Struct RecommendationJobInferenceBenchmark

#[non_exhaustive]
pub struct RecommendationJobInferenceBenchmark {
    pub metrics: Option<RecommendationMetrics>,
    pub endpoint_metrics: Option<InferenceMetrics>,
    pub endpoint_configuration: Option<EndpointOutputConfiguration>,
    pub model_configuration: Option<ModelConfiguration>,
    pub failure_reason: Option<String>,
    pub invocation_end_time: Option<DateTime>,
    pub invocation_start_time: Option<DateTime>,
}

The details for a specific benchmark from an Inference Recommender job.

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.

metrics: Option<RecommendationMetrics>

The metrics of recommendations.

endpoint_metrics: Option<InferenceMetrics>

The metrics for an existing endpoint compared in an Inference Recommender job.

endpoint_configuration: Option<EndpointOutputConfiguration>

The endpoint configuration made by Inference Recommender during a recommendation job.

model_configuration: Option<ModelConfiguration>

Defines the model configuration. Includes the specification name and environment parameters.

failure_reason: Option<String>

The reason why a benchmark failed.

invocation_end_time: Option<DateTime>

A timestamp that shows when the benchmark completed.

invocation_start_time: Option<DateTime>

A timestamp that shows when the benchmark started.

Implementations

impl RecommendationJobInferenceBenchmark

pub fn metrics(&self) -> Option<&RecommendationMetrics>

The metrics of recommendations.

pub fn endpoint_metrics(&self) -> Option<&InferenceMetrics>

The metrics for an existing endpoint compared in an Inference Recommender job.

pub fn endpoint_configuration(&self) -> Option<&EndpointOutputConfiguration>

The endpoint configuration made by Inference Recommender during a recommendation job.

pub fn model_configuration(&self) -> Option<&ModelConfiguration>

Defines the model configuration. Includes the specification name and environment parameters.

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

The reason why a benchmark failed.

pub fn invocation_end_time(&self) -> Option<&DateTime>

A timestamp that shows when the benchmark completed.

pub fn invocation_start_time(&self) -> Option<&DateTime>

A timestamp that shows when the benchmark started.

impl RecommendationJobInferenceBenchmark

pub fn builder() -> RecommendationJobInferenceBenchmarkBuilder

Creates a new builder-style object to manufacture RecommendationJobInferenceBenchmark.

Trait Implementations

impl Clone for RecommendationJobInferenceBenchmark

fn clone(&self) -> RecommendationJobInferenceBenchmark

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RecommendationJobInferenceBenchmark

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

Formats the value using the given formatter.

impl PartialEq for RecommendationJobInferenceBenchmark

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