata file contains metadata about a single document. Detailed below.

ExclusionPatterns []string

A list of glob patterns for documents that should not be indexed. If a document that matches an inclusion prefix or inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Exclusion Patterns for more examples.

InclusionPatterns []string

A list of glob patterns for documents that should be indexed. If a document that matches an inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Inclusion Patterns for more examples.

InclusionPrefixes []string

A list of S3 prefixes for the documents that should be included in the index.

bucketName String

The name of the bucket that contains the documents.

accessControlListConfiguration DataSourceConfigurationS3ConfigurationAccessControlListConfiguration

A block that provides the path to the S3 bucket that contains the user context filtering files for the data source. For the format of the file, see Access control for S3 data sources. Detailed below.

documentsMetadataConfiguration DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration

A block that defines the Ddcument metadata files that contain information such as the document access control information, source URI, document author, and custom attributes. Each metadata file contains metadata about a single document. Detailed below.

exclusionPatterns List<String>

A list of glob patterns for documents that should not be indexed. If a document that matches an inclusion prefix or inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Exclusion Patterns for more examples.

inclusionPatterns List<String>

A list of glob patterns for documents that should be indexed. If a document that matches an inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Inclusion Patterns for more examples.

inclusionPrefixes List<String>

A list of S3 prefixes for the documents that should be included in the index.

bucketName string

The name of the bucket that contains the documents.

accessControlListConfiguration DataSourceConfigurationS3ConfigurationAccessControlListConfiguration

A block that provides the path to the S3 bucket that contains the user context filtering files for the data source. For the format of the file, see Access control for S3 data sources. Detailed below.

documentsMetadataConfiguration DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration

A block that defines the Ddcument metadata files that contain information such as the document access control information, source URI, document author, and custom attributes. Each metadata file contains metadata about a single document. Detailed below.

exclusionPatterns string[]

A list of glob patterns for documents that should not be indexed. If a document that matches an inclusion prefix or inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Exclusion Patterns for more examples.

inclusionPatterns string[]

A list of glob patterns for documents that should be indexed. If a document that matches an inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Inclusion Patterns for more examples.

inclusionPrefixes string[]

A list of S3 prefixes for the documents that should be included in the index.

bucket_name str

The name of the bucket that contains the documents.

access_control_list_configuration DataSourceConfigurationS3ConfigurationAccessControlListConfiguration

A block that provides the path to the S3 bucket that contains the user context filtering files for the data source. For the format of the file, see Access control for S3 data sources. Detailed below.

documents_metadata_configuration DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration

A block that defines the Ddcument metadata files that contain information such as the document access control information, source URI, document author, and custom attributes. Each metadata file contains metadata about a single document. Detailed below.

exclusion_patterns Sequence[str]

A list of glob patterns for documents that should not be indexed. If a document that matches an inclusion prefix or inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Exclusion Patterns for more examples.

inclusion_patterns Sequence[str]

A list of glob patterns for documents that should be indexed. If a document that matches an inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Inclusion Patterns for more examples.

inclusion_prefixes Sequence[str]

A list of S3 prefixes for the documents that should be included in the index.

bucketName String

The name of the bucket that contains the documents.

accessControlListConfiguration Property Map

A block that provides the path to the S3 bucket that contains the user context filtering files for the data source. For the format of the file, see Access control for S3 data sources. Detailed below.

documentsMetadataConfiguration Property Map

A block that defines the Ddcument metadata files that contain information such as the document access control information, source URI, document author, and custom attributes. Each metadata file contains metadata about a single document. Detailed below.

exclusionPatterns List<String>

A list of glob patterns for documents that should not be indexed. If a document that matches an inclusion prefix or inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Exclusion Patterns for more examples.

inclusionPatterns List<String>

A list of glob patterns for documents that should be indexed. If a document that matches an inclusion pattern also matches an exclusion pattern, the document is not indexed. Refer to Inclusion Patterns for more examples.

inclusionPrefixes List<String>

A list of S3 prefixes for the documents that should be included in the index.

DataSourceConfigurationS3ConfigurationAccessControlListConfiguration

KeyPath string

Path to the AWS S3 bucket that contains the ACL files.

KeyPath string

Path to the AWS S3 bucket that contains the ACL files.

keyPath String

Path to the AWS S3 bucket that contains the ACL files.

keyPath string

Path to the AWS S3 bucket that contains the ACL files.

key_path str

Path to the AWS S3 bucket that contains the ACL files.

keyPath String

Path to the AWS S3 bucket that contains the ACL files.

DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration

S3Prefix string

A prefix used to filter metadata configuration files in the AWS S3 bucket. The S3 bucket might contain multiple metadata files. Use s3_prefix to include only the desired metadata files.

