Package software.amazon.awssdk.services.sagemaker.model

Interface RecommendationJobStoppingConditions.Builder

    • Method Detail

      • maxInvocations

        RecommendationJobStoppingConditions.Builder maxInvocations​(Integer maxInvocations)

        The maximum number of requests per minute expected for the endpoint.

        Parameters:
        maxInvocations - The maximum number of requests per minute expected for the endpoint.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • modelLatencyThresholds

        RecommendationJobStoppingConditions.Builder modelLatencyThresholds​(Collection<ModelLatencyThreshold> modelLatencyThresholds)

        The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.

        Parameters:
        modelLatencyThresholds - The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • modelLatencyThresholds

        RecommendationJobStoppingConditions.Builder modelLatencyThresholds​(ModelLatencyThreshold... modelLatencyThresholds)

        The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.

        Parameters:
        modelLatencyThresholds - The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.
        Returns:
        Returns a reference to this object so that method calls can be chained together.

      • modelLatencyThresholds

        RecommendationJobStoppingConditions.Builder modelLatencyThresholds​(Consumer<ModelLatencyThreshold.Builder>... modelLatencyThresholds)

        The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.

        This is a convenience method that creates an instance of the ModelLatencyThreshold.Builder avoiding the need to create one manually via ModelLatencyThreshold.builder().

        When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to #modelLatencyThresholds(List).

        Parameters:
        modelLatencyThresholds - a consumer that will call methods on ModelLatencyThreshold.Builder
        Returns:
        Returns a reference to this object so that method calls can be chained together.
        See Also:
        #modelLatencyThresholds(java.util.Collection)

      • flatInvocations

        RecommendationJobStoppingConditions.Builder flatInvocations​(String flatInvocations)

        Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.

        Parameters:
        flatInvocations - Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
        See Also:
        FlatInvocations, FlatInvocations

      • flatInvocations

        RecommendationJobStoppingConditions.Builder flatInvocations​(FlatInvocations flatInvocations)

        Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.

        Parameters:
        flatInvocations - Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
        See Also:
        FlatInvocations, FlatInvocations