Interface ModelPackageContainerDefinition.Builder
- All Superinterfaces:
Buildable
,CopyableBuilder<ModelPackageContainerDefinition.Builder,
,ModelPackageContainerDefinition> SdkBuilder<ModelPackageContainerDefinition.Builder,
,ModelPackageContainerDefinition> SdkPojo
- Enclosing class:
ModelPackageContainerDefinition
-
Method Summary
Modifier and TypeMethodDescriptionadditionalS3DataSource
(Consumer<AdditionalS3DataSource.Builder> additionalS3DataSource) The additional data source that is used during inference in the Docker container for your model package.additionalS3DataSource
(AdditionalS3DataSource additionalS3DataSource) The additional data source that is used during inference in the Docker container for your model package.containerHostname
(String containerHostname) The DNS host name for the Docker container.environment
(Map<String, String> environment) The environment variables to set in the Docker container.The machine learning framework of the model package container image.frameworkVersion
(String frameworkVersion) The framework version of the Model Package Container Image.The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.imageDigest
(String imageDigest) An MD5 hash of the training algorithm that identifies the Docker image used for training.modelDataSource
(Consumer<ModelDataSource.Builder> modelDataSource) Specifies the location of ML model data to deploy during endpoint creation.modelDataSource
(ModelDataSource modelDataSource) Specifies the location of ML model data to deploy during endpoint creation.modelDataUrl
(String modelDataUrl) The Amazon S3 path where the model artifacts, which result from model training, are stored.modelInput
(Consumer<ModelInput.Builder> modelInput) A structure with Model Input details.modelInput
(ModelInput modelInput) A structure with Model Input details.nearestModelName
(String nearestModelName) The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model.The Amazon Web Services Marketplace product ID of the model package.Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder
copy
Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder
applyMutation, build
Methods inherited from interface software.amazon.awssdk.core.SdkPojo
equalsBySdkFields, sdkFields
-
Method Details
-
containerHostname
The DNS host name for the Docker container.
- Parameters:
containerHostname
- The DNS host name for the Docker container.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
image
The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.
If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both
registry/repository[:tag]
andregistry/repository[@digest]
image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.- Parameters:
image
- The Amazon EC2 Container Registry (Amazon ECR) path where inference code is stored.If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both
registry/repository[:tag]
andregistry/repository[@digest]
image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
imageDigest
An MD5 hash of the training algorithm that identifies the Docker image used for training.
- Parameters:
imageDigest
- An MD5 hash of the training algorithm that identifies the Docker image used for training.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelDataUrl
The Amazon 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 model artifacts must be in an S3 bucket that is in the same region as the model package.
- Parameters:
modelDataUrl
- The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a singlegzip
compressed tar archive (.tar.gz
suffix).The model artifacts must be in an S3 bucket that is in the same region as the model package.
- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelDataSource
Specifies the location of ML model data to deploy during endpoint creation.
- Parameters:
modelDataSource
- Specifies the location of ML model data to deploy during endpoint creation.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelDataSource
default ModelPackageContainerDefinition.Builder modelDataSource(Consumer<ModelDataSource.Builder> modelDataSource) Specifies the location of ML model data to deploy during endpoint creation.
This is a convenience method that creates an instance of theModelDataSource.Builder
avoiding the need to create one manually viaModelDataSource.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed tomodelDataSource(ModelDataSource)
.- Parameters:
modelDataSource
- a consumer that will call methods onModelDataSource.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-
productId
The Amazon Web Services Marketplace product ID of the model package.
- Parameters:
productId
- The Amazon Web Services Marketplace product ID of the model package.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
environment
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 1024. We support up to 16 entries in the map.- Parameters:
environment
- The environment variables to set in the Docker container. Each key and value in theEnvironment
string to string map can have length of up to 1024. We support up to 16 entries in the map.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelInput
A structure with Model Input details.
- Parameters:
modelInput
- A structure with Model Input details.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
modelInput
A structure with Model Input details.
This is a convenience method that creates an instance of theModelInput.Builder
avoiding the need to create one manually viaModelInput.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed tomodelInput(ModelInput)
.- Parameters:
modelInput
- a consumer that will call methods onModelInput.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-
framework
The machine learning framework of the model package container image.
- Parameters:
framework
- The machine learning framework of the model package container image.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
frameworkVersion
The framework version of the Model Package Container Image.
- Parameters:
frameworkVersion
- The framework version of the Model Package Container Image.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
nearestModelName
The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model. You can find a list of benchmarked models by calling
ListModelMetadata
.- Parameters:
nearestModelName
- The name of a pre-trained machine learning benchmarked by Amazon SageMaker Inference Recommender model that matches your model. You can find a list of benchmarked models by callingListModelMetadata
.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
additionalS3DataSource
ModelPackageContainerDefinition.Builder additionalS3DataSource(AdditionalS3DataSource additionalS3DataSource) The additional data source that is used during inference in the Docker container for your model package.
- Parameters:
additionalS3DataSource
- The additional data source that is used during inference in the Docker container for your model package.- Returns:
- Returns a reference to this object so that method calls can be chained together.
-
additionalS3DataSource
default ModelPackageContainerDefinition.Builder additionalS3DataSource(Consumer<AdditionalS3DataSource.Builder> additionalS3DataSource) The additional data source that is used during inference in the Docker container for your model package.
This is a convenience method that creates an instance of theAdditionalS3DataSource.Builder
avoiding the need to create one manually viaAdditionalS3DataSource.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed toadditionalS3DataSource(AdditionalS3DataSource)
.- Parameters:
additionalS3DataSource
- a consumer that will call methods onAdditionalS3DataSource.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-