Class TrainedModelDeploymentStats.Builder
java.lang.Object
co.elastic.clients.util.ObjectBuilderBase
co.elastic.clients.util.WithJsonObjectBuilderBase<TrainedModelDeploymentStats.Builder>
co.elastic.clients.elasticsearch.ml.TrainedModelDeploymentStats.Builder
- All Implemented Interfaces:
WithJson<TrainedModelDeploymentStats.Builder>
,ObjectBuilder<TrainedModelDeploymentStats>
- Enclosing class:
- TrainedModelDeploymentStats
public static class TrainedModelDeploymentStats.Builder
extends WithJsonObjectBuilderBase<TrainedModelDeploymentStats.Builder>
implements ObjectBuilder<TrainedModelDeploymentStats>
Builder for
TrainedModelDeploymentStats
.-
Constructor Summary
-
Method Summary
Modifier and TypeMethodDescriptionRequired - The detailed allocation status for the deployment.allocationStatus
(Function<TrainedModelDeploymentAllocationStatus.Builder, ObjectBuilder<TrainedModelDeploymentAllocationStatus>> fn) Required - The detailed allocation status for the deployment.build()
Builds aTrainedModelDeploymentStats
.API name:cache_size
deploymentId
(String value) Required - The unique identifier for the trained model deployment.errorCount
(int value) Required - The sum oferror_count
for all nodes in the deployment.inferenceCount
(int value) Required - The sum ofinference_count
for all nodes in the deployment.Required - The unique identifier for the trained model.Required - The deployment stats for each node that currently has the model allocated.nodes
(Function<TrainedModelDeploymentNodesStats.Builder, ObjectBuilder<TrainedModelDeploymentNodesStats>> fn) Required - The deployment stats for each node that currently has the model allocated.numberOfAllocations
(int value) Required - The number of allocations requested.queueCapacity
(int value) Required - The number of inference requests that can be queued before new requests are rejected.Required - The reason for the current deployment state.rejectedExecutionCount
(int value) Required - The sum ofrejected_execution_count
for all nodes in the deployment.protected TrainedModelDeploymentStats.Builder
self()
startTime
(long value) Required - The epoch timestamp when the deployment started.state
(DeploymentState value) Required - The overall state of the deployment.threadsPerAllocation
(int value) Required - The number of threads used be each allocation during inference.timeoutCount
(int value) Required - The sum oftimeout_count
for all nodes in the deployment.Methods inherited from class co.elastic.clients.util.WithJsonObjectBuilderBase
withJson
Methods inherited from class co.elastic.clients.util.ObjectBuilderBase
_checkSingleUse, _listAdd, _listAddAll, _mapPut, _mapPutAll
-
Constructor Details
-
Builder
public Builder()
-
-
Method Details
-
allocationStatus
public final TrainedModelDeploymentStats.Builder allocationStatus(TrainedModelDeploymentAllocationStatus value) Required - The detailed allocation status for the deployment.API name:
allocation_status
-
allocationStatus
public final TrainedModelDeploymentStats.Builder allocationStatus(Function<TrainedModelDeploymentAllocationStatus.Builder, ObjectBuilder<TrainedModelDeploymentAllocationStatus>> fn) Required - The detailed allocation status for the deployment.API name:
allocation_status
-
cacheSize
API name:cache_size
-
deploymentId
Required - The unique identifier for the trained model deployment.API name:
deployment_id
-
errorCount
Required - The sum oferror_count
for all nodes in the deployment.API name:
error_count
-
inferenceCount
Required - The sum ofinference_count
for all nodes in the deployment.API name:
inference_count
-
modelId
Required - The unique identifier for the trained model.API name:
model_id
-
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
-
nodes
public final TrainedModelDeploymentStats.Builder nodes(Function<TrainedModelDeploymentNodesStats.Builder, ObjectBuilder<TrainedModelDeploymentNodesStats>> fn) 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
Required - The number of allocations requested.API name:
number_of_allocations
-
queueCapacity
Required - The number of inference requests that can be queued before new requests are rejected.API name:
queue_capacity
-
rejectedExecutionCount
Required - The sum ofrejected_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 thequeue_capacity
setting in the start trained model deployment API.API name:
rejected_execution_count
-
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
Required - The epoch timestamp when the deployment started.API name:
start_time
-
state
Required - The overall state of the deployment.API name:
state
-
threadsPerAllocation
Required - The number of threads used be each allocation during inference.API name:
threads_per_allocation
-
timeoutCount
Required - The sum oftimeout_count
for all nodes in the deployment.API name:
timeout_count
-
self
- Specified by:
self
in classWithJsonObjectBuilderBase<TrainedModelDeploymentStats.Builder>
-
build
Builds aTrainedModelDeploymentStats
.- Specified by:
build
in interfaceObjectBuilder<TrainedModelDeploymentStats>
- Throws:
NullPointerException
- if some of the required fields are null.
-