Docs Home
AWS v6.60.0 published on Tuesday, Nov 19, 2024 by Pulumi
aws.kendra.DataSource
Explore with Pulumi AI
Resource for managing an AWS Kendra Data Source.
Example Usage
Basic Usage
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
description: "example",
languageCode: "en",
type: "CUSTOM",
tags: {
hello: "world",
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
description="example",
language_code="en",
type="CUSTOM",
tags={
"hello": "world",
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Description = "example",
LanguageCode = "en",
Type = "CUSTOM",
Tags =
{
{ "hello", "world" },
},
});
});
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(exampleAwsKendraIndex.id())
.name("example")
.description("example")
.languageCode("en")
.type("CUSTOM")
.tags(Map.of("hello", "world"))
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
description: example
languageCode: en
type: CUSTOM
tags:
hello: world
S3 Connector
With Schedule
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "S3",
roleArn: exampleAwsIamRole.arn,
schedule: "cron(9 10 1 * ? *)",
configuration: {
s3Configuration: {
bucketName: exampleAwsS3Bucket.id,
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="S3",
role_arn=example_aws_iam_role["arn"],
schedule="cron(9 10 1 * ? *)",
configuration={
"s3_configuration": {
"bucket_name": example_aws_s3_bucket["id"],
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("S3"),
RoleArn: pulumi.Any(exampleAwsIamRole.Arn),
Schedule: pulumi.String("cron(9 10 1 * ? *)"),
Configuration: &kendra.DataSourceConfigurationArgs{
S3Configuration: &kendra.DataSourceConfigurationS3ConfigurationArgs{
BucketName: pulumi.Any(exampleAwsS3Bucket.Id),
},
},
})
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "S3",
RoleArn = exampleAwsIamRole.Arn,
Schedule = "cron(9 10 1 * ? *)",
Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
{
S3Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationArgs
{
BucketName = exampleAwsS3Bucket.Id,
},
},
});
});
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(exampleAwsKendraIndex.id())
.name("example")
.type("S3")
.roleArn(exampleAwsIamRole.arn())
.schedule("cron(9 10 1 * ? *)")
.configuration(DataSourceConfigurationArgs.builder()
.s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
.bucketName(exampleAwsS3Bucket.id())
.build())
.build())
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: S3
roleArn: ${exampleAwsIamRole.arn}
schedule: cron(9 10 1 * ? *)
configuration:
s3Configuration:
bucketName: ${exampleAwsS3Bucket.id}
With Access Control List
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "S3",
roleArn: exampleAwsIamRole.arn,
configuration: {
s3Configuration: {
bucketName: exampleAwsS3Bucket.id,
accessControlListConfiguration: {
keyPath: `s3://${exampleAwsS3Bucket.id}/path-1`,
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="S3",
role_arn=example_aws_iam_role["arn"],
configuration={
"s3_configuration": {
"bucket_name": example_aws_s3_bucket["id"],
"access_control_list_configuration": {
"key_path": f"s3://{example_aws_s3_bucket['id']}/path-1",
},
},
})
package main
import (
"fmt"
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("S3"),
RoleArn: pulumi.Any(exampleAwsIamRole.Arn),
Configuration: &kendra.DataSourceConfigurationArgs{
S3Configuration: &kendra.DataSourceConfigurationS3ConfigurationArgs{
BucketName: pulumi.Any(exampleAwsS3Bucket.Id),
AccessControlListConfiguration: &kendra.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs{
KeyPath: pulumi.Sprintf("s3://%v/path-1", exampleAwsS3Bucket.Id),
},
},
},
})
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "S3",
RoleArn = exampleAwsIamRole.Arn,
Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
{
S3Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationArgs
{
BucketName = exampleAwsS3Bucket.Id,
AccessControlListConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs
{
KeyPath = $"s3://{exampleAwsS3Bucket.Id}/path-1",
},
},
},
});
});
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(exampleAwsKendraIndex.id())
.name("example")
.type("S3")
.roleArn(exampleAwsIamRole.arn())
.configuration(DataSourceConfigurationArgs.builder()
.s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
.bucketName(exampleAwsS3Bucket.id())
.accessControlListConfiguration(DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs.builder()
.keyPath(String.format("s3://%s/path-1", exampleAwsS3Bucket.id()))
.build())
.build())
.build())
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: S3
roleArn: ${exampleAwsIamRole.arn}
configuration:
s3Configuration:
bucketName: ${exampleAwsS3Bucket.id}
accessControlListConfiguration:
keyPath: s3://${exampleAwsS3Bucket.id}/path-1
With Documents Metadata Configuration
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "S3",
roleArn: exampleAwsIamRole.arn,
configuration: {
s3Configuration: {
bucketName: exampleAwsS3Bucket.id,
exclusionPatterns: ["example"],
inclusionPatterns: ["hello"],
inclusionPrefixes: ["world"],
documentsMetadataConfiguration: {
s3Prefix: "example",
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="S3",
role_arn=example_aws_iam_role["arn"],
configuration={
"s3_configuration": {
"bucket_name": example_aws_s3_bucket["id"],
"exclusion_patterns": ["example"],
"inclusion_patterns": ["hello"],
"inclusion_prefixes": ["world"],
"documents_metadata_configuration": {
"s3_prefix": "example",
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("S3"),
RoleArn: pulumi.Any(exampleAwsIamRole.Arn),
Configuration: &kendra.DataSourceConfigurationArgs{
S3Configuration: &kendra.DataSourceConfigurationS3ConfigurationArgs{
BucketName: pulumi.Any(exampleAwsS3Bucket.Id),
ExclusionPatterns: pulumi.StringArray{
pulumi.String("example"),
},
InclusionPatterns: pulumi.StringArray{
pulumi.String("hello"),
},
InclusionPrefixes: pulumi.StringArray{
pulumi.String("world"),
},
DocumentsMetadataConfiguration: &kendra.DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs{
S3Prefix: pulumi.String("example"),
},
},
},
})
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "S3",
RoleArn = exampleAwsIamRole.Arn,
Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
{
S3Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationArgs
{
BucketName = exampleAwsS3Bucket.Id,
ExclusionPatterns = new[]
{
"example",
},
InclusionPatterns = new[]
{
"hello",
},
InclusionPrefixes = new[]
{
"world",
},
DocumentsMetadataConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs
{
S3Prefix = "example",
},
},
},
});
});
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.DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs;
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(exampleAwsKendraIndex.id())
.name("example")
.type("S3")
.roleArn(exampleAwsIamRole.arn())
.configuration(DataSourceConfigurationArgs.builder()
.s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
.bucketName(exampleAwsS3Bucket.id())
.exclusionPatterns("example")
.inclusionPatterns("hello")
.inclusionPrefixes("world")
.documentsMetadataConfiguration(DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs.builder()
.s3Prefix("example")
.build())
.build())
.build())
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: S3
roleArn: ${exampleAwsIamRole.arn}
configuration:
s3Configuration:
bucketName: ${exampleAwsS3Bucket.id}
exclusionPatterns:
- example
inclusionPatterns:
- hello
inclusionPrefixes:
- world
documentsMetadataConfiguration:
s3Prefix: example
Web Crawler Connector
With Seed URLs
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.arn())
.configuration(DataSourceConfigurationArgs.builder()
.webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
.urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
.seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
.seedUrls("REPLACE_WITH_YOUR_URL")
.build())
.build())
.build())
.build())
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
With Site Maps
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
urls: {
siteMapsConfiguration: {
siteMaps: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"urls": {
"site_maps_configuration": {
"site_maps": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.arn())
.configuration(DataSourceConfigurationArgs.builder()
.webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
.urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
.siteMapsConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs.builder()
.siteMaps("REPLACE_WITH_YOUR_URL")
.build())
.build())
.build())
.build())
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
urls:
siteMapsConfiguration:
siteMaps:
- REPLACE_WITH_YOUR_URL
With Web Crawler Mode
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
urls: {
seedUrlConfiguration: {
webCrawlerMode: "SUBDOMAINS",
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"urls": {
"seed_url_configuration": {
"web_crawler_mode": "SUBDOMAINS",