S3Prefix string

A prefix used to filter metadata configuration files in the AWS S3 bucket. The S3 bucket might contain multiple metadata files. Use s3_prefix to include only the desired metadata files.

s3Prefix String

A prefix used to filter metadata configuration files in the AWS S3 bucket. The S3 bucket might contain multiple metadata files. Use s3_prefix to include only the desired metadata files.

s3Prefix string

A prefix used to filter metadata configuration files in the AWS S3 bucket. The S3 bucket might contain multiple metadata files. Use s3_prefix to include only the desired metadata files.

s3_prefix str

A prefix used to filter metadata configuration files in the AWS S3 bucket. The S3 bucket might contain multiple metadata files. Use s3_prefix to include only the desired metadata files.

s3Prefix String

A prefix used to filter metadata configuration files in the AWS S3 bucket. The S3 bucket might contain multiple metadata files. Use s3_prefix to include only the desired metadata files.

DataSourceConfigurationWebCrawlerConfiguration

Urls DataSourceConfigurationWebCrawlerConfigurationUrls

A block that specifies the seed or starting point URLs of the websites or the sitemap URLs of the websites you want to crawl. You can include website subdomains. You can list up to 100 seed URLs and up to 3 sitemap URLs. You can only crawl websites that use the secure communication protocol, Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from crawling. When selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to index your own webpages, or webpages that you have authorization to index. Detailed below.

AuthenticationConfiguration DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration

A block with the configuration information required to connect to websites using authentication. You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Detailed below.

CrawlDepth int

Specifies the number of levels in a website that you want to crawl. The first level begins from the website seed or starting point URL. For example, if a website has 3 levels – index level (i.e. seed in this example), sections level, and subsections level – and you are only interested in crawling information up to the sections level (i.e. levels 0-1), you can set your depth to 1. The default crawl depth is set to 2. Minimum value of 0. Maximum value of 10.

MaxContentSizePerPageInMegaBytes double

The maximum size (in MB) of a webpage or attachment to crawl. Files larger than this size (in MB) are skipped/not crawled. The default maximum size of a webpage or attachment is set to 50 MB. Minimum value of 1.0e-06. Maximum value of 50.

MaxLinksPerPage int

The maximum number of URLs on a webpage to include when crawling a website. This number is per webpage. As a website’s webpages are crawled, any URLs the webpages link to are also crawled. URLs on a webpage are crawled in order of appearance. The default maximum links per page is 100. Minimum value of 1. Maximum value of 1000.

MaxUrlsPerMinuteCrawlRate int

The maximum number of URLs crawled per website host per minute. The default maximum number of URLs crawled per website host per minute is 300. Minimum value of 1. Maximum value of 300.

ProxyConfiguration DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration

Configuration information required to connect to your internal websites via a web proxy. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager. Detailed below.

UrlExclusionPatterns List<string>

A list of regular expression patterns to exclude certain URLs to crawl. URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

UrlInclusionPatterns List<string>

A list of regular expression patterns to include certain URLs to crawl. URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

Urls DataSourceConfigurationWebCrawlerConfigurationUrls

A block that specifies the seed or starting point URLs of the websites or the sitemap URLs of the websites you want to crawl. You can include website subdomains. You can list up to 100 seed URLs and up to 3 sitemap URLs. You can only crawl websites that use the secure communication protocol, Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from crawling. When selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to index your own webpages, or webpages that you have authorization to index. Detailed below.

AuthenticationConfiguration DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration

A block with the configuration information required to connect to websites using authentication. You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Detailed below.

CrawlDepth int

Specifies the number of levels in a website that you want to crawl. The first level begins from the website seed or starting point URL. For example, if a website has 3 levels – index level (i.e. seed in this example), sections level, and subsections level – and you are only interested in crawling information up to the sections level (i.e. levels 0-1), you can set your depth to 1. The default crawl depth is set to 2. Minimum value of 0. Maximum value of 10.

MaxContentSizePerPageInMegaBytes float64

The maximum size (in MB) of a webpage or attachment to crawl. Files larger than this size (in MB) are skipped/not crawled. The default maximum size of a webpage or attachment is set to 50 MB. Minimum value of 1.0e-06. Maximum value of 50.

MaxLinksPerPage int

The maximum number of URLs on a webpage to include when crawling a website. This number is per webpage. As a website’s webpages are crawled, any URLs the webpages link to are also crawled. URLs on a webpage are crawled in order of appearance. The default maximum links per page is 100. Minimum value of 1. Maximum value of 1000.

MaxUrlsPerMinuteCrawlRate int

The maximum number of URLs crawled per website host per minute. The default maximum number of URLs crawled per website host per minute is 300. Minimum value of 1. Maximum value of 300.

ProxyConfiguration DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration

Configuration information required to connect to your internal websites via a web proxy. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager. Detailed below.

