AWS SDK for C++  1.9.130
AWS SDK for C++
Public Member Functions | List of all members
Aws::SageMaker::Model::ContainerDefinition Class Reference

#include <ContainerDefinition.h>

Public Member Functions

 ContainerDefinition ()
 
 ContainerDefinition (Aws::Utils::Json::JsonView jsonValue)
 
ContainerDefinitionoperator= (Aws::Utils::Json::JsonView jsonValue)
 
Aws::Utils::Json::JsonValue Jsonize () const
 
const Aws::StringGetContainerHostname () const
 
bool ContainerHostnameHasBeenSet () const
 
void SetContainerHostname (const Aws::String &value)
 
void SetContainerHostname (Aws::String &&value)
 
void SetContainerHostname (const char *value)
 
ContainerDefinitionWithContainerHostname (const Aws::String &value)
 
ContainerDefinitionWithContainerHostname (Aws::String &&value)
 
ContainerDefinitionWithContainerHostname (const char *value)
 
const Aws::StringGetImage () const
 
bool ImageHasBeenSet () const
 
void SetImage (const Aws::String &value)
 
void SetImage (Aws::String &&value)
 
void SetImage (const char *value)
 
ContainerDefinitionWithImage (const Aws::String &value)
 
ContainerDefinitionWithImage (Aws::String &&value)
 
ContainerDefinitionWithImage (const char *value)
 
const ImageConfigGetImageConfig () const
 
bool ImageConfigHasBeenSet () const
 
void SetImageConfig (const ImageConfig &value)
 
void SetImageConfig (ImageConfig &&value)
 
ContainerDefinitionWithImageConfig (const ImageConfig &value)
 
ContainerDefinitionWithImageConfig (ImageConfig &&value)
 
const ContainerModeGetMode () const
 
bool ModeHasBeenSet () const
 
void SetMode (const ContainerMode &value)
 
void SetMode (ContainerMode &&value)
 
ContainerDefinitionWithMode (const ContainerMode &value)
 
ContainerDefinitionWithMode (ContainerMode &&value)
 
const Aws::StringGetModelDataUrl () const
 
bool ModelDataUrlHasBeenSet () const
 
void SetModelDataUrl (const Aws::String &value)
 
void SetModelDataUrl (Aws::String &&value)
 
void SetModelDataUrl (const char *value)
 
ContainerDefinitionWithModelDataUrl (const Aws::String &value)
 
ContainerDefinitionWithModelDataUrl (Aws::String &&value)
 
ContainerDefinitionWithModelDataUrl (const char *value)
 
const Aws::Map< Aws::String, Aws::String > & GetEnvironment () const
 
bool EnvironmentHasBeenSet () const
 
void SetEnvironment (const Aws::Map< Aws::String, Aws::String > &value)
 
void SetEnvironment (Aws::Map< Aws::String, Aws::String > &&value)
 
ContainerDefinitionWithEnvironment (const Aws::Map< Aws::String, Aws::String > &value)
 
ContainerDefinitionWithEnvironment (Aws::Map< Aws::String, Aws::String > &&value)
 
ContainerDefinitionAddEnvironment (const Aws::String &key, const Aws::String &value)
 
ContainerDefinitionAddEnvironment (Aws::String &&key, const Aws::String &value)
 
ContainerDefinitionAddEnvironment (const Aws::String &key, Aws::String &&value)
 
ContainerDefinitionAddEnvironment (Aws::String &&key, Aws::String &&value)
 
ContainerDefinitionAddEnvironment (const char *key, Aws::String &&value)
 
ContainerDefinitionAddEnvironment (Aws::String &&key, const char *value)
 
ContainerDefinitionAddEnvironment (const char *key, const char *value)
 
const Aws::StringGetModelPackageName () const
 
bool ModelPackageNameHasBeenSet () const
 
void SetModelPackageName (const Aws::String &value)
 
void SetModelPackageName (Aws::String &&value)
 
void SetModelPackageName (const char *value)
 
ContainerDefinitionWithModelPackageName (const Aws::String &value)
 
ContainerDefinitionWithModelPackageName (Aws::String &&value)
 
ContainerDefinitionWithModelPackageName (const char *value)
 
const MultiModelConfigGetMultiModelConfig () const
 
bool MultiModelConfigHasBeenSet () const
 
void SetMultiModelConfig (const MultiModelConfig &value)
 
void SetMultiModelConfig (MultiModelConfig &&value)
 
ContainerDefinitionWithMultiModelConfig (const MultiModelConfig &value)
 
ContainerDefinitionWithMultiModelConfig (MultiModelConfig &&value)
 

Detailed Description

Describes the container, as part of model definition.

