수집 중에 문서 보강

고객 식별 번호를 제거하도록 기본 데이터 조작을 구성하려면

aws kendra create-data-source \
 --name data-source-name \
 --index-id index-id \
 --role-arn arn:aws:iam::account-id:role/role-name \
 --type S3 \
 --configuration '{"S3Configuration":{"BucketName":"S3-bucket-name"}}' \
 --custom-document-enrichment-configuration '{"InlineConfigurations":[{"Target":{"TargetDocumentAttributeKey":"Customer_ID", "TargetDocumentAttributeValueDeletion": true}}]}' 

고객 식별 번호를 제거하도록 기본 데이터 조작을 구성하려면

import boto3
from botocore.exceptions import ClientError
import pprint
import time

kendra = boto3.client("kendra")

print("Create a data source with customizations")

# Provide the name of the data source
name = "data-source-name"
# Provide the index ID for the data source
index_id = "index-id"
# Provide the IAM role ARN required for data sources
role_arn = "arn:aws:iam::${account-id}:role/${role-name}"
# Provide the data source connection information
data_source_type = "S3"
S3_bucket_name = "S3-bucket-name"
# Configure the data source with Custom Document Enrichment
configuration = {"S3Configuration":
        {
            "BucketName": S3_bucket_name
        }
    }
custom_document_enrichment_configuration = {"InlineConfigurations":[
        {
            "Target":{"TargetDocumentAttributeKey":"Customer_ID",
                       "TargetDocumentAttributeValueDeletion": True}
        }]
    }

try:
    data_source_response = kendra.create_data_source(
        Name = name,
        IndexId = index_id,
        RoleArn = role_arn,
        Type = data_source_type
        Configuration = configuration
        CustomDocumentEnrichmentConfiguration = custom_document_enrichment_configuration
    )

    pprint.pprint(data_source_response)

    data_source_id = data_source_response["Id"]

    print("Wait for Amazon Kendra to create the data source with your customizations.")

    while True:
        # Get the details of the data source, such as the status
        data_source_description = kendra.describe_data_source(
            Id = data_source_id,
            IndexId = index_id
        )
        status = data_source_description["Status"]
        print(" Creating data source. Status: "+status)
        time.sleep(60)
        if status != "CREATING":
            break

    print("Synchronize the data source.")

    sync_response = kendra.start_data_source_sync_job(
        Id = data_source_id,
        IndexId = index_id
    )

    pprint.pprint(sync_response)

    print("Wait for the data source to sync with the index.")

    while True:

        jobs = kendra.list_data_source_sync_jobs(
            Id= data_source_id,
            IndexId= index_id
        )

        # For this example, there should be one job
        status = jobs["History"][0]["Status"]

        print(" Syncing data source. Status: "+status)
        time.sleep(60)
        if status != "SYNCING":
            break

except  ClientError as e:
        print("%s" % e)

print("Program ends.")

고객 식별 번호를 제거하도록 기본 데이터 조작을 구성하려면

package com.amazonaws.kendra;

import java.util.concurrent.TimeUnit;
import software.amazon.awssdk.services.kendra.KendraClient;
import software.amazon.awssdk.services.kendra.model.CreateDataSourceRequest;
import software.amazon.awssdk.services.kendra.model.CreateDataSourceResponse;
import software.amazon.awssdk.services.kendra.model.CreateIndexRequest;
import software.amazon.awssdk.services.kendra.model.CreateIndexResponse;
import software.amazon.awssdk.services.kendra.model.DataSourceConfiguration;
import software.amazon.awssdk.services.kendra.model.DataSourceStatus;
import software.amazon.awssdk.services.kendra.model.DataSourceSyncJob;
import software.amazon.awssdk.services.kendra.model.DataSourceSyncJobStatus;
import software.amazon.awssdk.services.kendra.model.DataSourceType;
import software.amazon.awssdk.services.kendra.model.DescribeDataSourceRequest;
import software.amazon.awssdk.services.kendra.model.DescribeDataSourceResponse;
import software.amazon.awssdk.services.kendra.model.DescribeIndexRequest;
import software.amazon.awssdk.services.kendra.model.DescribeIndexResponse;
import software.amazon.awssdk.services.kendra.model.IndexStatus;
import software.amazon.awssdk.services.kendra.model.ListDataSourceSyncJobsRequest;
import software.amazon.awssdk.services.kendra.model.ListDataSourceSyncJobsResponse;
import software.amazon.awssdk.services.kendra.model.S3DataSourceConfiguration;
import software.amazon.awssdk.services.kendra.model.StartDataSourceSyncJobRequest;
import software.amazon.awssdk.services.kendra.model.StartDataSourceSyncJobResponse;

public class CreateDataSourceWithCustomizationsExample {

    public static void main(String[] args) throws InterruptedException {
        System.out.println("Create a data source with customizations");
        