UrlExclusionPatterns []string

A list of regular expression patterns to exclude certain URLs to crawl. URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

UrlInclusionPatterns []string

A list of regular expression patterns to include certain URLs to crawl. URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urls DataSourceConfigurationWebCrawlerConfigurationUrls

A block that specifies the seed or starting point URLs of the websites or the sitemap URLs of the websites you want to crawl. You can include website subdomains. You can list up to 100 seed URLs and up to 3 sitemap URLs. You can only crawl websites that use the secure communication protocol, Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from crawling. When selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to index your own webpages, or webpages that you have authorization to index. Detailed below.

authenticationConfiguration DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration

A block with the configuration information required to connect to websites using authentication. You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Detailed below.

crawlDepth Integer

Specifies the number of levels in a website that you want to crawl. The first level begins from the website seed or starting point URL. For example, if a website has 3 levels – index level (i.e. seed in this example), sections level, and subsections level – and you are only interested in crawling information up to the sections level (i.e. levels 0-1), you can set your depth to 1. The default crawl depth is set to 2. Minimum value of 0. Maximum value of 10.

maxContentSizePerPageInMegaBytes Double

The maximum size (in MB) of a webpage or attachment to crawl. Files larger than this size (in MB) are skipped/not crawled. The default maximum size of a webpage or attachment is set to 50 MB. Minimum value of 1.0e-06. Maximum value of 50.

maxLinksPerPage Integer

The maximum number of URLs on a webpage to include when crawling a website. This number is per webpage. As a website’s webpages are crawled, any URLs the webpages link to are also crawled. URLs on a webpage are crawled in order of appearance. The default maximum links per page is 100. Minimum value of 1. Maximum value of 1000.

maxUrlsPerMinuteCrawlRate Integer

The maximum number of URLs crawled per website host per minute. The default maximum number of URLs crawled per website host per minute is 300. Minimum value of 1. Maximum value of 300.

proxyConfiguration DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration

Configuration information required to connect to your internal websites via a web proxy. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager. Detailed below.

urlExclusionPatterns List<String>

A list of regular expression patterns to exclude certain URLs to crawl. URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urlInclusionPatterns List<String>

A list of regular expression patterns to include certain URLs to crawl. URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urls DataSourceConfigurationWebCrawlerConfigurationUrls

A block that specifies the seed or starting point URLs of the websites or the sitemap URLs of the websites you want to crawl. You can include website subdomains. You can list up to 100 seed URLs and up to 3 sitemap URLs. You can only crawl websites that use the secure communication protocol, Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from crawling. When selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to index your own webpages, or webpages that you have authorization to index. Detailed below.

authenticationConfiguration DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration

A block with the configuration information required to connect to websites using authentication. You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Detailed below.

crawlDepth number

Specifies the number of levels in a website that you want to crawl. The first level begins from the website seed or starting point URL. For example, if a website has 3 levels – index level (i.e. seed in this example), sections level, and subsections level – and you are only interested in crawling information up to the sections level (i.e. levels 0-1), you can set your depth to 1. The default crawl depth is set to 2. Minimum value of 0. Maximum value of 10.

maxContentSizePerPageInMegaBytes number

The maximum size (in MB) of a webpage or attachment to crawl. Files larger than this size (in MB) are skipped/not crawled. The default maximum size of a webpage or attachment is set to 50 MB. Minimum value of 1.0e-06. Maximum value of 50.

maxLinksPerPage number

The maximum number of URLs on a webpage to include when crawling a website. This number is per webpage. As a website’s webpages are crawled, any URLs the webpages link to are also crawled. URLs on a webpage are crawled in order of appearance. The default maximum links per page is 100. Minimum value of 1. Maximum value of 1000.

maxUrlsPerMinuteCrawlRate number

The maximum number of URLs crawled per website host per minute. The default maximum number of URLs crawled per website host per minute is 300. Minimum value of 1. Maximum value of 300.

proxyConfiguration DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration

Configuration information required to connect to your internal websites via a web proxy. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager. Detailed below.

urlExclusionPatterns string[]

A list of regular expression patterns to exclude certain URLs to crawl. URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urlInclusionPatterns string[]

A list of regular expression patterns to include certain URLs to crawl. URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urls DataSourceConfigurationWebCrawlerConfigurationUrls

A block that specifies the seed or starting point URLs of the websites or the sitemap URLs of the websites you want to crawl. You can include website subdomains. You can list up to 100 seed URLs and up to 3 sitemap URLs. You can only crawl websites that use the secure communication protocol, Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from crawling. When selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to index your own webpages, or webpages that you have authorization to index. Detailed below.

authentication_configuration DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration

A block with the configuration information required to connect to websites using authentication. You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Detailed below.

crawl_depth int

Specifies the number of levels in a website that you want to crawl. The first level begins from the website seed or starting point URL. For example, if a website has 3 levels – index level (i.e. seed in this example), sections level, and subsections level – and you are only interested in crawling information up to the sections level (i.e. levels 0-1), you can set your depth to 1. The default crawl depth is set to 2. Minimum value of 0. Maximum value of 10.

max_content_size_per_page_in_mega_bytes float

The maximum size (in MB) of a webpage or attachment to crawl. Files larger than this size (in MB) are skipped/not crawled. The default maximum size of a webpage or attachment is set to 50 MB. Minimum value of 1.0e-06. Maximum value of 50.

max_links_per_page int

The maximum number of URLs on a webpage to include when crawling a website. This number is per webpage. As a website’s webpages are crawled, any URLs the webpages link to are also crawled. URLs on a webpage are crawled in order of appearance. The default maximum links per page is 100. Minimum value of 1. Maximum value of 1000.

max_urls_per_minute_crawl_rate int

The maximum number of URLs crawled per website host per minute. The default maximum number of URLs crawled per website host per minute is 300. Minimum value of 1. Maximum value of 300.