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.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());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
urls:
seedUrlConfiguration:
webCrawlerMode: SUBDOMAINS
seedUrls:
- REPLACE_WITH_YOUR_URL
With Authentication Configuration
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
authenticationConfiguration: {
basicAuthentications: [{
credentials: exampleAwsSecretsmanagerSecret.arn,
host: "a.example.com",
port: 443,
}],
},
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
}, {
dependsOn: [exampleAwsSecretsmanagerSecretVersion],
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"authentication_configuration": {
"basic_authentications": [{
"credentials": example_aws_secretsmanager_secret["arn"],
"host": "a.example.com",
"port": 443,
}],
},
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
opts = pulumi.ResourceOptions(depends_on=[example_aws_secretsmanager_secret_version]))
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.Arn),
Configuration: &kendra.DataSourceConfigurationArgs{
WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
AuthenticationConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs{
BasicAuthentications: kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArray{
&kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs{
Credentials: pulumi.Any(exampleAwsSecretsmanagerSecret.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{
exampleAwsSecretsmanagerSecretVersion,
}))
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 = exampleAwsSecretsmanagerSecret.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 =
{
exampleAwsSecretsmanagerSecretVersion,
},
});
});
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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.arn())
.configuration(DataSourceConfigurationArgs.builder()
.webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
.authenticationConfiguration(DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs.builder()
.basicAuthentications(DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs.builder()
.credentials(exampleAwsSecretsmanagerSecret.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(exampleAwsSecretsmanagerSecretVersion)
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
authenticationConfiguration:
basicAuthentications:
- credentials: ${exampleAwsSecretsmanagerSecret.arn}
host: a.example.com
port: '443'
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
options:
dependson:
- ${exampleAwsSecretsmanagerSecretVersion}
With Crawl Depth
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
crawlDepth: 3,
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"crawl_depth": 3,
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.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());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
crawlDepth: 3
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
With Max Links Per Page
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
maxLinksPerPage: 100,
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"max_links_per_page": 100,
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.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());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
maxLinksPerPage: 100
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
With Max Urls Per Minute Crawl Rate
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
maxUrlsPerMinuteCrawlRate: 300,
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"max_urls_per_minute_crawl_rate": 300,
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.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());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
maxUrlsPerMinuteCrawlRate: 300
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
With Proxy Configuration
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
proxyConfiguration: {
credentials: exampleAwsSecretsmanagerSecret.arn,
host: "a.example.com",
port: 443,
},
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
}, {
dependsOn: [exampleAwsSecretsmanagerSecretVersion],
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"proxy_configuration": {
"credentials": example_aws_secretsmanager_secret["arn"],
"host": "a.example.com",
"port": 443,
},
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
opts = pulumi.ResourceOptions(depends_on=[example_aws_secretsmanager_secret_version]))
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.Arn),
Configuration: &kendra.DataSourceConfigurationArgs{
WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
ProxyConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs{
Credentials: pulumi.Any(exampleAwsSecretsmanagerSecret.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{
exampleAwsSecretsmanagerSecretVersion,
}))
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.Arn,
Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
{
WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
{
ProxyConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs
{
Credentials = exampleAwsSecretsmanagerSecret.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 =
{
exampleAwsSecretsmanagerSecretVersion,
},
});
});
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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.arn())
.configuration(DataSourceConfigurationArgs.builder()
.webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
.proxyConfiguration(DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs.builder()
.credentials(exampleAwsSecretsmanagerSecret.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(exampleAwsSecretsmanagerSecretVersion)
.build());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
proxyConfiguration:
credentials: ${exampleAwsSecretsmanagerSecret.arn}
host: a.example.com
port: '443'
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
options:
dependson:
- ${exampleAwsSecretsmanagerSecretVersion}
With URL Exclusion and Inclusion Patterns
import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";
const example = new aws.kendra.DataSource("example", {
indexId: exampleAwsKendraIndex.id,
name: "example",
type: "WEBCRAWLER",
roleArn: exampleAwsIamRole.arn,
configuration: {
webCrawlerConfiguration: {
urlExclusionPatterns: ["example"],
urlInclusionPatterns: ["hello"],
urls: {
seedUrlConfiguration: {
seedUrls: ["REPLACE_WITH_YOUR_URL"],
},
},
},
},
});
import pulumi
import pulumi_aws as aws
example = aws.kendra.DataSource("example",
index_id=example_aws_kendra_index["id"],
name="example",
type="WEBCRAWLER",
role_arn=example_aws_iam_role["arn"],
configuration={
"web_crawler_configuration": {
"url_exclusion_patterns": ["example"],
"url_inclusion_patterns": ["hello"],
"urls": {
"seed_url_configuration": {
"seed_urls": ["REPLACE_WITH_YOUR_URL"],
},
},
},
})
package main
import (
"github.com/pulumi/pulumi-aws/sdk/v6/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(exampleAwsKendraIndex.Id),
Name: pulumi.String("example"),
Type: pulumi.String("WEBCRAWLER"),
RoleArn: pulumi.Any(exampleAwsIamRole.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
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;
return await Deployment.RunAsync(() =>
{
var example = new Aws.Kendra.DataSource("example", new()
{
IndexId = exampleAwsKendraIndex.Id,
Name = "example",
Type = "WEBCRAWLER",
RoleArn = exampleAwsIamRole.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 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(exampleAwsKendraIndex.id())
.name("example")
.type("WEBCRAWLER")
.roleArn(exampleAwsIamRole.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());
}
}
resources:
example:
type: aws:kendra:DataSource
properties:
indexId: ${exampleAwsKendraIndex.id}
name: example
type: WEBCRAWLER
roleArn: ${exampleAwsIamRole.arn}
configuration:
webCrawlerConfiguration:
urlExclusionPatterns:
- example
urlInclusionPatterns:
- hello
urls:
seedUrlConfiguration:
seedUrls:
- REPLACE_WITH_YOUR_URL
Create DataSource Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new DataSource(name: string, args: DataSourceArgs, opts?: CustomResourceOptions);@overload
def DataSource(resource_name: str,
args: DataSourceArgs,
opts: Optional[ResourceOptions] = None)
@overload
def DataSource(resource_name: str,
opts: Optional[ResourceOptions] = None,
index_id: Optional[str] = None,
type: Optional[str] = None,
configuration: Optional[DataSourceConfigurationArgs] = None,
custom_document_enrichment_configuration: Optional[DataSourceCustomDocumentEnrichmentConfigurationArgs] = None,
description: 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)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.
Parameters
- 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.
Constructor example
The following reference example uses placeholder values for all input properties.
