OpenSearch-Docs-Cn/_ml-commons-plugin/index.md

layout, title, nav_order, has_children, has_toc, nav_exclude

layout	title	nav_order	has_children	has_toc	nav_exclude
default	About ML Commons	1	false	false	true

ML Commons plugin

ML Commons for OpenSearch simplifies the development of machine learning (ML) features by providing a set of ML algorithms through transport and REST API calls. Those calls choose the right nodes and resources for each ML request and monitor ML tasks to ensure uptime. This allows you to use existing open-source ML algorithms and reduce the effort required to develop new ML features.

Interaction with the ML Commons plugin occurs through either the REST API or ad and kmeans Piped Processing Language (PPL) commands.

Models trained through the ML Commons plugin support model-based algorithms, such as k-means. After you've trained a model to your precision requirements, use the model to make predictions.

If you don't want to use a model, you can use the Train and Predict API to test your model without having to evaluate the model's performance.

Using ML Commons

1. Ensure that you've appropriately set the cluster settings described in ML Commons cluster settings.
2. Set up model access as described in Model access control.
3. Start using models:

• Run your custom models within an OpenSearch cluster.
• Integrate models hosted on an external platform.