IMPORTANT: No additional bug fixes or documentation updates will be released for this version. For the latest information, see the current release documentation.
« Delete data frame analytics jobs API Evaluate data frame analytics API »
Elastic Docs ›Elasticsearch Guide [7.9] ›REST APIs ›Machine learning data frame analytics APIs

Delete trained model API

edit

Delete trained model API

edit

Deletes an existing trained inference model that is currently not referenced by an ingest pipeline.

This functionality is in technical preview and may be changed or removed in a future release. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features.

Request

edit

DELETE _ml/inference/<model_id>

Prerequisites

edit

If the Elasticsearch security features are enabled, you must have the following built-in roles or equivalent privileges:

  • machine_learning_admin

For more information, see Built-in roles and Machine learning security privileges.

Path parameters

edit
<model_id>
(Optional, string) The unique identifier of the trained model.

Response codes

edit
409
The code indicates that the trained model is referenced by an ingest pipeline and cannot be deleted.

Examples

edit

The following example deletes the regression-job-one-1574775307356 trained model:

DELETE _ml/inference/regression-job-one-1574775307356

The API returns the following result:

{
  "acknowledged" : true
}
« Delete data frame analytics jobs API Evaluate data frame analytics API »