var awsDataSourceResource = new Aws.Kendra.DataSource("awsDataSourceResource", new()
{
IndexId = "string",
Type = "string",
Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationArgs
{
S3Configuration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationArgs
{
BucketName = "string",
AccessControlListConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs
{
KeyPath = "string",
},
DocumentsMetadataConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs
{
S3Prefix = "string",
},
ExclusionPatterns = new[]
{
"string",
},
InclusionPatterns = new[]
{
"string",
},
InclusionPrefixes = new[]
{
"string",
},
},
WebCrawlerConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationArgs
{
Urls = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
{
SeedUrlConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
{
SeedUrls = new[]
{
"string",
},
WebCrawlerMode = "string",
},
SiteMapsConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs
{
SiteMaps = new[]
{
"string",
},
},
},
AuthenticationConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs
{
BasicAuthentications = new[]
{
new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs
{
Credentials = "string",
Host = "string",
Port = 0,
},
},
},
CrawlDepth = 0,
MaxContentSizePerPageInMegaBytes = 0,
MaxLinksPerPage = 0,
MaxUrlsPerMinuteCrawlRate = 0,
ProxyConfiguration = new Aws.Kendra.Inputs.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs
{
Host = "string",
Port = 0,
Credentials = "string",
},
UrlExclusionPatterns = new[]
{
"string",
},
UrlInclusionPatterns = new[]
{
"string",
},
},
},
CustomDocumentEnrichmentConfiguration = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationArgs
{
InlineConfigurations = new[]
{
new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationArgs
{
Condition = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionArgs
{
ConditionDocumentAttributeKey = "string",
Operator = "string",
ConditionOnValue = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValueArgs
{
DateValue = "string",
LongValue = 0,
StringListValues = new[]
{
"string",
},
StringValue = "string",
},
},
DocumentContentDeletion = false,
Target = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetArgs
{
TargetDocumentAttributeKey = "string",
TargetDocumentAttributeValue = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValueArgs
{
DateValue = "string",
LongValue = 0,
StringListValues = new[]
{
"string",
},
StringValue = "string",
},
TargetDocumentAttributeValueDeletion = false,
},
},
},
PostExtractionHookConfiguration = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationArgs
{
LambdaArn = "string",
S3Bucket = "string",
InvocationCondition = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionArgs
{
ConditionDocumentAttributeKey = "string",
Operator = "string",
ConditionOnValue = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValueArgs
{
DateValue = "string",
LongValue = 0,
StringListValues = new[]
{
"string",
},
StringValue = "string",
},
},
},
PreExtractionHookConfiguration = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationArgs
{
LambdaArn = "string",
S3Bucket = "string",
InvocationCondition = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionArgs
{
ConditionDocumentAttributeKey = "string",
Operator = "string",
ConditionOnValue = new Aws.Kendra.Inputs.DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValueArgs
{
DateValue = "string",
LongValue = 0,
StringListValues = new[]
{
"string",
},
StringValue = "string",
},
},
},
RoleArn = "string",
},
Description = "string",
LanguageCode = "string",
Name = "string",
RoleArn = "string",
Schedule = "string",
Tags =
{
{ "string", "string" },
},
});
example, err := kendra.NewDataSource(ctx, "awsDataSourceResource", &kendra.DataSourceArgs{
IndexId: pulumi.String("string"),
Type: pulumi.String("string"),
Configuration: &kendra.DataSourceConfigurationArgs{
S3Configuration: &kendra.DataSourceConfigurationS3ConfigurationArgs{
BucketName: pulumi.String("string"),
AccessControlListConfiguration: &kendra.DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs{
KeyPath: pulumi.String("string"),
},
DocumentsMetadataConfiguration: &kendra.DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs{
S3Prefix: pulumi.String("string"),
},
ExclusionPatterns: pulumi.StringArray{
pulumi.String("string"),
},
InclusionPatterns: pulumi.StringArray{
pulumi.String("string"),
},
InclusionPrefixes: pulumi.StringArray{
pulumi.String("string"),
},
},
WebCrawlerConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationArgs{
Urls: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsArgs{
SeedUrlConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs{
SeedUrls: pulumi.StringArray{
pulumi.String("string"),
},
WebCrawlerMode: pulumi.String("string"),
},
SiteMapsConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs{
SiteMaps: pulumi.StringArray{
pulumi.String("string"),
},
},
},
AuthenticationConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs{
BasicAuthentications: kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArray{
&kendra.DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs{
Credentials: pulumi.String("string"),
Host: pulumi.String("string"),
Port: pulumi.Int(0),
},
},
},
CrawlDepth: pulumi.Int(0),
MaxContentSizePerPageInMegaBytes: pulumi.Float64(0),
MaxLinksPerPage: pulumi.Int(0),
MaxUrlsPerMinuteCrawlRate: pulumi.Int(0),
ProxyConfiguration: &kendra.DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs{
Host: pulumi.String("string"),
Port: pulumi.Int(0),
Credentials: pulumi.String("string"),
},
UrlExclusionPatterns: pulumi.StringArray{
pulumi.String("string"),
},
UrlInclusionPatterns: pulumi.StringArray{
pulumi.String("string"),
},
},
},
CustomDocumentEnrichmentConfiguration: &kendra.DataSourceCustomDocumentEnrichmentConfigurationArgs{
InlineConfigurations: kendra.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationArray{
&kendra.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationArgs{
Condition: &kendra.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionArgs{
ConditionDocumentAttributeKey: pulumi.String("string"),
Operator: pulumi.String("string"),
ConditionOnValue: &kendra.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValueArgs{
DateValue: pulumi.String("string"),
LongValue: pulumi.Int(0),
StringListValues: pulumi.StringArray{
pulumi.String("string"),
},
StringValue: pulumi.String("string"),
},
},
DocumentContentDeletion: pulumi.Bool(false),
Target: &kendra.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetArgs{
TargetDocumentAttributeKey: pulumi.String("string"),
TargetDocumentAttributeValue: &kendra.DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValueArgs{
DateValue: pulumi.String("string"),
LongValue: pulumi.Int(0),
StringListValues: pulumi.StringArray{
pulumi.String("string"),
},
StringValue: pulumi.String("string"),
},
TargetDocumentAttributeValueDeletion: pulumi.Bool(false),
},
},
},
PostExtractionHookConfiguration: &kendra.DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationArgs{
LambdaArn: pulumi.String("string"),
S3Bucket: pulumi.String("string"),
InvocationCondition: &kendra.DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionArgs{
ConditionDocumentAttributeKey: pulumi.String("string"),
Operator: pulumi.String("string"),
ConditionOnValue: &kendra.DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValueArgs{
DateValue: pulumi.String("string"),
LongValue: pulumi.Int(0),
StringListValues: pulumi.StringArray{
pulumi.String("string"),
},
StringValue: pulumi.String("string"),
},
},
},
PreExtractionHookConfiguration: &kendra.DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationArgs{
LambdaArn: pulumi.String("string"),
S3Bucket: pulumi.String("string"),
InvocationCondition: &kendra.DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionArgs{
ConditionDocumentAttributeKey: pulumi.String("string"),
Operator: pulumi.String("string"),
ConditionOnValue: &kendra.DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValueArgs{
DateValue: pulumi.String("string"),
LongValue: pulumi.Int(0),
StringListValues: pulumi.StringArray{
pulumi.String("string"),
},
StringValue: pulumi.String("string"),
},
},
},
RoleArn: pulumi.String("string"),
},
Description: pulumi.String("string"),
LanguageCode: pulumi.String("string"),
Name: pulumi.String("string"),
RoleArn: pulumi.String("string"),
Schedule: pulumi.String("string"),
Tags: pulumi.StringMap{
"string": pulumi.String("string"),
},
})
var awsDataSourceResource = new DataSource("awsDataSourceResource", DataSourceArgs.builder()
.indexId("string")
.type("string")
.configuration(DataSourceConfigurationArgs.builder()
.s3Configuration(DataSourceConfigurationS3ConfigurationArgs.builder()
.bucketName("string")
.accessControlListConfiguration(DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs.builder()
.keyPath("string")
.build())
.documentsMetadataConfiguration(DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs.builder()
.s3Prefix("string")
.build())
.exclusionPatterns("string")
.inclusionPatterns("string")
.inclusionPrefixes("string")
.build())
.webCrawlerConfiguration(DataSourceConfigurationWebCrawlerConfigurationArgs.builder()
.urls(DataSourceConfigurationWebCrawlerConfigurationUrlsArgs.builder()
.seedUrlConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs.builder()
.seedUrls("string")
.webCrawlerMode("string")
.build())
.siteMapsConfiguration(DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs.builder()
.siteMaps("string")
.build())
.build())
.authenticationConfiguration(DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs.builder()
.basicAuthentications(DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs.builder()
.credentials("string")
.host("string")
.port(0)
.build())
.build())
.crawlDepth(0)
.maxContentSizePerPageInMegaBytes(0)
.maxLinksPerPage(0)
.maxUrlsPerMinuteCrawlRate(0)
.proxyConfiguration(DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs.builder()
.host("string")
.port(0)
.credentials("string")
.build())
.urlExclusionPatterns("string")
.urlInclusionPatterns("string")
.build())
.build())
.customDocumentEnrichmentConfiguration(DataSourceCustomDocumentEnrichmentConfigurationArgs.builder()
.inlineConfigurations(DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationArgs.builder()
.condition(DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionArgs.builder()
.conditionDocumentAttributeKey("string")
.operator("string")
.conditionOnValue(DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValueArgs.builder()
.dateValue("string")
.longValue(0)
.stringListValues("string")
.stringValue("string")
.build())
.build())
.documentContentDeletion(false)
.target(DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetArgs.builder()
.targetDocumentAttributeKey("string")
.targetDocumentAttributeValue(DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValueArgs.builder()
.dateValue("string")
.longValue(0)
.stringListValues("string")
.stringValue("string")
.build())
.targetDocumentAttributeValueDeletion(false)
.build())
.build())
.postExtractionHookConfiguration(DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationArgs.builder()
.lambdaArn("string")
.s3Bucket("string")