See Also:

AWS API Reference

Definition at line 36 of file ContainerDefinition.h.

Constructor & Destructor Documentation

◆ ContainerDefinition() [1/2]

Aws::SageMaker::Model::ContainerDefinition::ContainerDefinition ( )

◆ ContainerDefinition() [2/2]

Aws::SageMaker::Model::ContainerDefinition::ContainerDefinition ( Aws::Utils::Json::JsonView  jsonValue)

Member Function Documentation

◆ AddEnvironment() [1/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( Aws::String &&  key,
Aws::String &&  value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 642 of file ContainerDefinition.h.

◆ AddEnvironment() [2/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( Aws::String &&  key,
const Aws::String value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 628 of file ContainerDefinition.h.

◆ AddEnvironment() [3/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( Aws::String &&  key,
const char *  value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 656 of file ContainerDefinition.h.

◆ AddEnvironment() [4/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( const Aws::String key,
Aws::String &&  value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 635 of file ContainerDefinition.h.

◆ AddEnvironment() [5/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( const Aws::String key,
const Aws::String value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 621 of file ContainerDefinition.h.

◆ AddEnvironment() [6/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( const char *  key,
Aws::String &&  value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 649 of file ContainerDefinition.h.

◆ AddEnvironment() [7/7]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::AddEnvironment ( const char *  key,
const char *  value 
)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 663 of file ContainerDefinition.h.

◆ ContainerHostnameHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::ContainerHostnameHasBeenSet ( ) const
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 77 of file ContainerDefinition.h.

◆ EnvironmentHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::EnvironmentHasBeenSet ( ) const
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 586 of file ContainerDefinition.h.

◆ GetContainerHostname()

const Aws::String& Aws::SageMaker::Model::ContainerDefinition::GetContainerHostname ( ) const
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 60 of file ContainerDefinition.h.

◆ GetEnvironment()

const Aws::Map<Aws::String, Aws::String>& Aws::SageMaker::Model::ContainerDefinition::GetEnvironment ( ) const
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 579 of file ContainerDefinition.h.

◆ GetImage()

const Aws::String& Aws::SageMaker::Model::ContainerDefinition::GetImage ( ) const
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 194 of file ContainerDefinition.h.

◆ GetImageConfig()

const ImageConfig& Aws::SageMaker::Model::ContainerDefinition::GetImageConfig ( ) const
inline

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers

Definition at line 302 of file ContainerDefinition.h.

◆ GetMode()

const ContainerMode& Aws::SageMaker::Model::ContainerDefinition::GetMode ( ) const
inline

Whether the container hosts a single model or multiple models.

Definition at line 353 of file ContainerDefinition.h.

◆ GetModelDataUrl()

const Aws::String& Aws::SageMaker::Model::ContainerDefinition::GetModelDataUrl ( ) const
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 403 of file ContainerDefinition.h.

◆ GetModelPackageName()

const Aws::String& Aws::SageMaker::Model::ContainerDefinition::GetModelPackageName ( ) const
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 670 of file ContainerDefinition.h.

◆ GetMultiModelConfig()

const MultiModelConfig& Aws::SageMaker::Model::ContainerDefinition::GetMultiModelConfig ( ) const
inline

Specifies additional configuration for multi-model endpoints.

Definition at line 718 of file ContainerDefinition.h.

◆ ImageConfigHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::ImageConfigHasBeenSet ( ) const
inline

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers

Definition at line 311 of file ContainerDefinition.h.

◆ ImageHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::ImageHasBeenSet ( ) const
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 208 of file ContainerDefinition.h.

◆ Jsonize()

Aws::Utils::Json::JsonValue Aws::SageMaker::Model::ContainerDefinition::Jsonize ( ) const

◆ ModeHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::ModeHasBeenSet ( ) const
inline

Whether the container hosts a single model or multiple models.

Definition at line 358 of file ContainerDefinition.h.

◆ ModelDataUrlHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::ModelDataUrlHasBeenSet ( ) const
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 427 of file ContainerDefinition.h.

◆ ModelPackageNameHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::ModelPackageNameHasBeenSet ( ) const
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 676 of file ContainerDefinition.h.

