Class RecommendationMetrics

    • Method Detail

      • costPerHour

        public final Float costPerHour()

        Defines the cost per hour for the instance.

        Returns:
        Defines the cost per hour for the instance.
      • costPerInference

        public final Float costPerInference()

        Defines the cost per inference for the instance .

        Returns:
        Defines the cost per inference for the instance .
      • maxInvocations

        public final Integer maxInvocations()

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

        Returns:
        The expected maximum number of requests per minute for the instance.
      • modelLatency

        public final Integer modelLatency()

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

        Returns:
        The expected model latency at maximum invocation per minute for the instance.
      • cpuUtilization

        public final Float cpuUtilization()

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

        NaN indicates that the value is not available.

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

        NaN indicates that the value is not available.

      • memoryUtilization

        public final Float memoryUtilization()

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

        NaN indicates that the value is not available.

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

        NaN indicates that the value is not available.

      • modelSetupTime

        public final 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.

        Returns:
        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.

      • hashCode

        public final int hashCode()
        Overrides:
        hashCode in class Object
      • equals

        public final boolean equals​(Object obj)
        Overrides:
        equals in class Object
      • toString

        public final String toString()
        Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value.
        Overrides:
        toString in class Object
      • getValueForField

        public final <T> Optional<T> getValueForField​(String fieldName,
                                                      Class<T> clazz)