Skip to content

InferenceComponentContainerSpecification

Source code in docs_src/capo_sagemaker/types/inference_component_container_specification.py 
14
15
16
17
18
19
20
21
22
23
24
class InferenceComponentContainerSpecification(TypedDict, closed=True):
    image: NotRequired["capo_sagemaker.types.container_image.ContainerImage"]
    """<p>The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.</p>"""
    artifact_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 gzip compressed tar archive (.tar.gz suffix).</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 Environment string-to-string map can have length of up to 1024. We support up to 16 entries in the map.</p>"""
    container_metrics_config: NotRequired[
        "capo_sagemaker.types.container_metrics_config.ContainerMetricsConfig"
    ]
    """<p>The configuration for container metrics scraping. Specifies the metrics endpoint path and publishing frequency for the inference component's container. If not specified when <code>EnableDetailedObservability</code> is <code>True</code>, the default path <code>/metrics</code> on port <code>8080</code> is used. For first-party and Deep Learning Containers (DLC), the endpoint path is determined automatically and this configuration is optional.</p>"""

artifact_url instance-attribute 

artifact_url: NotRequired[Url]

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).

container_metrics_config instance-attribute 

container_metrics_config: NotRequired[ContainerMetricsConfig]

The configuration for container metrics scraping. Specifies the metrics endpoint path and publishing frequency for the inference component's container. If not specified when EnableDetailedObservability is True, the default path /metrics on port 8080 is used. For first-party and Deep Learning Containers (DLC), the endpoint path is determined automatically and this configuration is optional.

environment instance-attribute 

environment: NotRequired[EnvironmentMap]

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.

image instance-attribute 

image: NotRequired[ContainerImage]

The Amazon Elastic Container Registry (Amazon ECR) path where the Docker image for the model is stored.