ModelContainer constructor

const ModelContainer({
  1. Input<List<ModelContainerAdditionalModelDataSource>?>? additionalModelDataSources,
  2. Input<String?>? containerHostname,
  3. Input<Map<String, String>?>? environment,
  4. Input<String?>? image,
  5. Input<ModelContainerImageConfig?>? imageConfig,
  6. Input<String?>? inferenceSpecificationName,
  7. Input<String?>? mode,
  8. Input<ModelContainerModelDataSource?>? modelDataSource,
  9. Input<String?>? modelDataUrl,
  10. Input<String?>? modelPackageName,
  11. Input<ModelContainerMultiModelConfig?>? multiModelConfig,
})

Creates a new ModelContainer. additionalModelDataSources Additional data sources that are available to the model in addition to those specified in modelDataSource. See Additional Model Data Source. containerHostname DNS host name for the container. environment Environment variables for the Docker container. image Registry path where the inference code image is stored in Amazon ECR. imageConfig Whether the model container is in Amazon ECR or a private Docker registry accessible from your VPC. For more information see Using a Private Docker Registry for Real-Time Inference Containers. see Image Config. inferenceSpecificationName Inference specification name in the model package version. mode Container hosts value. Allowed values are: SingleModel and MultiModel. The default value is SingleModel. modelDataSource Location of model data to deploy. Use this for uncompressed model deployment. For information about how to deploy an uncompressed model, see Deploying uncompressed models in the AWS SageMaker AI Developer Guide. modelDataUrl URL for the S3 location where model artifacts are stored. modelPackageName ARN of the model package to use to create the model. multiModelConfig Specifies additional configuration for multi-model endpoints. see Multi Model Config.

Implementation

const ModelContainer({
  this.additionalModelDataSources,
  this.containerHostname,
  this.environment,
  this.image,
  this.imageConfig,
  this.inferenceSpecificationName,
  this.mode,
  this.modelDataSource,
  this.modelDataUrl,
  this.modelPackageName,
  this.multiModelConfig,
});