Get trained models usage info | Elasticsearch API documentation

Path parameters

model_idstring | array[string] Required
The unique identifier of the trained model or a model alias. It can be a comma-separated list or a wildcard expression.

Query parameters

allow_no_matchboolean
Specifies what to do when the request:
- Contains wildcard expressions and there are no models that match.
- Contains the _all string or no identifiers and there are no matches.
- Contains wildcard expressions and there are only partial matches.
If true, it returns an empty array when there are no matches and the subset of results when there are partial matches.
fromnumber
Skips the specified number of models.
sizenumber
Specifies the maximum number of models to obtain.

Responses

200 application/json
Hide response attributes Show response attributes object
- countnumber Required
  The total number of trained model statistics that matched the requested ID patterns. Could be higher than the number of items in the trained_model_stats array as the size of the array is restricted by the supplied size parameter.
- trained_model_statsarray[object] Required
  An array of trained model statistics, which are sorted by the model_id value in ascending order.
  Hide trained_model_stats attributes Show trained_model_stats attributes object
  deployment_statsobject
  Hide deployment_stats attributes Show deployment_stats attributes object
  adaptive_allocationsobject
  Hide adaptive_allocations attributes Show adaptive_allocations attributes object
  allocation_statusobject
  Hide allocation_status attributes Show allocation_status attributes object
  allocation_countnumber Required
  The current number of nodes where the model is allocated.
  statestring Required
  Values are started, starting, or fully_allocated.
  target_allocation_countnumber Required
  The desired number of nodes for model allocation.
  cache_sizenumber | string
  One of:
  ByteSizenumber ByteSizestring
  deployment_idstring Required
  error_countnumber
  The sum of error_count for all nodes in the deployment.
  inference_countnumber
  The sum of inference_count for all nodes in the deployment.
  model_idstring Required
  nodesarray[object] Required
  The deployment stats for each node that currently has the model allocated. In serverless, stats are reported for a single unnamed virtual node.
  Hide nodes attributes Show nodes attributes object
  average_inference_time_ms
  average_inference_time_ms_last_minute
  average_inference_time_ms_excluding_cache_hits
  error_countnumber
  The number of errors when evaluating the trained model.
  inference_countnumber
  The total number of inference calls made against this node for this model.
  inference_cache_hit_countnumber
  inference_cache_hit_count_last_minutenumber
  last_access
  nodeobject
  number_of_allocationsnumber
  The number of allocations assigned to this node.
  number_of_pending_requestsnumber
  The number of inference requests queued to be processed.
  peak_throughput_per_minutenumber Required
  rejected_execution_countnumber
  The number of inference requests that were not processed because the queue was full.
  routing_stateobject Required
  start_time
  threads_per_allocationnumber
  The number of threads used by each allocation during inference.
  throughput_last_minutenumber Required
  timeout_countnumber
  The number of inference requests that timed out before being processed.
  number_of_allocationsnumber
  The number of allocations requested.
  peak_throughput_per_minutenumber Required
  prioritystring Required
  Values are normal or low.
  queue_capacitynumber
  The number of inference requests that can be queued before new requests are rejected.
  rejected_execution_countnumber
  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.
  reasonstring
  The reason for the current deployment state. Usually only populated when the model is not deployed to a node.
  start_timenumber
  Time unit for milliseconds
  statestring
  Values are started, starting, stopping, or failed.
  threads_per_allocationnumber
  The number of threads used be each allocation during inference.
  timeout_countnumber
  The sum of timeout_count for all nodes in the deployment.
  inference_statsobject
  Hide inference_stats attributes Show inference_stats attributes object
  cache_miss_countnumber Required
  The number of times the model was loaded for inference and was not retrieved from the cache. If this number is close to the inference_count, the cache is not being appropriately used. This can be solved by increasing the cache size or its time-to-live (TTL). Refer to general machine learning settings for the appropriate settings.
  failure_countnumber Required
  The number of failures when using the model for inference.
  inference_countnumber Required
  The total number of times the model has been called for inference. This is across all inference contexts, including all pipelines.
  missing_all_fields_countnumber Required
  The number of inference calls where all the training features for the model were missing.
  timestampnumber
  Time unit for milliseconds
  ingestobject
  A collection of ingest stats for the model across all nodes. The values are summations of the individual node statistics. The format matches the ingest section in the nodes stats API.
  Hide ingest attribute Show ingest attribute object
  *object Additional properties
  model_idstring Required
  model_size_statsobject Required
  Hide model_size_stats attributes Show model_size_stats attributes object
  model_size_bytesnumber | string Required
  One of:
  ByteSizenumber ByteSizestring
  required_native_memory_bytesnumber | string Required
  One of:
  ByteSizenumber ByteSizestring
  pipeline_countnumber Required
  The number of ingest pipelines that currently refer to the model.

GET /_ml/trained_models/{model_id}/_stats

GET _ml/trained_models/_stats

resp = client.ml.get_trained_models_stats()

const response = await client.ml.getTrainedModelsStats();

response = client.ml.get_trained_models_stats

$resp = $client->ml()->getTrainedModelsStats();

curl -X GET -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_ml/trained_models/_stats"

Path parameters

Query parameters

Responses

cache_sizenumber | string

model_size_bytesnumber | string Required

required_native_memory_bytesnumber | string Required