configuring-the-model-registry-component.adoc

Configuring the model registry component

• {org-name} Authorino Operator (Technical Preview)

• {org-name} OpenShift Serverless Operator

• {org-name} OpenShift Service Mesh Operator

Prerequisites

• You have cluster administrator privileges for your {openshift-platform} cluster.

• You have access to the data science cluster.

Procedure

1. In the {openshift-platform} console, click Operators → Installed Operators.

2. Click the Data Science Cluster tab.

3. Click the default instance name (for example, default-dsc) to open the instance details page.

4. Click the YAML tab to show the instance specifications.

5. Find the spec.components section, and then add or update it to include the following modelregistry component entry, with the managementState field set to Managed, and the registriesNamespace field set to rhoai-model-registries:

    modelregistry:
       managementState: Managed
       registriesNamespace: rhoai-model-registries

6. Click Save.

Verification

• Confirm that the model registry namespace was created successfully:

  1. In the OpenShift console, click Home → Projects.

  2. Confirm that the rhoai-model-registries namespace appears in the Projects drop-down list.

• Check the status of the model-registry-operator-controller-manager pod:

  1. Click Workloads → Deployments.

  2. Search for the model-registry-operator-controller-manager deployment.

  3. Check the status:

     1. Click the deployment name to open the deployment details page.

     2. Click the Pods tab.

     3. View the pod status.

        When the status of the model-registry-operator-controller-manager-<pod-id> pod is Running, the pod is ready to use.

Next step

{productname-short} administrators can create, delete, and manage permissions for model registries. For more information, see Managing model registries.