Stop a trained model deployment Generally available; Added in 8.0.0

View as markdown
POST /_ml/trained_models/{model_id}/deployment/_stop
Api key auth Basic auth Bearer auth

Required authorization

  • Cluster privileges: manage_ml

Path parameters

  • model_id string Required

    The unique identifier of the trained model.

Query parameters

  • allow_no_match boolean

    Specifies what to do when the request: contains wildcard expressions and there are no deployments that match; contains the _all string or no identifiers and there are no matches; or contains wildcard expressions and there are only partial matches. By default, it returns an empty array when there are no matches and the subset of results when there are partial matches. If false, the request returns a 404 status code when there are no matches or only partial matches.

  • force boolean

    Forcefully stops the deployment, even if it is used by ingest pipelines. You can't use these pipelines until you restart the model deployment.

Responses

  • 200 application/json
    Hide response attribute Show response attribute object
    • stopped boolean Required
POST /_ml/trained_models/{model_id}/deployment/_stop 
POST _ml/trained_models/my_model_for_search/deployment/_stop

resp = client.ml.stop_trained_model_deployment(
    model_id="my_model_for_search",
)
const response = await client.ml.stopTrainedModelDeployment({
  model_id: "my_model_for_search",
});
response = client.ml.stop_trained_model_deployment(
  model_id: "my_model_for_search"
)
$resp = $client->ml()->stopTrainedModelDeployment([
    "model_id" => "my_model_for_search",
]);
curl -X POST -H "Authorization: ApiKey $ELASTIC_API_KEY" "$ELASTICSEARCH_URL/_ml/trained_models/my_model_for_search/deployment/_stop"
client.ml().stopTrainedModelDeployment(s -> s
    .modelId("my_model_for_search")
);