Chapter 4. Creating project-scoped resources

Procedure

1. Log in to the OpenShift console as a cluster administrator.

2. Copy the YAML code to create the resource.

   You can get the YAML code from a trusted source, such as an existing resource, a Git repository, or documentation.

   For example, you can copy the YAML code from an existing resource, as follows:

   1. In the Administrator perspective, click Home Search.

   2. From the Project list, select the appropriate value.

      To limit the search to global OpenShift AI resources only, select the redhat-ods-applications project.

   3. In the Resources list, search for the relevant resource type, as follows:

      • For workbench images, search for ImageStream.
      • For hardware profiles, search for HardwareProfile.
      • For accelerator profiles, search for AcceleratorProfile.
      • For serving runtimes, search for Template. From the resulting list, find the templates that have the objects.kind specification set to ServingRuntime.
   4. Select a resource, and click the YAML tab.
   5. Copy the YAML content, and click Cancel.
3. From the Project list, select the target project name. Note the spelling.
4. From the toolbar, click the + icon to open the Import YAML page.
5. Paste the relevant YAML content into the code area.
6. Edit the metadata.namespace value to specify the name of the target project.
7. If necessary, edit the metadata.name value to ensure that the resource name is unique within the specified project.

8. Optional: Edit the resource name that is displayed in the OpenShift AI console, as follows:

   • For workbench images, edit the metadata.annotations.opendatahub.io/notebook-image-name value.
   • For hardware profiles and accelerator profiles, edit the spec.displayName value.
   • For serving runtimes, edit the objects.metadata.annotations.openshift.io/display-name value.
9. Click Create.

Verification

1. Log in to the OpenShift AI console as a regular user.

2. Verify that the project-scoped resource is shown in the specified project only:

   • For workbench images, hardware profiles, and accelerator profiles, see Creating a workbench.
   • For serving runtimes, see Deploying models on the single-model serving platform.