Package co.elastic.clients.elasticsearch.ml

Class TrainedModelDeploymentStats

java.lang.Object
co.elastic.clients.elasticsearch.ml.TrainedModelDeploymentStats
All Implemented Interfaces:
JsonpSerializable
@JsonpDeserializable public class TrainedModelDeploymentStats extends Object implements JsonpSerializable
See Also:

  • Field Details

  • Method Details

    • of

      public static TrainedModelDeploymentStats of(Function<TrainedModelDeploymentStats.Builder,ObjectBuilder<TrainedModelDeploymentStats>> fn)

    • allocationStatus

      public final TrainedModelDeploymentAllocationStatus allocationStatus()
      Required - The detailed allocation status for the deployment.

      API name: allocation_status

    • cacheSize

      @Nullable public final String cacheSize()
      API name: cache_size

    • deploymentId

      public final String deploymentId()
      Required - The unique identifier for the trained model deployment.

      API name: deployment_id

    • errorCount

      public final int errorCount()
      Required - The sum of error_count for all nodes in the deployment.

      API name: error_count

    • inferenceCount

      public final int inferenceCount()
      Required - The sum of inference_count for all nodes in the deployment.

      API name: inference_count

    • modelId

      public final String modelId()
      Required - The unique identifier for the trained model.

      API name: model_id

    • nodes

      public final TrainedModelDeploymentNodesStats nodes()
      Required - The deployment stats for each node that currently has the model allocated. In serverless, stats are reported for a single unnamed virtual node.

      API name: nodes

    • numberOfAllocations

      public final int numberOfAllocations()
      Required - The number of allocations requested.

      API name: number_of_allocations

    • queueCapacity

      public final int queueCapacity()
      Required - The number of inference requests that can be queued before new requests are rejected.

      API name: queue_capacity

    • rejectedExecutionCount

      public final int rejectedExecutionCount()
      Required - The sum of rejected_execution_count for all nodes in the deployment. Individual nodes reject an inference request if the inference queue is full. The queue size is controlled by the queue_capacity setting in the start trained model deployment API.

      API name: rejected_execution_count

    • reason

      public final String reason()
      Required - The reason for the current deployment state. Usually only populated when the model is not deployed to a node.

      API name: reason

    • startTime

      public final long startTime()
      Required - The epoch timestamp when the deployment started.

      API name: start_time

    • state

      public final DeploymentState state()
      Required - The overall state of the deployment.

      API name: state

    • threadsPerAllocation

      public final int threadsPerAllocation()
      Required - The number of threads used be each allocation during inference.

      API name: threads_per_allocation

    • timeoutCount

      public final int timeoutCount()
      Required - The sum of timeout_count for all nodes in the deployment.

      API name: timeout_count

    • serialize

      public void serialize(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper)
      Serialize this object to JSON.
      Specified by:
      serialize in interface JsonpSerializable

    • serializeInternal

      protected void serializeInternal(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper)

    • toString

      public String toString()
      Overrides:
      toString in class Object

    • setupTrainedModelDeploymentStatsDeserializer

      protected static void setupTrainedModelDeploymentStatsDeserializer(ObjectDeserializer<TrainedModelDeploymentStats.Builder> op)