        String dataSourceName = "data-source-name";
        String indexId = "index-id";
        String dataSourceRoleArn = "arn:aws:iam::account-id:role/role-name";
        String s3BucketName = "S3-bucket-name"

        KendraClient kendra = KendraClient.builder().build();
        
        CreateDataSourceRequest createDataSourceRequest = CreateDataSourceRequest
            .builder()
            .name(dataSourceName)
            .description(experienceDescription)
            .roleArn(experienceRoleArn)
            .type(DataSourceType.S3)
            .configuration(
                DataSourceConfiguration
                    .builder()
                    .s3Configuration(
                        S3DataSourceConfiguration
                            .builder()
                            .bucketName(s3BucketName)
                            .build()
                    ).build()
            )
            .customDocumentEnrichmentConfiguration(
                CustomDocumentEnrichmentConfiguration
                    .builder()
                    .inlineConfigurations(Arrays.asList(
                        InlineCustomDocumentEnrichmentConfiguration
                            .builder()
                            .target(
                                DocumentAttributeTarget
                                    .builder()
                                    .targetDocumentAttributeKey("Customer_ID")
                                    .targetDocumentAttributeValueDeletion(true)
                                    .build())
                            .build()
                    )).build();
        
        CreateDataSourceResponse createDataSourceResponse = kendra.createDataSource(createDataSourceRequest);
        System.out.println(String.format("Response of creating data source: %s", createDataSourceResponse));

        String dataSourceId = createDataSourceResponse.id();
        System.out.println(String.format("Waiting for Kendra to create the data source %s", dataSourceId));
        DescribeDataSourceRequest describeDataSourceRequest = DescribeDataSourceRequest
            .builder()
            .indexId(indexId)
            .id(dataSourceId)
            .build();

        while (true) {
            DescribeDataSourceResponse describeDataSourceResponse = kendra.describeDataSource(describeDataSourceRequest);

            DataSourceStatus status = describeDataSourceResponse.status();
            System.out.println(String.format("Creating data source. Status: %s", status));
            TimeUnit.SECONDS.sleep(60);
            if (status != DataSourceStatus.CREATING) {
                break;
            }
        }

        System.out.println(String.format("Synchronize the data source %s", dataSourceId));
        StartDataSourceSyncJobRequest startDataSourceSyncJobRequest = StartDataSourceSyncJobRequest
            .builder()
            .indexId(indexId)
            .id(dataSourceId)
            .build();
        StartDataSourceSyncJobResponse startDataSourceSyncJobResponse = kendra.startDataSourceSyncJob(startDataSourceSyncJobRequest);
        System.out.println(String.format("Waiting for the data source to sync with the index %s for execution ID %s", indexId, startDataSourceSyncJobResponse.executionId()));

        // For this example, there should be one job
        ListDataSourceSyncJobsRequest listDataSourceSyncJobsRequest = ListDataSourceSyncJobsRequest
            .builder()
            .indexId(indexId)
            .id(dataSourceId)
            .build();

        while (true) {
            ListDataSourceSyncJobsResponse listDataSourceSyncJobsResponse = kendra.listDataSourceSyncJobs(listDataSourceSyncJobsRequest);
            DataSourceSyncJob job = listDataSourceSyncJobsResponse.history().get(0);
            System.out.println(String.format("Syncing data source. Status: %s", job.status()));

            TimeUnit.SECONDS.sleep(60);
            if (job.status() != DataSourceSyncJobStatus.SYNCING) {
                break;
            }

        }

        System.out.println("Data source creation with customizations is complete");
    }
}

