Interface RecommendationMetrics.Builder

    • Method Detail

      • costPerHour

        RecommendationMetrics.Builder costPerHour​(Float costPerHour)

        Defines the cost per hour for the instance.

        Parameters:
        costPerHour - Defines the cost per hour for the instance.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • costPerInference

        RecommendationMetrics.Builder costPerInference​(Float costPerInference)

        Defines the cost per inference for the instance .

        Parameters:
        costPerInference - Defines the cost per inference for the instance .
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • maxInvocations

        RecommendationMetrics.Builder maxInvocations​(Integer maxInvocations)

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

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

        RecommendationMetrics.Builder modelLatency​(Integer modelLatency)

        The expected model latency at maximum invocation per minute for the instance.

        Parameters:
        modelLatency - The expected model latency at maximum invocation per minute for the instance.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • cpuUtilization

        RecommendationMetrics.Builder cpuUtilization​(Float cpuUtilization)

        The expected CPU utilization at maximum invocations per minute for the instance.

        NaN indicates that the value is not available.

        Parameters:
        cpuUtilization - The expected CPU utilization at maximum invocations per minute for the instance.

        NaN indicates that the value is not available.

        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • memoryUtilization

        RecommendationMetrics.Builder memoryUtilization​(Float memoryUtilization)

        The expected memory utilization at maximum invocations per minute for the instance.

        NaN indicates that the value is not available.

        Parameters:
        memoryUtilization - The expected memory utilization at maximum invocations per minute for the instance.

        NaN indicates that the value is not available.

        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • modelSetupTime

        RecommendationMetrics.Builder modelSetupTime​(Integer modelSetupTime)

        The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container.

        NaN indicates that the value is not available.

        Parameters:
        modelSetupTime - The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container.

        NaN indicates that the value is not available.

        Returns:
        Returns a reference to this object so that method calls can be chained together.