.invocationCondition(DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionArgs.builder()
.conditionDocumentAttributeKey("string")
.operator("string")
.conditionOnValue(DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValueArgs.builder()
.dateValue("string")
.longValue(0)
.stringListValues("string")
.stringValue("string")
.build())
.build())
.build())
.preExtractionHookConfiguration(DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationArgs.builder()
.lambdaArn("string")
.s3Bucket("string")
.invocationCondition(DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionArgs.builder()
.conditionDocumentAttributeKey("string")
.operator("string")
.conditionOnValue(DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValueArgs.builder()
.dateValue("string")
.longValue(0)
.stringListValues("string")
.stringValue("string")
.build())
.build())
.build())
.roleArn("string")
.build())
.description("string")
.languageCode("string")
.name("string")
.roleArn("string")
.schedule("string")
.tags(Map.of("string", "string"))
.build());
aws_data_source_resource = aws.kendra.DataSource("awsDataSourceResource",
index_id="string",
type="string",
configuration={
"s3_configuration": {
"bucket_name": "string",
"access_control_list_configuration": {
"key_path": "string",
},
"documents_metadata_configuration": {
"s3_prefix": "string",
},
"exclusion_patterns": ["string"],
"inclusion_patterns": ["string"],
"inclusion_prefixes": ["string"],
},
"web_crawler_configuration": {
"urls": {
"seed_url_configuration": {
"seed_urls": ["string"],
"web_crawler_mode": "string",
},
"site_maps_configuration": {
"site_maps": ["string"],
},
},
"authentication_configuration": {
"basic_authentications": [{
"credentials": "string",
"host": "string",
"port": 0,
}],
},
"crawl_depth": 0,
"max_content_size_per_page_in_mega_bytes": 0,
"max_links_per_page": 0,
"max_urls_per_minute_crawl_rate": 0,
"proxy_configuration": {
"host": "string",
"port": 0,
"credentials": "string",
},
"url_exclusion_patterns": ["string"],
"url_inclusion_patterns": ["string"],
},
},
custom_document_enrichment_configuration={
"inline_configurations": [{
"condition": {
"condition_document_attribute_key": "string",
"operator": "string",
"condition_on_value": {
"date_value": "string",
"long_value": 0,
"string_list_values": ["string"],
"string_value": "string",
},
},
"document_content_deletion": False,
"target": {
"target_document_attribute_key": "string",
"target_document_attribute_value": {
"date_value": "string",
"long_value": 0,
"string_list_values": ["string"],
"string_value": "string",
},
"target_document_attribute_value_deletion": False,
},
}],
"post_extraction_hook_configuration": {
"lambda_arn": "string",
"s3_bucket": "string",
"invocation_condition": {
"condition_document_attribute_key": "string",
"operator": "string",
"condition_on_value": {
"date_value": "string",
"long_value": 0,
"string_list_values": ["string"],
"string_value": "string",
},
},
},
"pre_extraction_hook_configuration": {
"lambda_arn": "string",
"s3_bucket": "string",
"invocation_condition": {
"condition_document_attribute_key": "string",
"operator": "string",
"condition_on_value": {
"date_value": "string",
"long_value": 0,
"string_list_values": ["string"],
"string_value": "string",
},
},
},
"role_arn": "string",
},
description="string",
language_code="string",
name="string",
role_arn="string",
schedule="string",
tags={
"string": "string",
})
const awsDataSourceResource = new aws.kendra.DataSource("awsDataSourceResource", {
indexId: "string",
type: "string",
configuration: {
s3Configuration: {
bucketName: "string",
accessControlListConfiguration: {
keyPath: "string",
},
documentsMetadataConfiguration: {
s3Prefix: "string",
},
exclusionPatterns: ["string"],
inclusionPatterns: ["string"],
inclusionPrefixes: ["string"],
},
webCrawlerConfiguration: {
urls: {
seedUrlConfiguration: {
seedUrls: ["string"],
webCrawlerMode: "string",
},
siteMapsConfiguration: {
siteMaps: ["string"],
},
},
authenticationConfiguration: {
basicAuthentications: [{
credentials: "string",
host: "string",
port: 0,
}],
},
crawlDepth: 0,
maxContentSizePerPageInMegaBytes: 0,
maxLinksPerPage: 0,
maxUrlsPerMinuteCrawlRate: 0,
proxyConfiguration: {
host: "string",
port: 0,
credentials: "string",
},
urlExclusionPatterns: ["string"],
urlInclusionPatterns: ["string"],
},
},
customDocumentEnrichmentConfiguration: {
inlineConfigurations: [{
condition: {
conditionDocumentAttributeKey: "string",
operator: "string",
conditionOnValue: {
dateValue: "string",
longValue: 0,
stringListValues: ["string"],
stringValue: "string",
},
},
documentContentDeletion: false,
target: {
targetDocumentAttributeKey: "string",
targetDocumentAttributeValue: {
dateValue: "string",
longValue: 0,
stringListValues: ["string"],
stringValue: "string",
},
targetDocumentAttributeValueDeletion: false,
},
}],
postExtractionHookConfiguration: {
lambdaArn: "string",
s3Bucket: "string",
invocationCondition: {
conditionDocumentAttributeKey: "string",
operator: "string",
conditionOnValue: {
dateValue: "string",
longValue: 0,
stringListValues: ["string"],
stringValue: "string",
},
},
},
preExtractionHookConfiguration: {
lambdaArn: "string",
s3Bucket: "string",
invocationCondition: {
conditionDocumentAttributeKey: "string",
operator: "string",
conditionOnValue: {
dateValue: "string",
longValue: 0,
stringListValues: ["string"],
stringValue: "string",
},
},
},
roleArn: "string",
},
description: "string",
languageCode: "string",
name: "string",
roleArn: "string",
schedule: "string",
tags: {
string: "string",
},
});
type: aws:kendra:DataSource
properties:
configuration:
s3Configuration:
accessControlListConfiguration:
keyPath: string
bucketName: string
documentsMetadataConfiguration:
s3Prefix: string
exclusionPatterns:
- string
inclusionPatterns:
- string
inclusionPrefixes:
- string
webCrawlerConfiguration:
authenticationConfiguration:
basicAuthentications:
- credentials: string
host: string
port: 0
crawlDepth: 0
maxContentSizePerPageInMegaBytes: 0
maxLinksPerPage: 0
maxUrlsPerMinuteCrawlRate: 0
proxyConfiguration:
credentials: string
host: string
port: 0
urlExclusionPatterns:
- string
urlInclusionPatterns:
- string
urls:
seedUrlConfiguration:
seedUrls:
- string
webCrawlerMode: string
siteMapsConfiguration:
siteMaps:
- string
customDocumentEnrichmentConfiguration:
inlineConfigurations:
- condition:
conditionDocumentAttributeKey: string
conditionOnValue:
dateValue: string
longValue: 0
stringListValues:
- string
stringValue: string
operator: string
documentContentDeletion: false
target:
targetDocumentAttributeKey: string
targetDocumentAttributeValue:
dateValue: string
longValue: 0
stringListValues:
- string
stringValue: string
targetDocumentAttributeValueDeletion: false
postExtractionHookConfiguration:
invocationCondition:
conditionDocumentAttributeKey: string
conditionOnValue:
dateValue: string
longValue: 0
stringListValues:
- string
stringValue: string
operator: string
lambdaArn: string
s3Bucket: string
preExtractionHookConfiguration:
invocationCondition:
conditionDocumentAttributeKey: string
conditionOnValue:
dateValue: string
longValue: 0
stringListValues:
- string
stringValue: string
operator: string
lambdaArn: string
s3Bucket: string
roleArn: string
description: string
indexId: string
languageCode: string
name: string
roleArn: string
schedule: string
tags:
string: string
type: string
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
In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.
The DataSource resource accepts the following input properties:
- Index
Id 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.
The following arguments are optional:
- Configuration
Data
Source Configuration - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - Custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration - 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.
- Language
Code 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.
- Role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - Dictionary<string, string>
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level.
- Index
Id 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.
The following arguments are optional:
- Configuration
Data
Source Configuration Args - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - Custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration Args - 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.
- Language
Code 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.
- Role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - map[string]string
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level.
- index
Id 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.
The following arguments are optional:
- configuration
Data
Source Configuration - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration - 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.
- language
Code 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.
- role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - Map<String,String>
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level.
- index
Id 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.
The following arguments are optional:
- configuration
Data
Source Configuration - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration - 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.
- language
Code 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.
- role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - {[key: string]: string}
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level.
- 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.
The following arguments are optional:
- configuration
Data
Source Configuration Args - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - custom_
document_ Dataenrichment_ configuration Source Custom Document Enrichment Configuration Args - 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - Mapping[str, str]
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level.
- index
Id 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.
The following arguments are optional:
- configuration Property Map
- A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - custom
Document Property MapEnrichment Configuration - 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.
- language
Code 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.
- role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - Map<String>
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level.
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.
- Created
At string - The Unix timestamp of when the Data Source was created.
- Data
Source stringId - The unique identifiers of the Data Source.
- Error
Message 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
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Dictionary<string, string>
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - Updated
At string - The Unix timestamp of when the Data Source was last updated.
- Arn string
- ARN of the Data Source.
- Created
At string - The Unix timestamp of when the Data Source was created.
- Data
Source stringId - The unique identifiers of the Data Source.