proxy_configuration DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration

Configuration information required to connect to your internal websites via a web proxy. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager. Detailed below.

url_exclusion_patterns Sequence[str]

A list of regular expression patterns to exclude certain URLs to crawl. URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

url_inclusion_patterns Sequence[str]

A list of regular expression patterns to include certain URLs to crawl. URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urls Property Map

A block that specifies the seed or starting point URLs of the websites or the sitemap URLs of the websites you want to crawl. You can include website subdomains. You can list up to 100 seed URLs and up to 3 sitemap URLs. You can only crawl websites that use the secure communication protocol, Hypertext Transfer Protocol Secure (HTTPS). If you receive an error when crawling a website, it could be that the website is blocked from crawling. When selecting websites to index, you must adhere to the Amazon Acceptable Use Policy and all other Amazon terms. Remember that you must only use Amazon Kendra Web Crawler to index your own webpages, or webpages that you have authorization to index. Detailed below.

authenticationConfiguration Property Map

A block with the configuration information required to connect to websites using authentication. You can connect to websites using basic authentication of user name and password. You use a secret in AWS Secrets Manager to store your authentication credentials. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Detailed below.

crawlDepth Number

Specifies the number of levels in a website that you want to crawl. The first level begins from the website seed or starting point URL. For example, if a website has 3 levels – index level (i.e. seed in this example), sections level, and subsections level – and you are only interested in crawling information up to the sections level (i.e. levels 0-1), you can set your depth to 1. The default crawl depth is set to 2. Minimum value of 0. Maximum value of 10.

maxContentSizePerPageInMegaBytes Number

The maximum size (in MB) of a webpage or attachment to crawl. Files larger than this size (in MB) are skipped/not crawled. The default maximum size of a webpage or attachment is set to 50 MB. Minimum value of 1.0e-06. Maximum value of 50.

maxLinksPerPage Number

The maximum number of URLs on a webpage to include when crawling a website. This number is per webpage. As a website’s webpages are crawled, any URLs the webpages link to are also crawled. URLs on a webpage are crawled in order of appearance. The default maximum links per page is 100. Minimum value of 1. Maximum value of 1000.

maxUrlsPerMinuteCrawlRate Number

The maximum number of URLs crawled per website host per minute. The default maximum number of URLs crawled per website host per minute is 300. Minimum value of 1. Maximum value of 300.

proxyConfiguration Property Map

Configuration information required to connect to your internal websites via a web proxy. You must provide the website host name and port number. For example, the host name of https://a.example.com/page1.html is "a.example.com" and the port is 443, the standard port for HTTPS. Web proxy credentials are optional and you can use them to connect to a web proxy server that requires basic authentication. To store web proxy credentials, you use a secret in AWS Secrets Manager. Detailed below.

urlExclusionPatterns List<String>

A list of regular expression patterns to exclude certain URLs to crawl. URLs that match the patterns are excluded from the index. URLs that don't match the patterns are included in the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

urlInclusionPatterns List<String>

A list of regular expression patterns to include certain URLs to crawl. URLs that match the patterns are included in the index. URLs that don't match the patterns are excluded from the index. If a URL matches both an inclusion and exclusion pattern, the exclusion pattern takes precedence and the URL file isn't included in the index. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 150.

DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration

BasicAuthentications List<DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthentication>

The list of configuration information that's required to connect to and crawl a website host using basic authentication credentials. The list includes the name and port number of the website host. Detailed below.

BasicAuthentications []DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthentication

The list of configuration information that's required to connect to and crawl a website host using basic authentication credentials. The list includes the name and port number of the website host. Detailed below.

basicAuthentications List<DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthentication>

The list of configuration information that's required to connect to and crawl a website host using basic authentication credentials. The list includes the name and port number of the website host. Detailed below.

basicAuthentications DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthentication[]

The list of configuration information that's required to connect to and crawl a website host using basic authentication credentials. The list includes the name and port number of the website host. Detailed below.

basic_authentications Sequence[DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthentication]

The list of configuration information that's required to connect to and crawl a website host using basic authentication credentials. The list includes the name and port number of the website host. Detailed below.

basicAuthentications List<Property Map>

The list of configuration information that's required to connect to and crawl a website host using basic authentication credentials. The list includes the name and port number of the website host. Detailed below.

DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthentication

Credentials string

Your secret ARN, which you can create in AWS Secrets Manager. You use a secret if basic authentication credentials are required to connect to a website. The secret stores your credentials of user name and password.

Host string

The name of the website host you want to connect to using authentication credentials. For example, the host name of https://a.example.com/page1.html is "a.example.com".

Port int

The port number of the website host you want to connect to using authentication credentials. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

Credentials string

Your secret ARN, which you can create in AWS Secrets Manager. You use a secret if basic authentication credentials are required to connect to a website. The secret stores your credentials of user name and password.

Host string

The name of the website host you want to connect to using authentication credentials. For example, the host name of https://a.example.com/page1.html is "a.example.com".

