This is a cache of https://www.elastic.co/guide/en/machine-learning/8.19/ml-nlp-deploy-models.html. It is a snapshot of the page as it appeared on 2025-11-17T01:54:34.197+0000.
Deploy trained models | Machine Learning in the Elastic Stack [8.19] | Elastic
« Search and compare text Select a trained model »
Elastic Docs ›Machine Learning in the Elastic Stack [8.19] ›Natural language processing

Deploy trained models

edit
IMPORTANT: This documentation is no longer updated. Refer to Elastic's version policy and the latest documentation.

Deploy trained models

edit

If you want to perform natural language processing tasks in your cluster, you must deploy an appropriate trained model. There is tooling support in Eland and Kibana to help you prepare and manage models.

  1. Select a trained model.
  2. Import the trained model and vocabulary.
  3. Deploy the model in your cluster.
  4. Try it out.
« Search and compare text Select a trained model »