Membuat sumber Amazon S3 data

aws kendra create-data-source \
 --index-id index ID \
 --name example-data-source \
 --type S3 \
 --configuration '{"S3Configuration":{"BucketName":"bucket name"}}' 
 --role-arn 'arn:aws:iam::account id:role:/role name

Cuplikan kode Python berikut menciptakan sumber data. Amazon S3 Untuk contoh lengkap, lihat Memulai (AWS SDK for Python (Boto3)).

print("Create an Amazon S3 data source.")
    
    # Provide a name for the data source
    name = "getting-started-data-source"
    # Provide an optional description for the data source
    description = "Getting started data source."
    # Provide the IAM role ARN required for data sources
    role_arn = "arn:aws:iam::${accountID}:role/${roleName}"
    # Provide the data soource connection information
    s3_bucket_name = "S3-bucket-name"
    type = "S3"
    # Configure the data source
    configuration = {"S3DataSourceConfiguration":
        {
            "BucketName": s3_bucket_name
        }
    }

    data_source_response = kendra.create_data_source(
        Configuration = configuration,
        Name = name,
        Description = description,
        RoleArn = role_arn,
        Type = type,
        IndexId = index_id
    )

aws kendra describe-data-source \
 --index-id index ID \
 --id data source ID

Cuplikan kode Python berikut ini mendapatkan informasi tentang sumber data S3. Untuk contoh lengkap, lihat Memulai (AWS SDK for Python (Boto3)).

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

    while True:
        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

aws kendra start-data-source-sync-job \
 --index-id index ID \
 --id data source ID

Cuplikan kode Python berikut menyinkronkan sumber data. Amazon S3 Untuk contoh lengkap, lihat Memulai (AWS SDK for Python (Boto3)).

print("Synchronize the data source.")

    sync_response = kendra.start_data_source_sync_job(
        Id = "data-source-id",
        IndexId = "index-id"
    )