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:
-
Nested Class Summary
Nested Classes -
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final JsonpDeserializer<TrainedModelDeploymentStats>
Json deserializer forTrainedModelDeploymentStats
-
Method Summary
Modifier and TypeMethodDescriptionAPI name:adaptive_allocations
The detailed allocation status for the deployment.final String
API name:cache_size
final String
Required - The unique identifier for the trained model deployment.final Integer
The sum oferror_count
for all nodes in the deployment.final Integer
The sum ofinference_count
for all nodes in the deployment.final String
modelId()
Required - The unique identifier for the trained model.nodes()
Required - The deployment stats for each node that currently has the model allocated.final Integer
The number of allocations requested.static TrainedModelDeploymentStats
final long
Required - API name:peak_throughput_per_minute
final TrainingPriority
priority()
Required - API name:priority
final Integer
The number of inference requests that can be queued before new requests are rejected.final String
reason()
The reason for the current deployment state.final Integer
The sum ofrejected_execution_count
for all nodes in the deployment.void
serialize
(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper) Serialize this object to JSON.protected void
serializeInternal
(jakarta.json.stream.JsonGenerator generator, JsonpMapper mapper) protected static void
setupTrainedModelDeploymentStatsDeserializer
(ObjectDeserializer<TrainedModelDeploymentStats.Builder> op) final long
Required - The epoch timestamp when the deployment started.state()
The overall state of the deployment.final Integer
The number of threads used be each allocation during inference.final Integer
The sum oftimeout_count
for all nodes in the deployment.toString()
-
Field Details
-
_DESERIALIZER
Json deserializer forTrainedModelDeploymentStats
-
-
Method Details
-
of
-
adaptiveAllocations
API name:adaptive_allocations
-
allocationStatus
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
The sum oferror_count
for all nodes in the deployment.API name:
error_count
-
inferenceCount
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
-
numberOfAllocations
The number of allocations requested.API name:
number_of_allocations
-
peakThroughputPerMinute
public final long peakThroughputPerMinute()Required - API name:peak_throughput_per_minute
-
priority
Required - API name:priority
-
queueCapacity
The number of inference requests that can be queued before new requests are rejected.API name:
queue_capacity
-
rejectedExecutionCount
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
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
The overall state of the deployment.API name:
state
-
threadsPerAllocation
The number of threads used be each allocation during inference.API name:
threads_per_allocation
-
timeoutCount
The sum oftimeout_count
for all nodes in the deployment.API name:
timeout_count
-
serialize
Serialize this object to JSON.- Specified by:
serialize
in interfaceJsonpSerializable
-
serializeInternal
-
toString
-
setupTrainedModelDeploymentStatsDeserializer
protected static void setupTrainedModelDeploymentStatsDeserializer(ObjectDeserializer<TrainedModelDeploymentStats.Builder> op)
-