Port int

The port number of the website host you want to connect to using authentication credentials. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials String

Your secret ARN, which you can create in AWS Secrets Manager. You use a secret if basic authentication credentials are required to connect to a website. The secret stores your credentials of user name and password.

host String

The name of the website host you want to connect to using authentication credentials. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port Integer

The port number of the website host you want to connect to using authentication credentials. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials string

Your secret ARN, which you can create in AWS Secrets Manager. You use a secret if basic authentication credentials are required to connect to a website. The secret stores your credentials of user name and password.

host string

The name of the website host you want to connect to using authentication credentials. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port number

The port number of the website host you want to connect to using authentication credentials. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials str

Your secret ARN, which you can create in AWS Secrets Manager. You use a secret if basic authentication credentials are required to connect to a website. The secret stores your credentials of user name and password.

host str

The name of the website host you want to connect to using authentication credentials. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port int

The port number of the website host you want to connect to using authentication credentials. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials String

Your secret ARN, which you can create in AWS Secrets Manager. You use a secret if basic authentication credentials are required to connect to a website. The secret stores your credentials of user name and password.

host String

The name of the website host you want to connect to using authentication credentials. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port Number

The port number of the website host you want to connect to using authentication credentials. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration

Host string

The name of the website host you want to connect to via a web proxy server. For example, the host name of https://a.example.com/page1.html is "a.example.com".

Port int

The port number of the website host you want to connect to via a web proxy server. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

Credentials string

Your secret ARN, which you can create in AWS Secrets Manager. The credentials are optional. You use a secret if web proxy credentials are required to connect to a website host. Amazon Kendra currently support basic authentication to connect to a web proxy server. The secret stores your credentials.

Host string

The name of the website host you want to connect to via a web proxy server. For example, the host name of https://a.example.com/page1.html is "a.example.com".

Port int

The port number of the website host you want to connect to via a web proxy server. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

Credentials string

Your secret ARN, which you can create in AWS Secrets Manager. The credentials are optional. You use a secret if web proxy credentials are required to connect to a website host. Amazon Kendra currently support basic authentication to connect to a web proxy server. The secret stores your credentials.

host String

The name of the website host you want to connect to via a web proxy server. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port Integer

The port number of the website host you want to connect to via a web proxy server. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials String

Your secret ARN, which you can create in AWS Secrets Manager. The credentials are optional. You use a secret if web proxy credentials are required to connect to a website host. Amazon Kendra currently support basic authentication to connect to a web proxy server. The secret stores your credentials.

host string

The name of the website host you want to connect to via a web proxy server. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port number

The port number of the website host you want to connect to via a web proxy server. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials string

Your secret ARN, which you can create in AWS Secrets Manager. The credentials are optional. You use a secret if web proxy credentials are required to connect to a website host. Amazon Kendra currently support basic authentication to connect to a web proxy server. The secret stores your credentials.

host str

The name of the website host you want to connect to via a web proxy server. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port int

The port number of the website host you want to connect to via a web proxy server. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials str

Your secret ARN, which you can create in AWS Secrets Manager. The credentials are optional. You use a secret if web proxy credentials are required to connect to a website host. Amazon Kendra currently support basic authentication to connect to a web proxy server. The secret stores your credentials.

host String

The name of the website host you want to connect to via a web proxy server. For example, the host name of https://a.example.com/page1.html is "a.example.com".

port Number

The port number of the website host you want to connect to via a web proxy server. For example, the port for https://a.example.com/page1.html is 443, the standard port for HTTPS.

credentials String

Your secret ARN, which you can create in AWS Secrets Manager. The credentials are optional. You use a secret if web proxy credentials are required to connect to a website host. Amazon Kendra currently support basic authentication to connect to a web proxy server. The secret stores your credentials.

DataSourceConfigurationWebCrawlerConfigurationUrls

SeedUrlConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration

A block that specifies the configuration of the seed or starting point URLs of the websites you want to crawl. You can choose to crawl only the website host names, or the website host names with subdomains, or the website host names with subdomains and other domains that the webpages link to. You can list up to 100 seed URLs. Detailed below.

SiteMapsConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration

A block that specifies the configuration of the sitemap URLs of the websites you want to crawl. Only URLs belonging to the same website host names are crawled. You can list up to 3 sitemap URLs. Detailed below.

SeedUrlConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration

A block that specifies the configuration of the seed or starting point URLs of the websites you want to crawl. You can choose to crawl only the website host names, or the website host names with subdomains, or the website host names with subdomains and other domains that the webpages link to. You can list up to 100 seed URLs. Detailed below.

SiteMapsConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration

A block that specifies the configuration of the sitemap URLs of the websites you want to crawl. Only URLs belonging to the same website host names are crawled. You can list up to 3 sitemap URLs. Detailed below.

seedUrlConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration

A block that specifies the configuration of the seed or starting point URLs of the websites you want to crawl. You can choose to crawl only the website host names, or the website host names with subdomains, or the website host names with subdomains and other domains that the webpages link to. You can list up to 100 seed URLs. Detailed below.

siteMapsConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration

A block that specifies the configuration of the sitemap URLs of the websites you want to crawl. Only URLs belonging to the same website host names are crawled. You can list up to 3 sitemap URLs. Detailed below.

seedUrlConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration

A block that specifies the configuration of the seed or starting point URLs of the websites you want to crawl. You can choose to crawl only the website host names, or the website host names with subdomains, or the website host names with subdomains and other domains that the webpages link to. You can list up to 100 seed URLs. Detailed below.

siteMapsConfiguration DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration

A block that specifies the configuration of the sitemap URLs of the websites you want to crawl. Only URLs belonging to the same website host names are crawled. You can list up to 3 sitemap URLs. Detailed below.

seed_url_configuration DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration

A block that specifies the configuration of the seed or starting point URLs of the websites you want to crawl. You can choose to crawl only the website host names, or the website host names with subdomains, or the website host names with subdomains and other domains that the webpages link to. You can list up to 100 seed URLs. Detailed below.

site_maps_configuration DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration

A block that specifies the configuration of the sitemap URLs of the websites you want to crawl. Only URLs belonging to the same website host names are crawled. You can list up to 3 sitemap URLs. Detailed below.

seedUrlConfiguration Property Map

A block that specifies the configuration of the seed or starting point URLs of the websites you want to crawl. You can choose to crawl only the website host names, or the website host names with subdomains, or the website host names with subdomains and other domains that the webpages link to. You can list up to 100 seed URLs. Detailed below.

siteMapsConfiguration Property Map

A block that specifies the configuration of the sitemap URLs of the websites you want to crawl. Only URLs belonging to the same website host names are crawled. You can list up to 3 sitemap URLs. Detailed below.

DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration

SeedUrls List<string>

The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of 100 seed URLs. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 2048.

WebCrawlerMode string

The default mode is set to HOST_ONLY. You can choose one of the following modes:

SeedUrls []string

The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of 100 seed URLs. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 2048.

WebCrawlerMode string

The default mode is set to HOST_ONLY. You can choose one of the following modes:

seedUrls List<String>

The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of 100 seed URLs. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 2048.

webCrawlerMode String

The default mode is set to HOST_ONLY. You can choose one of the following modes:

seedUrls string[]

The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of 100 seed URLs. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 2048.

webCrawlerMode string

The default mode is set to HOST_ONLY. You can choose one of the following modes:

seed_urls Sequence[str]

The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of 100 seed URLs. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 2048.

web_crawler_mode str

The default mode is set to HOST_ONLY. You can choose one of the following modes:

seedUrls List<String>

The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of 100 seed URLs. Array Members: Minimum number of 0 items. Maximum number of 100 items. Length Constraints: Minimum length of 1. Maximum length of 2048.

webCrawlerMode String

The default mode is set to HOST_ONLY. You can choose one of the following modes:

DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration

SiteMaps List<string>

The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of 3 sitemap URLs.

SiteMaps []string

The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of 3 sitemap URLs.

siteMaps List<String>

The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of 3 sitemap URLs.

siteMaps string[]

The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of 3 sitemap URLs.

site_maps Sequence[str]

The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of 3 sitemap URLs.

siteMaps List<String>

The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of 3 sitemap URLs.

DataSourceCustomDocumentEnrichmentConfiguration

InlineConfigurations List<DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration>

Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of 0 items. Maximum number of 100 items. Detailed below.

PostExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration

A block that specifies the configuration information for invoking a Lambda function in AWS Lambda on the structured documents with their metadata and text extracted. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

PreExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration

Configuration information for invoking a Lambda function in AWS Lambda on the original or raw documents before extracting their metadata and text. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

RoleArn string

The Amazon Resource Name (ARN) of a role with permission to run pre_extraction_hook_configuration and post_extraction_hook_configuration for altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.

InlineConfigurations []DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration

Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of 0 items. Maximum number of 100 items. Detailed below.

PostExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration

A block that specifies the configuration information for invoking a Lambda function in AWS Lambda on the structured documents with their metadata and text extracted. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

PreExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration

Configuration information for invoking a Lambda function in AWS Lambda on the original or raw documents before extracting their metadata and text. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

RoleArn string

The Amazon Resource Name (ARN) of a role with permission to run pre_extraction_hook_configuration and post_extraction_hook_configuration for altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.

inlineConfigurations List<DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration>

Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of 0 items. Maximum number of 100 items. Detailed below.

postExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration

A block that specifies the configuration information for invoking a Lambda function in AWS Lambda on the structured documents with their metadata and text extracted. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

preExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration

Configuration information for invoking a Lambda function in AWS Lambda on the original or raw documents before extracting their metadata and text. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

roleArn String

The Amazon Resource Name (ARN) of a role with permission to run pre_extraction_hook_configuration and post_extraction_hook_configuration for altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.

inlineConfigurations DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration[]

Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of 0 items. Maximum number of 100 items. Detailed below.

postExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration

A block that specifies the configuration information for invoking a Lambda function in AWS Lambda on the structured documents with their metadata and text extracted. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

preExtractionHookConfiguration DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration

Configuration information for invoking a Lambda function in AWS Lambda on the original or raw documents before extracting their metadata and text. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

roleArn string

The Amazon Resource Name (ARN) of a role with permission to run pre_extraction_hook_configuration and post_extraction_hook_configuration for altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.

