Struct InferenceSpecification

#[non_exhaustive]
pub struct InferenceSpecification {
    pub containers: Option<Vec<ModelPackageContainerDefinition>>,
    pub supported_transform_instance_types: Option<Vec<TransformInstanceType>>,
    pub supported_realtime_inference_instance_types: Option<Vec<ProductionVariantInstanceType>>,
    pub supported_content_types: Option<Vec<String>>,
    pub supported_response_mime_types: Option<Vec<String>>,
}

Defines how to perform inference generation after a training job is run.

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.

containers: Option<Vec<ModelPackageContainerDefinition>>

The Amazon ECR registry path of the Docker image that contains the inference code.

supported_transform_instance_types: Option<Vec<TransformInstanceType>>

A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.

This parameter is required for unversioned models, and optional for versioned models.

supported_realtime_inference_instance_types: Option<Vec<ProductionVariantInstanceType>>

A list of the instance types that are used to generate inferences in real-time.

This parameter is required for unversioned models, and optional for versioned models.

supported_content_types: Option<Vec<String>>

The supported MIME types for the input data.

supported_response_mime_types: Option<Vec<String>>

The supported MIME types for the output data.

Implementations

impl InferenceSpecification

pub fn containers(&self) -> &[ModelPackageContainerDefinition]

The Amazon ECR registry path of the Docker image that contains the inference code.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .containers.is_none().

pub fn supported_transform_instance_types(&self) -> &[TransformInstanceType]

A list of the instance types on which a transformation job can be run or on which an endpoint can be deployed.

This parameter is required for unversioned models, and optional for versioned models.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .supported_transform_instance_types.is_none().

pub fn supported_realtime_inference_instance_types( &self, ) -> &[ProductionVariantInstanceType]

A list of the instance types that are used to generate inferences in real-time.

This parameter is required for unversioned models, and optional for versioned models.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .supported_realtime_inference_instance_types.is_none().

pub fn supported_content_types(&self) -> &[String]

The supported MIME types for the input data.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .supported_content_types.is_none().

pub fn supported_response_mime_types(&self) -> &[String]

The supported MIME types for the output data.

If no value was sent for this field, a default will be set. If you want to determine if no value was sent, use .supported_response_mime_types.is_none().

impl InferenceSpecification

pub fn builder() -> InferenceSpecificationBuilder

Creates a new builder-style object to manufacture InferenceSpecification.

Trait Implementations

impl Clone for InferenceSpecification

fn clone(&self) -> InferenceSpecification

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceSpecification

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

Formats the value using the given formatter.

impl PartialEq for InferenceSpecification

fn eq(&self, other: &InferenceSpecification) -> 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 InferenceSpecification