Skip to main content
Version: 0.5.0

Managing ML models in Lucenia Dashboards

Introduced 2.9

Administrators of machine learning (ML) clusters can use Lucenia Dashboards to manage and check the status of ML models running inside a cluster. This can help ML developers provision nodes to ensure their models run efficiently.

You can register and deploy models using the API only. For more information, see Using ML models within Lucenia.

Enabling ML in Dashboards​

In Lucenia 2.6, ML functionality is disabled by default. To enable it, you need to edit the configuration in lucenia_dashboards.yml and then restart your cluster.

To enable the feature:

  1. In your Lucenia cluster, navigate to your Dashboards home directory; for example, in Docker, /usr/share/lucenia-dashboards.
  2. Open your local copy of the Dashboards configuration file lucenia_dashboards.yml. If you don't have a copy, get one from GitHub: lucenia_dashboards.yml.
  3. Add the setting ml_commons_dashboards.enabled: to lucenia_dashboards.yml. Then, set it to ml_commons_dashboards.enabled: true and save the configuration file.
  4. Restart the Dashboards container.
  5. Verify that the feature configuration settings were created and configured properly by launching Lucenia Dashboards. The Machine Learning section should appear under Lucenia plugins.

Accessing ML functionality in Dashboards​

To access ML functionality in Lucenia Dashboards,select Lucenia plugins > Machine Learning.

Machine Learning section in Lucenia dashboards

In the Machine Learning section, you now have access to the Deployed models dashboard.

Deployed models dashboard​

The deployed models dashboard gives admins the ability to check the status of any models stored inside your Lucenia cluster.

The deployed models view.

The dashboard includes the following information about the model:

  • Name: The name of the model given upon upload.
  • Status: The number of nodes for which the model responds.
    • When all nodes are responsive, the status is Green.
    • When some nodes are responsive,the status is Yellow.
    • When all nodes are unresponsive,the status is Red.
  • Model ID: The model ID.
  • Action: What actions you can take with the model.

As of Lucenia 2.6, the only action available is View Status Details, shown in the following image.

You can view status details under actions.

When selected, the Status Details panel appears.

The panel provides the following details inside the panel:

  • Model ID
  • Model status by node: The number of nodes for which the model is responsive.

A list of nodes gives you a view of each node the model is running on, including each node’s Node ID and status, as shown in the following image. This is useful if you want to use the node's Node ID to determine why a node is unresponsive.

The status of each node running the model.

Next steps​

For more information about how to manage ML models in Lucenia, see Using ML models within Lucenia.