inline_configurations Sequence[DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration]

Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of 0 items. Maximum number of 100 items. Detailed below.

post_extraction_hook_configuration DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration

A block that specifies the configuration information for invoking a Lambda function in AWS Lambda on the structured documents with their metadata and text extracted. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

pre_extraction_hook_configuration DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration

Configuration information for invoking a Lambda function in AWS Lambda on the original or raw documents before extracting their metadata and text. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

role_arn str

The Amazon Resource Name (ARN) of a role with permission to run pre_extraction_hook_configuration and post_extraction_hook_configuration for altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.

inlineConfigurations List<Property Map>

Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of 0 items. Maximum number of 100 items. Detailed below.

postExtractionHookConfiguration Property Map

A block that specifies the configuration information for invoking a Lambda function in AWS Lambda on the structured documents with their metadata and text extracted. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

preExtractionHookConfiguration Property Map

Configuration information for invoking a Lambda function in AWS Lambda on the original or raw documents before extracting their metadata and text. You can use a Lambda function to apply advanced logic for creating, modifying, or deleting document metadata and content. For more information, see Advanced data manipulation. Detailed below.

roleArn String

The Amazon Resource Name (ARN) of a role with permission to run pre_extraction_hook_configuration and post_extraction_hook_configuration for altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.

DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration

Condition DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationCondition

Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See Document Attribute Condition.

DocumentContentDeletion bool

TRUE to delete content if the condition used for the target attribute is met.

Target DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget

Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.

Condition DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationCondition

Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See Document Attribute Condition.

DocumentContentDeletion bool

TRUE to delete content if the condition used for the target attribute is met.

Target DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget

Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.

condition DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationCondition

Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See Document Attribute Condition.

documentContentDeletion Boolean

TRUE to delete content if the condition used for the target attribute is met.

target DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget

Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.

condition DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationCondition

Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See Document Attribute Condition.

documentContentDeletion boolean

TRUE to delete content if the condition used for the target attribute is met.

target DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget

Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.

condition DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationCondition

Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See Document Attribute Condition.

document_content_deletion bool

TRUE to delete content if the condition used for the target attribute is met.

target DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget

Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.

condition Property Map

Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See Document Attribute Condition.

documentContentDeletion Boolean

TRUE to delete content if the condition used for the target attribute is met.

target Property Map

Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.

DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationCondition

ConditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

Operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

ConditionOnValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

ConditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

Operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

ConditionOnValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey String

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator String

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

condition_document_attribute_key str

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator str

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

condition_on_value DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey String

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator String

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue Property Map

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue

DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues List<string>

A list of strings.

StringValue string
DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues []string

A list of strings.

StringValue string
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Integer

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String
dateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue number

A long integer value.

stringListValues string[]

A list of strings.

stringValue string
date_value str

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

long_value int

A long integer value.

string_list_values Sequence[str]

A list of strings.

string_value str
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Number

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String

DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget

TargetDocumentAttributeKey string

The identifier of the target document attribute or metadata field. For example, 'Department' could be an identifier for the target attribute or metadata field that includes the department names associated with the documents.

TargetDocumentAttributeValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue

The target value you want to create for the target attribute. For example, 'Finance' could be the target value for the target attribute key 'Department'. See Document Attribute Value.

TargetDocumentAttributeValueDeletion bool

TRUE to delete the existing target value for your specified target attribute key. You cannot create a target value and set this to TRUE. To create a target value (TargetDocumentAttributeValue), set this to FALSE.

TargetDocumentAttributeKey string

The identifier of the target document attribute or metadata field. For example, 'Department' could be an identifier for the target attribute or metadata field that includes the department names associated with the documents.

TargetDocumentAttributeValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue

The target value you want to create for the target attribute. For example, 'Finance' could be the target value for the target attribute key 'Department'. See Document Attribute Value.

TargetDocumentAttributeValueDeletion bool

TRUE to delete the existing target value for your specified target attribute key. You cannot create a target value and set this to TRUE. To create a target value (TargetDocumentAttributeValue), set this to FALSE.

targetDocumentAttributeKey String

The identifier of the target document attribute or metadata field. For example, 'Department' could be an identifier for the target attribute or metadata field that includes the department names associated with the documents.

targetDocumentAttributeValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue

The target value you want to create for the target attribute. For example, 'Finance' could be the target value for the target attribute key 'Department'. See Document Attribute Value.

targetDocumentAttributeValueDeletion Boolean

TRUE to delete the existing target value for your specified target attribute key. You cannot create a target value and set this to TRUE. To create a target value (TargetDocumentAttributeValue), set this to FALSE.

targetDocumentAttributeKey string

The identifier of the target document attribute or metadata field. For example, 'Department' could be an identifier for the target attribute or metadata field that includes the department names associated with the documents.

targetDocumentAttributeValue DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue

The target value you want to create for the target attribute. For example, 'Finance' could be the target value for the target attribute key 'Department'. See Document Attribute Value.