- Error
Message 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
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - map[string]string
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - Updated
At string - The Unix timestamp of when the Data Source was last updated.
- arn String
- ARN of the Data Source.
- created
At String - The Unix timestamp of when the Data Source was created.
- data
Source StringId - The unique identifiers of the Data Source.
- error
Message 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
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Map<String,String>
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - updated
At String - The Unix timestamp of when the Data Source was last updated.
- arn string
- ARN of the Data Source.
- created
At string - The Unix timestamp of when the Data Source was created.
- data
Source stringId - The unique identifiers of the Data Source.
- error
Message 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
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - {[key: string]: string}
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - updated
At 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_ strid - 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
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Mapping[str, str]
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - updated_
at str - The Unix timestamp of when the Data Source was last updated.
- arn String
- ARN of the Data Source.
- created
At String - The Unix timestamp of when the Data Source was created.
- data
Source StringId - The unique identifiers of the Data Source.
- error
Message 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
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Map<String>
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - updated
At String - The Unix timestamp of when the Data Source was last updated.
Look up 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) -> DataSourcefunc 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.
- Arn string
- ARN of the Data Source.
- Configuration
Data
Source Configuration - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - Created
At string - The Unix timestamp of when the Data Source was created.
- Custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration - 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 stringId - The unique identifiers of the Data Source.
- Description string
- A description for the Data Source connector.
- Error
Message string - 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 string - The identifier of the index for your Amazon Kendra data source.
- Language
Code 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.
- Role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - Status string
- The current status of the Data Source. When the status is
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Dictionary<string, string>
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level. - Dictionary<string, string>
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - Type string
The type of data source repository. For an updated list of values, refer to Valid Values for Type.
The following arguments are optional:
- Updated
At string - The Unix timestamp of when the Data Source was last updated.
- Arn string
- ARN of the Data Source.
- Configuration
Data
Source Configuration Args - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - Created
At string - The Unix timestamp of when the Data Source was created.
- Custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration Args - 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 stringId - The unique identifiers of the Data Source.
- Description string
- A description for the Data Source connector.
- Error
Message string - 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 string - The identifier of the index for your Amazon Kendra data source.
- Language
Code 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.
- Role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - Status string
- The current status of the Data Source. When the status is
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - map[string]string
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level. - map[string]string
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - Type string
The type of data source repository. For an updated list of values, refer to Valid Values for Type.
The following arguments are optional:
- Updated
At string - The Unix timestamp of when the Data Source was last updated.
- arn String
- ARN of the Data Source.
- configuration
Data
Source Configuration - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - created
At String - The Unix timestamp of when the Data Source was created.
- custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration - 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 StringId - The unique identifiers of the Data Source.
- description String
- A description for the Data Source connector.
- error
Message String - 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 String - The identifier of the index for your Amazon Kendra data source.
- language
Code 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.
- role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - status String
- The current status of the Data Source. When the status is
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Map<String,String>
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level. - Map<String,String>
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - type String
The type of data source repository. For an updated list of values, refer to Valid Values for Type.
The following arguments are optional:
- updated
At String - The Unix timestamp of when the Data Source was last updated.
- arn string
- ARN of the Data Source.
- configuration
Data
Source Configuration - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - created
At string - The Unix timestamp of when the Data Source was created.
- custom
Document DataEnrichment Configuration Source Custom Document Enrichment Configuration - 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 stringId - The unique identifiers of the Data Source.
- description string
- A description for the Data Source connector.
- error
Message string - 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 string - The identifier of the index for your Amazon Kendra data source.
- language
Code 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.
- role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - status string
- The current status of the Data Source. When the status is
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - {[key: string]: string}
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level. - {[key: string]: string}
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - type string
The type of data source repository. For an updated list of values, refer to Valid Values for Type.
The following arguments are optional:
- updated
At string - The Unix timestamp of when the Data Source was last updated.
- arn str
- ARN of the Data Source.
- configuration
Data
Source Configuration Args - A block with the configuration information to connect to your Data Source repository. You can't specify the
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - created_
at str - The Unix timestamp of when the Data Source was created.
- custom_
document_ Dataenrichment_ configuration Source Custom Document Enrichment Configuration Args - 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_ strid - 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - status str
- The current status of the Data Source. When the status is
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Mapping[str, str]
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level. - Mapping[str, str]
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - type str
The type of data source repository. For an updated list of values, refer to Valid Values for Type.
The following arguments are optional:
- 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
configurationblock when thetypeparameter is set toCUSTOM. Detailed below. - created
At String - The Unix timestamp of when the Data Source was created.
- custom
Document Property MapEnrichment Configuration - 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 StringId - The unique identifiers of the Data Source.
- description String
- A description for the Data Source connector.
- error
Message String - 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 String - The identifier of the index for your Amazon Kendra data source.
- language
Code 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.
- role
Arn 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_arnparameter when thetypeparameter is set toCUSTOM. Therole_arnparameter 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
StartDataSourceSyncJobAPI to update the index. - status String
- The current status of the Data Source. When the status is
ACTIVEthe Data Source is ready to use. When the status isFAILED, theerror_messagefield contains the reason that the Data Source failed. - Map<String>
- Key-value map of resource tags. If configured with a provider
default_tagsconfiguration block present, tags with matching keys will overwrite those defined at the provider-level. - Map<String>
- A map of tags assigned to the resource, including those inherited from the provider
default_tagsconfiguration block. - type String
The type of data source repository. For an updated list of values, refer to Valid Values for Type.
The following arguments are optional:
- updated
At String - The Unix timestamp of when the Data Source was last updated.
Supporting Types
DataSourceConfiguration, DataSourceConfigurationArgs
- S3Configuration
Data
Source Configuration S3Configuration - A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.
- Web
Crawler DataConfiguration Source Configuration Web Crawler Configuration - A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.
- S3Configuration
Data
Source Configuration S3Configuration - A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.
- Web
Crawler DataConfiguration Source Configuration Web Crawler Configuration - A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.
- s3Configuration
Data
Source Configuration S3Configuration - A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.
- web
Crawler DataConfiguration Source Configuration Web Crawler Configuration - A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.
- s3Configuration
Data
Source Configuration S3Configuration - A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.
- web
Crawler DataConfiguration Source Configuration Web Crawler Configuration - A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.
- s3_
configuration DataSource Configuration S3Configuration - A block that provides the configuration information to connect to an Amazon S3 bucket as your data source. Detailed below.
- web_
crawler_ Dataconfiguration Source Configuration Web Crawler Configuration - 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.
- web
Crawler Property MapConfiguration - A block that provides the configuration information required for Amazon Kendra Web Crawler. Detailed below.
DataSourceConfigurationS3Configuration, DataSourceConfigurationS3ConfigurationArgs
- Bucket
Name string - The name of the bucket that contains the documents.
- Access
Control DataList Configuration Source Configuration S3Configuration Access Control List Configuration - 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 DataConfiguration Source Configuration S3Configuration Documents Metadata Configuration - A block that defines the Document 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 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.
- Inclusion
Patterns 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.
- Inclusion
Prefixes List<string> - A list of S3 prefixes for the documents that should be included in the index.
- Bucket
Name string - The name of the bucket that contains the documents.
- Access
Control DataList Configuration Source Configuration S3Configuration Access Control List Configuration - 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 DataConfiguration Source Configuration S3Configuration Documents Metadata Configuration - A block that defines the Document 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 []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.
- Inclusion
Patterns []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.
- Inclusion
Prefixes []string - A list of S3 prefixes for the documents that should be included in the index.
- bucket
Name String - The name of the bucket that contains the documents.
- access
Control DataList Configuration Source Configuration S3Configuration Access Control List Configuration - 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 DataConfiguration Source Configuration S3Configuration Documents Metadata Configuration - A block that defines the Document 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 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.
- inclusion
Patterns 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.
- inclusion
Prefixes List<String> - A list of S3 prefixes for the documents that should be included in the index.
- bucket
Name string - The name of the bucket that contains the documents.
- access
Control DataList Configuration Source Configuration S3Configuration Access Control List Configuration - 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 DataConfiguration Source Configuration S3Configuration Documents Metadata Configuration - A block that defines the Document 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 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.
- inclusion
Patterns 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.
- inclusion
Prefixes 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_ Datalist_ configuration Source Configuration S3Configuration Access Control List Configuration - 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_ Dataconfiguration Source Configuration S3Configuration Documents Metadata Configuration - A block that defines the Document 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.
- bucket
Name String - The name of the bucket that contains the documents.
