ModelPackageContainerDefinition ¶

class ModelPackageContainerDefinition(TypedDict, closed=True):
    container_hostname: NotRequired[
        "capo_sagemaker.types.container_hostname.ContainerHostname"
    ]
    """<p>The DNS host name for the Docker container.</p>"""
    image: NotRequired["capo_sagemaker.types.container_image.ContainerImage"]
    """<p>The Amazon Elastic Container Registry (Amazon ECR) path where inference code is stored.</p> <p>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 <code>registry/repository[:tag]</code> and <code>registry/repository[@digest]</code> image path formats. For more information, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms.html">Using Your Own Algorithms with Amazon SageMaker</a>.</p>"""
    image_digest: NotRequired["capo_sagemaker.types.image_digest.ImageDigest"]
    """<p>An MD5 hash of the training algorithm that identifies the Docker image used for training.</p>"""
    model_data_url: NotRequired["capo_sagemaker.types.url.Url"]
    """<p>The Amazon S3 path where the model artifacts, which result from model training, are stored. This path must point to a single <code>gzip</code> compressed tar archive (<code>.tar.gz</code> suffix).</p> <note> <p>The model artifacts must be in an S3 bucket that is in the same region as the model package.</p> </note>"""
    model_data_source: NotRequired[
        "capo_sagemaker.types.model_data_source.ModelDataSource"
    ]
    """<p>Specifies the location of ML model data to deploy during endpoint creation.</p>"""
    product_id: NotRequired["capo_sagemaker.types.product_id.ProductId"]
    """<p>The Amazon Web Services Marketplace product ID of the model package.</p>"""
    environment: NotRequired["capo_sagemaker.types.environment_map.EnvironmentMap"]
    """<p>The environment variables to set in the Docker container. Each key and value in the <code>Environment</code> string to string map can have length of up to 1024. We support up to 16 entries in the map.</p>"""
    model_input: NotRequired["capo_sagemaker.types.model_input.ModelInput"]
    """<p>A structure with Model Input details.</p>"""
    framework: NotRequired["capo_sagemaker.types.string.String"]
    """<p>The machine learning framework of the model package container image.</p>"""
    framework_version: NotRequired[
        "capo_sagemaker.types.model_package_framework_version.ModelPackageFrameworkVersion"
    ]
    """<p>The framework version of the Model Package Container Image.</p>"""
    nearest_model_name: NotRequired["capo_sagemaker.types.string.String"]
    """<p>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 <code>ListModelMetadata</code>.</p>"""
    additional_model_data_sources: NotRequired[
        "capo_sagemaker.types.additional_model_data_sources.AdditionalModelDataSources"
    ]
    """<p>Data sources that are available to your model in addition to the one that you specify for <code>ModelDataSource</code> when you use the <code>CreateModelPackage</code> action.</p>"""
    additional_s3_data_source: NotRequired[
        "capo_sagemaker.types.additional_s3_data_source.AdditionalS3DataSource"
    ]
    """<p>The additional data source that is used during inference in the Docker container for your model package.</p>"""
    model_data_e_tag: NotRequired["capo_sagemaker.types.string.String"]
    """<p>The ETag associated with Model Data URL.</p>"""
    is_checkpoint: NotRequired["capo_sagemaker.types.boolean.Boolean"]
    """<p> Specifies whether the model data is a training checkpoint. </p>"""
    base_model: NotRequired["capo_sagemaker.types.base_model.BaseModel"]
    """<p> Identifies the foundation model that was used as the starting point for model customization. </p>"""