targetDocumentAttributeValueDeletion boolean

TRUE to delete the existing target value for your specified target attribute key. You cannot create a target value and set this to TRUE. To create a target value (TargetDocumentAttributeValue), set this to FALSE.

target_document_attribute_key str

The identifier of the target document attribute or metadata field. For example, 'Department' could be an identifier for the target attribute or metadata field that includes the department names associated with the documents.

target_document_attribute_value DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue

The target value you want to create for the target attribute. For example, 'Finance' could be the target value for the target attribute key 'Department'. See Document Attribute Value.

target_document_attribute_value_deletion bool

TRUE to delete the existing target value for your specified target attribute key. You cannot create a target value and set this to TRUE. To create a target value (TargetDocumentAttributeValue), set this to FALSE.

targetDocumentAttributeKey String

The identifier of the target document attribute or metadata field. For example, 'Department' could be an identifier for the target attribute or metadata field that includes the department names associated with the documents.

targetDocumentAttributeValue Property Map

The target value you want to create for the target attribute. For example, 'Finance' could be the target value for the target attribute key 'Department'. See Document Attribute Value.

targetDocumentAttributeValueDeletion Boolean

TRUE to delete the existing target value for your specified target attribute key. You cannot create a target value and set this to TRUE. To create a target value (TargetDocumentAttributeValue), set this to FALSE.

DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue

DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues List<string>

A list of strings.

StringValue string
DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues []string

A list of strings.

StringValue string
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Integer

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String
dateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue number

A long integer value.

stringListValues string[]

A list of strings.

stringValue string
date_value str

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

long_value int

A long integer value.

string_list_values Sequence[str]

A list of strings.

string_value str
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Number

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String

DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration

LambdaArn string

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

S3Bucket string

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

InvocationCondition DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

LambdaArn string

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

S3Bucket string

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

InvocationCondition DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambdaArn String

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3Bucket String

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocationCondition DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambdaArn string

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3Bucket string

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocationCondition DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambda_arn str

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3_bucket str

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocation_condition DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambdaArn String

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3Bucket String

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocationCondition Property Map

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition

ConditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

Operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

ConditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

ConditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

Operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

ConditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey String

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator String

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

condition_document_attribute_key str

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator str

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

condition_on_value DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey String

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator String

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue Property Map

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue

DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues List<string>

A list of strings.

StringValue string
DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues []string

A list of strings.

StringValue string
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Integer

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String
dateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue number

A long integer value.

stringListValues string[]

A list of strings.

stringValue string
date_value str

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

long_value int

A long integer value.

string_list_values Sequence[str]

A list of strings.

string_value str
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Number

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String

DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration

LambdaArn string

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

S3Bucket string

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

InvocationCondition DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

LambdaArn string

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

S3Bucket string

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

InvocationCondition DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambdaArn String

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3Bucket String

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocationCondition DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambdaArn string

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3Bucket string

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocationCondition DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambda_arn str

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3_bucket str

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocation_condition DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

lambdaArn String

The Amazon Resource Name (ARN) of a Lambda Function that can manipulate your document metadata fields or attributes and content.

s3Bucket String

Stores the original, raw documents or the structured, parsed documents before and after altering them. For more information, see Data contracts for Lambda functions.

invocationCondition Property Map

A block that specifies the condition used for when a Lambda function should be invoked. For example, you can specify a condition that if there are empty date-time values, then Amazon Kendra should invoke a function that inserts the current date-time. See Document Attribute Condition.

DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition

ConditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

Operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

ConditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

ConditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

Operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

ConditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey String

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator String

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey string

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator string

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

condition_document_attribute_key str

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator str

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

condition_on_value DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

conditionDocumentAttributeKey String

The identifier of the document attribute used for the condition. For example, _source_uri could be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support _document_body as an attribute key used for the condition.

operator String

The condition operator. For example, you can use Contains to partially match a string. Valid Values: GreaterThan | GreaterThanOrEquals | LessThan | LessThanOrEquals | Equals | NotEquals | Contains | NotContains | Exists | NotExists | BeginsWith.

conditionOnValue Property Map

The value used by the operator. For example, you can specify the value 'financial' for strings in the _source_uri field that partially match or contain this value. See Document Attribute Value.

DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue

DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues List<string>

A list of strings.

StringValue string
DateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

LongValue int

A long integer value.

StringListValues []string

A list of strings.

StringValue string
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Integer

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String
dateValue string

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue number

A long integer value.

stringListValues string[]

A list of strings.

stringValue string
date_value str

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

long_value int

A long integer value.

string_list_values Sequence[str]

A list of strings.

string_value str
dateValue String

A date expressed as an ISO 8601 string. It is important for the time zone to be included in the ISO 8601 date-time format. As of this writing only UTC is supported. For example, 2012-03-25T12:30:10+00:00.

longValue Number

A long integer value.

stringListValues List<String>

A list of strings.

stringValue String

Package Details

Repository
https://github.com/pulumi/pulumi-aws
License
Apache-2.0
Notes

This Pulumi package is based on the aws Terraform Provider.