- access
Control Property MapList Configuration - 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 Property MapConfiguration - A block that defines the Document 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 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.
- inclusion
Patterns 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.
- inclusion
Prefixes List<String> - A list of S3 prefixes for the documents that should be included in the index.
DataSourceConfigurationS3ConfigurationAccessControlListConfiguration, DataSourceConfigurationS3ConfigurationAccessControlListConfigurationArgs
- Key
Path string - Path to the AWS S3 bucket that contains the ACL files.
- Key
Path string - Path to the AWS S3 bucket that contains the ACL files.
- key
Path String - Path to the AWS S3 bucket that contains the ACL files.
- key
Path 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.
- key
Path String - Path to the AWS S3 bucket that contains the ACL files.
DataSourceConfigurationS3ConfigurationDocumentsMetadataConfiguration, DataSourceConfigurationS3ConfigurationDocumentsMetadataConfigurationArgs
- 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_prefixto 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_prefixto 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_prefixto 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_prefixto 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_prefixto 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_prefixto include only the desired metadata files.
DataSourceConfigurationWebCrawlerConfiguration, DataSourceConfigurationWebCrawlerConfigurationArgs
- Urls
Data
Source Configuration Web Crawler Configuration Urls - 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
100seed URLs and up to3sitemap 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 DataSource Configuration Web Crawler Configuration Authentication Configuration - 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.htmlis"a.example.com"and the port is443, 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 of0. Maximum value of10. - Max
Content doubleSize Per Page In Mega Bytes - 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
50MB. Minimum value of1.0e-06. Maximum value of50. - Max
Links intPer Page - 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 of1. Maximum value of1000. - Max
Urls intPer Minute Crawl Rate - 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 of1. Maximum value of300. - Proxy
Configuration DataSource Configuration Web Crawler Configuration Proxy Configuration - 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.htmlis"a.example.com"and the port is443, 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 List<string>Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150. - Url
Inclusion List<string>Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150.
- Urls
Data
Source Configuration Web Crawler Configuration Urls - 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
100seed URLs and up to3sitemap 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 DataSource Configuration Web Crawler Configuration Authentication Configuration - 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.htmlis"a.example.com"and the port is443, 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 of0. Maximum value of10. - Max
Content float64Size Per Page In Mega Bytes - 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
50MB. Minimum value of1.0e-06. Maximum value of50. - Max
Links intPer Page - 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 of1. Maximum value of1000. - Max
Urls intPer Minute Crawl Rate - 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 of1. Maximum value of300. - Proxy
Configuration DataSource Configuration Web Crawler Configuration Proxy Configuration - 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.htmlis"a.example.com"and the port is443, 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 []stringPatterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150. - Url
Inclusion []stringPatterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150.
- urls
Data
Source Configuration Web Crawler Configuration Urls - 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
100seed URLs and up to3sitemap 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 DataSource Configuration Web Crawler Configuration Authentication Configuration - 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.htmlis"a.example.com"and the port is443, the standard port for HTTPS. Detailed below. - crawl
Depth 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 of0. Maximum value of10. - max
Content DoubleSize Per Page In Mega Bytes - 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
50MB. Minimum value of1.0e-06. Maximum value of50. - max
Links IntegerPer Page - 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 of1. Maximum value of1000. - max
Urls IntegerPer Minute Crawl Rate - 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 of1. Maximum value of300. - proxy
Configuration DataSource Configuration Web Crawler Configuration Proxy Configuration - 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.htmlis"a.example.com"and the port is443, 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 List<String>Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150. - url
Inclusion List<String>Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150.
- urls
Data
Source Configuration Web Crawler Configuration Urls - 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
100seed URLs and up to3sitemap 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 DataSource Configuration Web Crawler Configuration Authentication Configuration - 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.htmlis"a.example.com"and the port is443, the standard port for HTTPS. Detailed below. - crawl
Depth 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 of0. Maximum value of10. - max
Content numberSize Per Page In Mega Bytes - 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
50MB. Minimum value of1.0e-06. Maximum value of50. - max
Links numberPer Page - 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 of1. Maximum value of1000. - max
Urls numberPer Minute Crawl Rate - 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 of1. Maximum value of300. - proxy
Configuration DataSource Configuration Web Crawler Configuration Proxy Configuration - 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.htmlis"a.example.com"and the port is443, 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 string[]Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150. - url
Inclusion string[]Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150.
- urls
Data
Source Configuration Web Crawler Configuration Urls - 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
100seed URLs and up to3sitemap 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 DataSource Configuration Web Crawler Configuration Authentication Configuration - 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.htmlis"a.example.com"and the port is443, 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 of0. Maximum value of10. - max_
content_ floatsize_ per_ page_ in_ mega_ bytes - 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
50MB. Minimum value of1.0e-06. Maximum value of50. - max_
links_ intper_ page - 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 of1. Maximum value of1000. - max_
urls_ intper_ minute_ crawl_ rate - 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 of1. Maximum value of300. - proxy_
configuration DataSource Configuration Web Crawler Configuration Proxy Configuration - 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.htmlis"a.example.com"and the port is443, 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_ Sequence[str]patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150. - url_
inclusion_ Sequence[str]patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150.
- 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
100seed URLs and up to3sitemap 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 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.htmlis"a.example.com"and the port is443, the standard port for HTTPS. Detailed below. - crawl
Depth 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 of0. Maximum value of10. - max
Content NumberSize Per Page In Mega Bytes - 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
50MB. Minimum value of1.0e-06. Maximum value of50. - max
Links NumberPer Page - 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 of1. Maximum value of1000. - max
Urls NumberPer Minute Crawl Rate - 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 of1. Maximum value of300. - proxy
Configuration 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.htmlis"a.example.com"and the port is443, 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 List<String>Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150. - url
Inclusion List<String>Patterns - 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
0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of150.
DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfiguration, DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationArgs
- Basic
Authentications List<DataSource Configuration Web Crawler Configuration Authentication Configuration Basic Authentication> - 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 []DataSource Configuration Web Crawler Configuration Authentication Configuration Basic Authentication - 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 List<DataSource Configuration Web Crawler Configuration Authentication Configuration Basic Authentication> - 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 DataSource Configuration Web Crawler Configuration Authentication Configuration Basic Authentication[] - 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[DataSource Configuration Web Crawler Configuration Authentication Configuration Basic Authentication] - 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 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, DataSourceConfigurationWebCrawlerConfigurationAuthenticationConfigurationBasicAuthenticationArgs
- 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, the standard port for HTTPS.
DataSourceConfigurationWebCrawlerConfigurationProxyConfiguration, DataSourceConfigurationWebCrawlerConfigurationProxyConfigurationArgs
- 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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.htmlis"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.htmlis443, 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, DataSourceConfigurationWebCrawlerConfigurationUrlsArgs
- Seed
Url DataConfiguration Source Configuration Web Crawler Configuration Urls Seed Url Configuration - 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
100seed URLs. Detailed below. - Site
Maps DataConfiguration Source Configuration Web Crawler Configuration Urls Site Maps Configuration - 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
3sitemap URLs. Detailed below.
- Seed
Url DataConfiguration Source Configuration Web Crawler Configuration Urls Seed Url Configuration - 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
100seed URLs. Detailed below. - Site
Maps DataConfiguration Source Configuration Web Crawler Configuration Urls Site Maps Configuration - 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
3sitemap URLs. Detailed below.
- seed
Url DataConfiguration Source Configuration Web Crawler Configuration Urls Seed Url Configuration - 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
100seed URLs. Detailed below. - site
Maps DataConfiguration Source Configuration Web Crawler Configuration Urls Site Maps Configuration - 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
3sitemap URLs. Detailed below.
- seed
Url DataConfiguration Source Configuration Web Crawler Configuration Urls Seed Url Configuration - 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
100seed URLs. Detailed below. - site
Maps DataConfiguration Source Configuration Web Crawler Configuration Urls Site Maps Configuration - 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
3sitemap URLs. Detailed below.
- seed_
url_ Dataconfiguration Source Configuration Web Crawler Configuration Urls Seed Url Configuration - 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
100seed URLs. Detailed below. - site_
maps_ Dataconfiguration Source Configuration Web Crawler Configuration Urls Site Maps Configuration - 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
3sitemap URLs. Detailed below.
- seed
Url Property MapConfiguration - 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
100seed URLs. Detailed below. - site
Maps Property MapConfiguration - 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
3sitemap URLs. Detailed below.
DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfiguration, DataSourceConfigurationWebCrawlerConfigurationUrlsSeedUrlConfigurationArgs
- Seed
Urls List<string> - The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of
100seed URLs. Array Members: Minimum number of0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of2048. - Web
Crawler stringMode - The default mode is set to
HOST_ONLY. You can choose one of the following modes:HOST_ONLY– crawl only the website host names. For example, if the seed URL is"abc.example.com", then only URLs with host name"abc.example.com"are crawled.SUBDOMAINS– crawl the website host names with subdomains. For example, if the seed URL is"abc.example.com", then"a.abc.example.com"and"b.abc.example.com"are also crawled.EVERYTHING– crawl the website host names with subdomains and other domains that the webpages link to.
- Seed
Urls []string - The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of
100seed URLs. Array Members: Minimum number of0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of2048. - Web
Crawler stringMode - The default mode is set to
HOST_ONLY. You can choose one of the following modes:HOST_ONLY– crawl only the website host names. For example, if the seed URL is"abc.example.com", then only URLs with host name"abc.example.com"are crawled.SUBDOMAINS– crawl the website host names with subdomains. For example, if the seed URL is"abc.example.com", then"a.abc.example.com"and"b.abc.example.com"are also crawled.EVERYTHING– crawl the website host names with subdomains and other domains that the webpages link to.
- seed
Urls List<String> - The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of
100seed URLs. Array Members: Minimum number of0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of2048. - web
Crawler StringMode - The default mode is set to
HOST_ONLY. You can choose one of the following modes:HOST_ONLY– crawl only the website host names. For example, if the seed URL is"abc.example.com", then only URLs with host name"abc.example.com"are crawled.SUBDOMAINS– crawl the website host names with subdomains. For example, if the seed URL is"abc.example.com", then"a.abc.example.com"and"b.abc.example.com"are also crawled.EVERYTHING– crawl the website host names with subdomains and other domains that the webpages link to.
- seed
Urls string[] - The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of
100seed URLs. Array Members: Minimum number of0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of2048. - web
Crawler stringMode - The default mode is set to
HOST_ONLY. You can choose one of the following modes:HOST_ONLY– crawl only the website host names. For example, if the seed URL is"abc.example.com", then only URLs with host name"abc.example.com"are crawled.SUBDOMAINS– crawl the website host names with subdomains. For example, if the seed URL is"abc.example.com", then"a.abc.example.com"and"b.abc.example.com"are also crawled.EVERYTHING– crawl the website host names with subdomains and other domains that the webpages link to.
- 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
100seed URLs. Array Members: Minimum number of0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of2048. - web_
crawler_ strmode - The default mode is set to
HOST_ONLY. You can choose one of the following modes:HOST_ONLY– crawl only the website host names. For example, if the seed URL is"abc.example.com", then only URLs with host name"abc.example.com"are crawled.SUBDOMAINS– crawl the website host names with subdomains. For example, if the seed URL is"abc.example.com", then"a.abc.example.com"and"b.abc.example.com"are also crawled.EVERYTHING– crawl the website host names with subdomains and other domains that the webpages link to.
- seed
Urls List<String> - The list of seed or starting point URLs of the websites you want to crawl. The list can include a maximum of
100seed URLs. Array Members: Minimum number of0items. Maximum number of100items. Length Constraints: Minimum length of1. Maximum length of2048. - web
Crawler StringMode - The default mode is set to
HOST_ONLY. You can choose one of the following modes:HOST_ONLY– crawl only the website host names. For example, if the seed URL is"abc.example.com", then only URLs with host name"abc.example.com"are crawled.SUBDOMAINS– crawl the website host names with subdomains. For example, if the seed URL is"abc.example.com", then"a.abc.example.com"and"b.abc.example.com"are also crawled.EVERYTHING– crawl the website host names with subdomains and other domains that the webpages link to.
DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfiguration, DataSourceConfigurationWebCrawlerConfigurationUrlsSiteMapsConfigurationArgs
- Site
Maps List<string> - The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of
3sitemap URLs.
- Site
Maps []string - The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of
3sitemap URLs.
- site
Maps List<String> - The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of
3sitemap URLs.
- site
Maps string[] - The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of
3sitemap URLs.
- site_
maps Sequence[str] - The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of
3sitemap URLs.
- site
Maps List<String> - The list of sitemap URLs of the websites you want to crawl. The list can include a maximum of
3sitemap URLs.
DataSourceCustomDocumentEnrichmentConfiguration, DataSourceCustomDocumentEnrichmentConfigurationArgs
- Inline
Configurations List<DataSource Custom Document Enrichment Configuration Inline Configuration> - Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of
0items. Maximum number of100items. Detailed below. - Post
Extraction DataHook Configuration Source Custom Document Enrichment Configuration Post Extraction Hook Configuration - 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 DataHook Configuration Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration - 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 string - The Amazon Resource Name (ARN) of a role with permission to run
pre_extraction_hook_configurationandpost_extraction_hook_configurationfor altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.
- Inline
Configurations []DataSource Custom Document Enrichment Configuration Inline Configuration - Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of
0items. Maximum number of100items. Detailed below. - Post
Extraction DataHook Configuration Source Custom Document Enrichment Configuration Post Extraction Hook Configuration - 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 DataHook Configuration Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration - 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 string - The Amazon Resource Name (ARN) of a role with permission to run
pre_extraction_hook_configurationandpost_extraction_hook_configurationfor altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.
- inline
Configurations List<DataSource Custom Document Enrichment Configuration Inline Configuration> - Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of
0items. Maximum number of100items. Detailed below. - post
Extraction DataHook Configuration Source Custom Document Enrichment Configuration Post Extraction Hook Configuration - 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 DataHook Configuration Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration - 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 String - The Amazon Resource Name (ARN) of a role with permission to run
pre_extraction_hook_configurationandpost_extraction_hook_configurationfor altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.
- inline
Configurations DataSource Custom Document Enrichment Configuration Inline Configuration[] - Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of
0items. Maximum number of100items. Detailed below. - post
Extraction DataHook Configuration Source Custom Document Enrichment Configuration Post Extraction Hook Configuration - 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 DataHook Configuration Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration - 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 string - The Amazon Resource Name (ARN) of a role with permission to run
pre_extraction_hook_configurationandpost_extraction_hook_configurationfor altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.
- inline_
configurations Sequence[DataSource Custom Document Enrichment Configuration Inline Configuration] - Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of
0items. Maximum number of100items. Detailed below. - post_
extraction_ Datahook_ configuration Source Custom Document Enrichment Configuration Post Extraction Hook Configuration - 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_ Datahook_ configuration Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration - 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_configurationandpost_extraction_hook_configurationfor altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.
- inline
Configurations List<Property Map> - Configuration information to alter document attributes or metadata fields and content when ingesting documents into Amazon Kendra. Minimum number of
0items. Maximum number of100items. Detailed below. - post
Extraction Property MapHook Configuration - 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 Property MapHook Configuration - 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 String - The Amazon Resource Name (ARN) of a role with permission to run
pre_extraction_hook_configurationandpost_extraction_hook_configurationfor altering document metadata and content during the document ingestion process. For more information, see IAM roles for Amazon Kendra.
DataSourceCustomDocumentEnrichmentConfigurationInlineConfiguration, DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationArgs
- Condition
Data
Source Custom Document Enrichment Configuration Inline Configuration Condition - Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See condition.
- Document
Content boolDeletion TRUEto delete content if the condition used for the target attribute is met.- Target
Data
Source Custom Document Enrichment Configuration Inline Configuration Target - Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.
- Condition
Data
Source Custom Document Enrichment Configuration Inline Configuration Condition - Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See condition.
- Document
Content boolDeletion TRUEto delete content if the condition used for the target attribute is met.- Target
Data
Source Custom Document Enrichment Configuration Inline Configuration Target - Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.
- condition
Data
Source Custom Document Enrichment Configuration Inline Configuration Condition - Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See condition.
- document
Content BooleanDeletion TRUEto delete content if the condition used for the target attribute is met.- target
Data
Source Custom Document Enrichment Configuration Inline Configuration Target - Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.
- condition
Data
Source Custom Document Enrichment Configuration Inline Configuration Condition - Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See condition.
- document
Content booleanDeletion TRUEto delete content if the condition used for the target attribute is met.- target
Data
Source Custom Document Enrichment Configuration Inline Configuration Target - Configuration of the target document attribute or metadata field when ingesting documents into Amazon Kendra. You can also include a value. Detailed below.
- condition
Data
Source Custom Document Enrichment Configuration Inline Configuration Condition - Configuration of the condition used for the target document attribute or metadata field when ingesting documents into Amazon Kendra. See condition.
