Struct ModelPackageContainerDefinition

#[non_exhaustive]
pub struct ModelPackageContainerDefinition {

    pub container_hostname: Option<String>,
    pub image: Option<String>,
    pub image_digest: Option<String>,
    pub model_data_url: Option<String>,
    pub model_data_source: Option<ModelDataSource>,
    pub product_id: Option<String>,
    pub environment: Option<HashMap<String, String>>,
    pub model_input: Option<ModelInput>,
    pub framework: Option<String>,
    pub framework_version: Option<String>,
    pub nearest_model_name: Option<String>,
    pub additional_s3_data_source: Option<AdditionalS3DataSource>,
    pub model_data_e_tag: Option<String>,
}

Describes the Docker container for the model package.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

container_hostname: Option<String>

The DNS host name for the Docker container.

image: Option<String>

The Amazon Elastic 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\[:tag\] and registry/repository\[@digest\] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.

image_digest: Option<String>

An MD5 hash of the training algorithm that identifies the Docker image used for training.

model_data_url: Option<String>

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.

model_data_source: Option<ModelDataSource>

Specifies the location of ML model data to deploy during endpoint creation.

product_id: Option<String>

The Amazon Web Services Marketplace product ID of the model package.

environment: Option<HashMap<String, String>>

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.

model_input: Option<ModelInput>

A structure with Model Input details.

framework: Option<String>

The machine learning framework of the model package container image.

framework_version: Option<String>

The framework version of the Model Package Container Image.

nearest_model_name: Option<String>

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.

additional_s3_data_source: Option<AdditionalS3DataSource>

The additional data source that is used during inference in the Docker container for your model package.

model_data_e_tag: Option<String>

The ETag associated with Model Data URL.

Implementations

impl ModelPackageContainerDefinition

pub fn container_hostname(&self) -> Option<&str>

The DNS host name for the Docker container.

pub fn image(&self) -> Option<&str>

The Amazon Elastic 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\[:tag\] and registry/repository\[@digest\] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.

pub fn image_digest(&self) -> Option<&str>

An MD5 hash of the training algorithm that identifies the Docker image used for training.

pub fn model_data_url(&self) -> Option<&str>

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.

pub fn model_data_source(&self) -> Option<&ModelDataSource>

Specifies the location of ML model data to deploy during endpoint creation.

pub fn product_id(&self) -> Option<&str>

The Amazon Web Services Marketplace product ID of the model package.

pub fn environment(&self) -> Option<&HashMap<String, String>>

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.

pub fn model_input(&self) -> Option<&ModelInput>

A structure with Model Input details.

pub fn framework(&self) -> Option<&str>

The machine learning framework of the model package container image.

pub fn framework_version(&self) -> Option<&str>

The framework version of the Model Package Container Image.

pub fn nearest_model_name(&self) -> Option<&str>

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.

pub fn additional_s3_data_source(&self) -> Option<&AdditionalS3DataSource>

The additional data source that is used during inference in the Docker container for your model package.

pub fn model_data_e_tag(&self) -> Option<&str>

The ETag associated with Model Data URL.

impl ModelPackageContainerDefinition

pub fn builder() -> ModelPackageContainerDefinitionBuilder

Creates a new builder-style object to manufacture ModelPackageContainerDefinition.

Trait Implementations

impl Clone for ModelPackageContainerDefinition

fn clone(&self) -> ModelPackageContainerDefinition

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ModelPackageContainerDefinition

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for ModelPackageContainerDefinition

fn eq(&self, other: &ModelPackageContainerDefinition) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for ModelPackageContainerDefinition