원시, 원본 데이터에 대한 고급 데이터 조작을 위해 Lambda 함수를 구성하려면

aws kendra create-data-source \
 --name data-source-name \
 --index-id index-id \
 --role-arn arn:aws:iam::account-id:role/role-name \
 --type S3 \
 --configuration '{"S3Configuration":{"BucketName":"S3-bucket-name"}}' \
 --custom-document-enrichment-configuration '{"PreExtractionHookConfiguration":{"LambdaArn":"arn:aws:iam::account-id:function/function-name", "S3Bucket":"S3-bucket-name"}, "RoleArn": "arn:aws:iam:account-id:role/cde-role-name"}'

원시, 원본 데이터에 대한 고급 데이터 조작을 위해 Lambda 함수를 구성하려면

import boto3
from botocore.exceptions import ClientError
import pprint
import time

kendra = boto3.client("kendra")

print("Create a data source with customizations.")

# Provide the name of the data source
name = "data-source-name"
# Provide the index ID for the data source
index_id = "index-id"
# Provide the IAM role ARN required for data sources
role_arn = "arn:aws:iam::${account-id}:role/${role-name}"
# Provide the data source connection information
data_source_type = "S3"
S3_bucket_name = "S3-bucket-name"
# Configure the data source with Custom Document Enrichment
configuration = {"S3Configuration":
        {
            "BucketName": S3_bucket_name
        }
    }
custom_document_enrichment_configuration = {"PreExtractionHookConfiguration":
        {
            "LambdaArn":"arn:aws:iam::account-id:function/function-name",
            "S3Bucket":"S3-bucket-name"
        }
    "RoleArn":"arn:aws:iam::account-id:role/cde-role-name"
    }

try:
    data_source_response = kendra.create_data_source(
        Name = name,
        IndexId = index_id,
        RoleArn = role_arn,
        Type = data_source_type
        Configuration = configuration
        CustomDocumentEnrichmentConfiguration = custom_document_enrichment_configuration
    )

    pprint.pprint(data_source_response)

    data_source_id = data_source_response["Id"]

    print("Wait for Amazon Kendra to create the data source with your customizations.")

    while True:
        # Get the details of the data source, such as the status
        data_source_description = kendra.describe_data_source(
            Id = data_source_id,
            IndexId = index_id
        )
        status = data_source_description["Status"]
        print(" Creating data source. Status: "+status)
        time.sleep(60)
        if status != "CREATING":
            break

    print("Synchronize the data source.")

    sync_response = kendra.start_data_source_sync_job(
        Id = data_source_id,
        IndexId = index_id
    )

    pprint.pprint(sync_response)

    print("Wait for the data source to sync with the index.")

    while True:

        jobs = kendra.list_data_source_sync_jobs(
            Id = data_source_id,
            IndexId = index_id
        )

        # For this example, there should be one job
        status = jobs["History"][0]["Status"]

        print(" Syncing data source. Status: "+status)
        time.sleep(60)
        if status != "SYNCING":
            break

except  ClientError as e:
        print("%s" % e)

print("Program ends.")

원시, 원본 데이터에 대한 고급 데이터 조작을 위해 Lambda 함수를 구성하려면

package com.amazonaws.kendra;

import java.util.concurrent.TimeUnit;
import software.amazon.awssdk.services.kendra.KendraClient;
import software.amazon.awssdk.services.kendra.model.CreateDataSourceRequest;
import software.amazon.awssdk.services.kendra.model.CreateDataSourceResponse;
import software.amazon.awssdk.services.kendra.model.CreateIndexRequest;
import software.amazon.awssdk.services.kendra.model.CreateIndexResponse;
import software.amazon.awssdk.services.kendra.model.DataSourceConfiguration;
import software.amazon.awssdk.services.kendra.model.DataSourceStatus;
import software.amazon.awssdk.services.kendra.model.DataSourceSyncJob;
import software.amazon.awssdk.services.kendra.model.DataSourceSyncJobStatus;
import software.amazon.awssdk.services.kendra.model.DataSourceType;
import software.amazon.awssdk.services.kendra.model.DescribeDataSourceRequest;
import software.amazon.awssdk.services.kendra.model.DescribeDataSourceResponse;
import software.amazon.awssdk.services.kendra.model.DescribeIndexRequest;
import software.amazon.awssdk.services.kendra.model.DescribeIndexResponse;
import software.amazon.awssdk.services.kendra.model.IndexStatus;
import software.amazon.awssdk.services.kendra.model.ListDataSourceSyncJobsRequest;
import software.amazon.awssdk.services.kendra.model.ListDataSourceSyncJobsResponse;
import software.amazon.awssdk.services.kendra.model.S3DataSourceConfiguration;
import software.amazon.awssdk.services.kendra.model.StartDataSourceSyncJobRequest;
import software.amazon.awssdk.services.kendra.model.StartDataSourceSyncJobResponse;


public class CreateDataSourceWithCustomizationsExample {

    public static void main(String[] args) throws InterruptedException {
        System.out.println("Create a data source with customizations");
        
        String dataSourceName = "data-source-name";
        String indexId = "index-id";
        String dataSourceRoleArn = "arn:aws:iam::account-id:role/role-name";
        String s3BucketName = "S3-bucket-name"

        KendraClient kendra = KendraClient.builder().build();
        
        CreateDataSourceRequest createDataSourceRequest = CreateDataSourceRequest
            .builder()
            .name(dataSourceName)
            .description(experienceDescription)
            .roleArn(experienceRoleArn)
            .type(DataSourceType.S3)
            .configuration(
                DataSourceConfiguration
                    .builder()
                    .s3Configuration(
                        S3DataSourceConfiguration
                            .builder()
                            .bucketName(s3BucketName)
                            .build()
                    ).build()
            )
            .customDocumentEnrichmentConfiguration(
                CustomDocumentEnrichmentConfiguration
                    .builder()
                    .preExtractionHookConfiguration(
                        HookConfiguration
                            .builder()
                            .lambdaArn("arn:aws:iam::account-id:function/function-name")
                            .s3Bucket("S3-bucket-name")
                            .build())
                    .roleArn("arn:aws:iam::account-id:role/cde-role-name")
                    .build();
        
        CreateDataSourceResponse createDataSourceResponse = kendra.createDataSource(createDataSourceRequest);
        System.out.println(String.format("Response of creating data source: %s", createDataSourceResponse));

        String dataSourceId = createDataSourceResponse.id();
        System.out.println(String.format("Waiting for Kendra to create the data source %s", dataSourceId));
        DescribeDataSourceRequest describeDataSourceRequest = DescribeDataSourceRequest
            .builder()
            .indexId(indexId)
            .id(dataSourceId)
            .build();

        while (true) {
            DescribeDataSourceResponse describeDataSourceResponse = kendra.describeDataSource(describeDataSourceRequest);

            DataSourceStatus status = describeDataSourceResponse.status();
            System.out.println(String.format("Creating data source. Status: %s", status));
            TimeUnit.SECONDS.sleep(60);
            if (status != DataSourceStatus.CREATING) {
                break;
            }
        }

        System.out.println(String.format("Synchronize the data source %s", dataSourceId));
        StartDataSourceSyncJobRequest startDataSourceSyncJobRequest = StartDataSourceSyncJobRequest
            .builder()
            .indexId(indexId)
            .id(dataSourceId)
            .build();
        StartDataSourceSyncJobResponse startDataSourceSyncJobResponse = kendra.startDataSourceSyncJob(startDataSourceSyncJobRequest);
        System.out.println(String.format("Waiting for the data source to sync with the index %s for execution ID %s", indexId, startDataSourceSyncJobResponse.executionId()));

        // For this example, there should be one job
        ListDataSourceSyncJobsRequest listDataSourceSyncJobsRequest = ListDataSourceSyncJobsRequest
            .builder()
            .indexId(indexId)
            .id(dataSourceId)
            .build();

        while (true) {
            ListDataSourceSyncJobsResponse listDataSourceSyncJobsResponse = kendra.listDataSourceSyncJobs(listDataSourceSyncJobsRequest);
            DataSourceSyncJob job = listDataSourceSyncJobsResponse.history().get(0);
            System.out.println(String.format("Syncing data source. Status: %s", job.status()));

            TimeUnit.SECONDS.sleep(60);
            if (job.status() != DataSourceSyncJobStatus.SYNCING) {
                break;
            }

        }

        System.out.println("Data source creation with customizations is complete");
    }
}