- document_
content_ booldeletion TRUEto delete content if the condition used for the target attribute is met.- target
Data
Source Custom Document Enrichment Configuration Inline Configuration Target - 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 condition.
- document
Content BooleanDeletion TRUEto 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, DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionArgs
- Condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - Operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - Condition
On DataValue Source Custom Document Enrichment Configuration Inline Configuration Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- Condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - Operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - Condition
On DataValue Source Custom Document Enrichment Configuration Inline Configuration Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document StringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator String
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On DataValue Source Custom Document Enrichment Configuration Inline Configuration Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On DataValue Source Custom Document Enrichment Configuration Inline Configuration Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition_
document_ strattribute_ key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator str
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition_
on_ Datavalue Source Custom Document Enrichment Configuration Inline Configuration Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document StringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator String
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On Property MapValue - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValue, DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationConditionConditionOnValueArgs
- Date
Value 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. - Long
Value int - A long integer value.
- String
List List<string>Values - A list of strings.
- String
Value string
- Date
Value 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. - Long
Value int - A long integer value.
- String
List []stringValues - A list of strings.
- String
Value string
- date
Value 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. - long
Value Integer - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
- date
Value 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. - long
Value number - A long integer value.
- string
List string[]Values - A list of strings.
- string
Value 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_ Sequence[str]values - A list of strings.
- string_
value str
- date
Value 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. - long
Value Number - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTarget, DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetArgs
- Target
Document stringAttribute Key - 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 DataAttribute Value Source Custom Document Enrichment Configuration Inline Configuration Target Target Document Attribute Value - 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 target_document_attribute_value.
- Target
Document boolAttribute Value Deletion TRUEto delete the existing target value for your specified target attribute key. You cannot create a target value and set this toTRUE. To create a target value (TargetDocumentAttributeValue), set this toFALSE.
- Target
Document stringAttribute Key - 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 DataAttribute Value Source Custom Document Enrichment Configuration Inline Configuration Target Target Document Attribute Value - 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 target_document_attribute_value.
- Target
Document boolAttribute Value Deletion TRUEto delete the existing target value for your specified target attribute key. You cannot create a target value and set this toTRUE. To create a target value (TargetDocumentAttributeValue), set this toFALSE.
- target
Document StringAttribute Key - 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 DataAttribute Value Source Custom Document Enrichment Configuration Inline Configuration Target Target Document Attribute Value - 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 target_document_attribute_value.
- target
Document BooleanAttribute Value Deletion TRUEto delete the existing target value for your specified target attribute key. You cannot create a target value and set this toTRUE. To create a target value (TargetDocumentAttributeValue), set this toFALSE.
- target
Document stringAttribute Key - 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 DataAttribute Value Source Custom Document Enrichment Configuration Inline Configuration Target Target Document Attribute Value - 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 target_document_attribute_value.
- target
Document booleanAttribute Value Deletion TRUEto delete the existing target value for your specified target attribute key. You cannot create a target value and set this toTRUE. To create a target value (TargetDocumentAttributeValue), set this toFALSE.
- target_
document_ strattribute_ key - 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_ Dataattribute_ value Source Custom Document Enrichment Configuration Inline Configuration Target Target Document Attribute Value - 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 target_document_attribute_value.
- target_
document_ boolattribute_ value_ deletion TRUEto delete the existing target value for your specified target attribute key. You cannot create a target value and set this toTRUE. To create a target value (TargetDocumentAttributeValue), set this toFALSE.
- target
Document StringAttribute Key - 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 Property MapAttribute Value - 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 target_document_attribute_value.
- target
Document BooleanAttribute Value Deletion TRUEto delete the existing target value for your specified target attribute key. You cannot create a target value and set this toTRUE. To create a target value (TargetDocumentAttributeValue), set this toFALSE.
DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValue, DataSourceCustomDocumentEnrichmentConfigurationInlineConfigurationTargetTargetDocumentAttributeValueArgs
- Date
Value 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. - Long
Value int - A long integer value.
- String
List List<string>Values - A list of strings.
- String
Value string
- Date
Value 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. - Long
Value int - A long integer value.
- String
List []stringValues - A list of strings.
- String
Value string
- date
Value 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. - long
Value Integer - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
- date
Value 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. - long
Value number - A long integer value.
- string
List string[]Values - A list of strings.
- string
Value 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_ Sequence[str]values - A list of strings.
- string_
value str
- date
Value 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. - long
Value Number - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfiguration, DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationArgs
- Lambda
Arn 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.
- Invocation
Condition DataSource Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- Lambda
Arn 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.
- Invocation
Condition DataSource Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- lambda
Arn 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.
- invocation
Condition DataSource Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- lambda
Arn 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.
- invocation
Condition DataSource Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition - 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 invocation_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 DataSource Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- lambda
Arn 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.
- invocation
Condition 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 invocation_condition.
DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationCondition, DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionArgs
- Condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - Operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - Condition
On DataValue Source Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- Condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - Operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - Condition
On DataValue Source Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document StringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator String
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On DataValue Source Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On DataValue Source Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition_
document_ strattribute_ key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator str
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition_
on_ Datavalue Source Custom Document Enrichment Configuration Post Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document StringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator String
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On Property MapValue - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValue, DataSourceCustomDocumentEnrichmentConfigurationPostExtractionHookConfigurationInvocationConditionConditionOnValueArgs
- Date
Value 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. - Long
Value int - A long integer value.
- String
List List<string>Values - A list of strings.
- String
Value string
- Date
Value 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. - Long
Value int - A long integer value.
- String
List []stringValues - A list of strings.
- String
Value string
- date
Value 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. - long
Value Integer - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
- date
Value 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. - long
Value number - A long integer value.
- string
List string[]Values - A list of strings.
- string
Value 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_ Sequence[str]values - A list of strings.
- string_
value str
- date
Value 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. - long
Value Number - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfiguration, DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationArgs
- Lambda
Arn 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.
- Invocation
Condition DataSource Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- Lambda
Arn 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.
- Invocation
Condition DataSource Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- lambda
Arn 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.
- invocation
Condition DataSource Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- lambda
Arn 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.
- invocation
Condition DataSource Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition - 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 invocation_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 DataSource Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition - 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 invocation_condition.
- lambda
Arn 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.
- invocation
Condition 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 invocation_condition.
DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationCondition, DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionArgs
- Condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - Operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - Condition
On DataValue Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- Condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - Operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - Condition
On DataValue Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document StringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator String
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On DataValue Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document stringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator string
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On DataValue Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition_
document_ strattribute_ key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator str
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition_
on_ Datavalue Source Custom Document Enrichment Configuration Pre Extraction Hook Configuration Invocation Condition Condition On Value - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
- condition
Document StringAttribute Key - The identifier of the document attribute used for the condition. For example,
_source_uricould be an identifier for the attribute or metadata field that contains source URIs associated with the documents. Amazon Kendra currently does not support_document_bodyas an attribute key used for the condition. - operator String
- The condition operator. For example, you can use
Containsto partially match a string. Valid Values:GreaterThan|GreaterThanOrEquals|LessThan|LessThanOrEquals|Equals|NotEquals|Contains|NotContains|Exists|NotExists|BeginsWith. - condition
On Property MapValue - The value used by the operator. For example, you can specify the value 'financial' for strings in the
_source_urifield that partially match or contain this value. See condition_on_value.
DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValue, DataSourceCustomDocumentEnrichmentConfigurationPreExtractionHookConfigurationInvocationConditionConditionOnValueArgs
- Date
Value 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. - Long
Value int - A long integer value.
- String
List List<string>Values - A list of strings.
- String
Value string
- Date
Value 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. - Long
Value int - A long integer value.
- String
List []stringValues - A list of strings.
- String
Value string
- date
Value 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. - long
Value Integer - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
- date
Value 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. - long
Value number - A long integer value.
- string
List string[]Values - A list of strings.
- string
Value 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_ Sequence[str]values - A list of strings.
- string_
value str
- date
Value 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. - long
Value Number - A long integer value.
- string
List List<String>Values - A list of strings.
- string
Value String
Import
Using pulumi import, import Kendra Data Source using the unique identifiers of the data_source and index separated by a slash (/). For example:
$ pulumi import aws:kendra/dataSource:DataSource example 1045d08d-66ef-4882-b3ed-dfb7df183e90/b34dfdf7-1f2b-4704-9581-79e00296845f
To learn more about importing existing cloud resources, see Importing resources.
Package Details
- Repository
- AWS Classic pulumi/pulumi-aws
- License
- Apache-2.0
- Notes
- This Pulumi package is based on the
awsTerraform Provider.