Link Search Menu Expand Document Documentation Menu

Using ML models within OpenSearch

Introduced 2.9

To integrate machine learning (ML) models into your OpenSearch cluster, you can upload and serve them locally. Choose one of the following options.

Pretrained models provided by OpenSearch

Explore OpenSearch's collection of optimized ML models for immediate use in AI applications

Custom models

Learn how to upload and serve your own ML models in OpenSearch for specialized use cases

For production environments, run local models on dedicated ML nodes rather than data nodes. For more information, see Run tasks and models on ML nodes only.

Running local models on the CentOS 7 operating system is not supported. Moreover, not all local models can run on all hardware and operating systems.

GPU acceleration

Take advantage of GPU acceleration on your ML node for better performance

350 characters left

Have a question? .

Want to contribute? or .