◆ MultiModelConfigHasBeenSet()

bool Aws::SageMaker::Model::ContainerDefinition::MultiModelConfigHasBeenSet ( ) const
inline

Specifies additional configuration for multi-model endpoints.

Definition at line 723 of file ContainerDefinition.h.

◆ operator=()

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::operator= ( Aws::Utils::Json::JsonView  jsonValue)

◆ SetContainerHostname() [1/3]

void Aws::SageMaker::Model::ContainerDefinition::SetContainerHostname ( Aws::String &&  value)
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 111 of file ContainerDefinition.h.

◆ SetContainerHostname() [2/3]

void Aws::SageMaker::Model::ContainerDefinition::SetContainerHostname ( const Aws::String value)
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 94 of file ContainerDefinition.h.

◆ SetContainerHostname() [3/3]

void Aws::SageMaker::Model::ContainerDefinition::SetContainerHostname ( const char *  value)
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 128 of file ContainerDefinition.h.

◆ SetEnvironment() [1/2]

void Aws::SageMaker::Model::ContainerDefinition::SetEnvironment ( Aws::Map< Aws::String, Aws::String > &&  value)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 600 of file ContainerDefinition.h.

◆ SetEnvironment() [2/2]

void Aws::SageMaker::Model::ContainerDefinition::SetEnvironment ( const Aws::Map< Aws::String, Aws::String > &  value)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 593 of file ContainerDefinition.h.

◆ SetImage() [1/3]

void Aws::SageMaker::Model::ContainerDefinition::SetImage ( Aws::String &&  value)
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 236 of file ContainerDefinition.h.

◆ SetImage() [2/3]

void Aws::SageMaker::Model::ContainerDefinition::SetImage ( const Aws::String value)
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 222 of file ContainerDefinition.h.

◆ SetImage() [3/3]

void Aws::SageMaker::Model::ContainerDefinition::SetImage ( const char *  value)
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 250 of file ContainerDefinition.h.

◆ SetImageConfig() [1/2]

void Aws::SageMaker::Model::ContainerDefinition::SetImageConfig ( const ImageConfig value)
inline

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers

Definition at line 320 of file ContainerDefinition.h.

◆ SetImageConfig() [2/2]

void Aws::SageMaker::Model::ContainerDefinition::SetImageConfig ( ImageConfig &&  value)
inline

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers

Definition at line 329 of file ContainerDefinition.h.

◆ SetMode() [1/2]

void Aws::SageMaker::Model::ContainerDefinition::SetMode ( const ContainerMode value)
inline

Whether the container hosts a single model or multiple models.

Definition at line 363 of file ContainerDefinition.h.

◆ SetMode() [2/2]

void Aws::SageMaker::Model::ContainerDefinition::SetMode ( ContainerMode &&  value)
inline

Whether the container hosts a single model or multiple models.

Definition at line 368 of file ContainerDefinition.h.

◆ SetModelDataUrl() [1/3]

void Aws::SageMaker::Model::ContainerDefinition::SetModelDataUrl ( Aws::String &&  value)
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 475 of file ContainerDefinition.h.

◆ SetModelDataUrl() [2/3]

void Aws::SageMaker::Model::ContainerDefinition::SetModelDataUrl ( const Aws::String value)
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 451 of file ContainerDefinition.h.

◆ SetModelDataUrl() [3/3]

void Aws::SageMaker::Model::ContainerDefinition::SetModelDataUrl ( const char *  value)
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 499 of file ContainerDefinition.h.

◆ SetModelPackageName() [1/3]

void Aws::SageMaker::Model::ContainerDefinition::SetModelPackageName ( Aws::String &&  value)
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 688 of file ContainerDefinition.h.

◆ SetModelPackageName() [2/3]

void Aws::SageMaker::Model::ContainerDefinition::SetModelPackageName ( const Aws::String value)
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 682 of file ContainerDefinition.h.

◆ SetModelPackageName() [3/3]

void Aws::SageMaker::Model::ContainerDefinition::SetModelPackageName ( const char *  value)
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 694 of file ContainerDefinition.h.

◆ SetMultiModelConfig() [1/2]

void Aws::SageMaker::Model::ContainerDefinition::SetMultiModelConfig ( const MultiModelConfig value)
inline

Specifies additional configuration for multi-model endpoints.

Definition at line 728 of file ContainerDefinition.h.

◆ SetMultiModelConfig() [2/2]

void Aws::SageMaker::Model::ContainerDefinition::SetMultiModelConfig ( MultiModelConfig &&  value)
inline

Specifies additional configuration for multi-model endpoints.

