AWS services or capabilities described in AWS Documentation may vary by region/location. Click Getting Started with Amazon AWS to see specific differences applicable to the China (Beijing) Region.

You are viewing documentation for version 2 of the AWS SDK for Ruby. Version 3 documentation can be found here.

Class: Aws::SageMaker::Types::EndpointInput

Inherits:
Struct
  • Object
show all
Defined in:
(unknown)

Overview

Note:

When passing EndpointInput as input to an Aws::Client method, you can use a vanilla Hash:

{
  endpoint_name: "EndpointName", # required
  local_path: "ProcessingLocalPath", # required
  s3_input_mode: "Pipe", # accepts Pipe, File
  s3_data_distribution_type: "FullyReplicated", # accepts FullyReplicated, ShardedByS3Key
}

Input object for the endpoint

Returned by:

Instance Attribute Summary collapse

Instance Attribute Details

#endpoint_nameString

An endpoint in customer\'s account which has enabled DataCaptureConfig enabled.

Returns:

  • (String)

    An endpoint in customer\'s account which has enabled DataCaptureConfig enabled.

#local_pathString

Path to the filesystem where the endpoint data is available to the container.

Returns:

  • (String)

    Path to the filesystem where the endpoint data is available to the container.

#s3_data_distribution_typeString

Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key. Defauts to FullyReplicated

Possible values:

  • FullyReplicated
  • ShardedByS3Key

Returns:

  • (String)

    Whether input data distributed in Amazon S3 is fully replicated or sharded by an S3 key.

#s3_input_modeString

Whether the Pipe or File is used as the input mode for transfering data for the monitoring job. Pipe mode is recommended for large datasets. File mode is useful for small files that fit in memory. Defaults to File.

Possible values:

  • Pipe
  • File

Returns:

  • (String)

    Whether the Pipe or File is used as the input mode for transfering data for the monitoring job.