Definition at line 733 of file ContainerDefinition.h.

◆ WithContainerHostname() [1/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithContainerHostname ( Aws::String &&  value)
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 162 of file ContainerDefinition.h.

◆ WithContainerHostname() [2/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithContainerHostname ( const Aws::String value)
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 145 of file ContainerDefinition.h.

◆ WithContainerHostname() [3/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithContainerHostname ( const char *  value)
inline

This parameter is ignored for models that contain only a PrimaryContainer.

When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.

Definition at line 179 of file ContainerDefinition.h.

◆ WithEnvironment() [1/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithEnvironment ( Aws::Map< Aws::String, Aws::String > &&  value)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 614 of file ContainerDefinition.h.

◆ WithEnvironment() [2/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithEnvironment ( const Aws::Map< Aws::String, Aws::String > &  value)
inline

The environment variables to set in the Docker container. Each key and value in the Environment string to string map can have length of up to

  1. We support up to 16 entries in the map.

Definition at line 607 of file ContainerDefinition.h.

◆ WithImage() [1/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithImage ( Aws::String &&  value)
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 278 of file ContainerDefinition.h.

◆ WithImage() [2/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithImage ( const Aws::String value)
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 264 of file ContainerDefinition.h.

◆ WithImage() [3/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithImage ( const char *  value)
inline

The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by Amazon SageMaker, the inference code must meet Amazon SageMaker requirements. Amazon SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker

Definition at line 292 of file ContainerDefinition.h.

◆ WithImageConfig() [1/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithImageConfig ( const ImageConfig value)
inline

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers

Definition at line 338 of file ContainerDefinition.h.

◆ WithImageConfig() [2/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithImageConfig ( ImageConfig &&  value)
inline

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers

Definition at line 347 of file ContainerDefinition.h.

◆ WithMode() [1/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithMode ( const ContainerMode value)
inline

Whether the container hosts a single model or multiple models.

Definition at line 373 of file ContainerDefinition.h.

◆ WithMode() [2/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithMode ( ContainerMode &&  value)
inline

Whether the container hosts a single model or multiple models.

Definition at line 378 of file ContainerDefinition.h.

◆ WithModelDataUrl() [1/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithModelDataUrl ( Aws::String &&  value)
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 547 of file ContainerDefinition.h.

◆ WithModelDataUrl() [2/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithModelDataUrl ( const Aws::String value)
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 523 of file ContainerDefinition.h.

◆ WithModelDataUrl() [3/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithModelDataUrl ( const char *  value)
inline

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for Amazon SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.

The model artifacts must be in an S3 bucket that is in the same region as the model or endpoint you are creating.

If you provide a value for this parameter, Amazon SageMaker uses Amazon Web Services Security Token Service to download model artifacts from the S3 path you provide. Amazon Web Services STS is activated in your IAM user account by default. If you previously deactivated Amazon Web Services STS for a region, you need to reactivate Amazon Web Services STS for that region. For more information, see Activating and Deactivating Amazon Web Services STS in an Amazon Web Services Region in the Amazon Web Services Identity and Access Management User Guide.

If you use a built-in algorithm to create a model, Amazon SageMaker requires that you provide a S3 path to the model artifacts in ModelDataUrl.

Definition at line 571 of file ContainerDefinition.h.

◆ WithModelPackageName() [1/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithModelPackageName ( Aws::String &&  value)
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 706 of file ContainerDefinition.h.

◆ WithModelPackageName() [2/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithModelPackageName ( const Aws::String value)
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 700 of file ContainerDefinition.h.

◆ WithModelPackageName() [3/3]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithModelPackageName ( const char *  value)
inline

The name or Amazon Resource Name (ARN) of the model package to use to create the model.

Definition at line 712 of file ContainerDefinition.h.

◆ WithMultiModelConfig() [1/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithMultiModelConfig ( const MultiModelConfig value)
inline

Specifies additional configuration for multi-model endpoints.

Definition at line 738 of file ContainerDefinition.h.

◆ WithMultiModelConfig() [2/2]

ContainerDefinition& Aws::SageMaker::Model::ContainerDefinition::WithMultiModelConfig ( MultiModelConfig &&  value)
inline

Specifies additional configuration for multi-model endpoints.

Definition at line 743 of file ContainerDefinition.h.


The documentation for this class was generated from the following file: