Chapter 6. Creating project-scoped resources for your project
As an OpenShift AI user, you can access global resources in all OpenShift AI projects, but you can access project-scoped resources within the specified project only.
As a user with access permissions to a project, you can create the following types of project-scoped resources for your OpenShift AI project:
- Workbench images
- Model-serving runtimes for KServe
- Hardware profiles
All resource names must be unique within a project.
A user with access permissions to a project can create project-scoped resources for that project, as described in Creating project-scoped resources.
Prerequisites
- You can access the OpenShift console.
-
An OpenShift AI administrator has set the
disableProjectScopeddashboard configuration option tofalse, as described in Customizing the dashboard. - You can access a project in the OpenShift AI console.
You have example YAML code for the type of resource that you want to create.
You can get the YAML code from a trusted source, such as an existing project-scoped resource, a Git repository, or documentation. Alternatively, you can contact your cluster administrator to request the relevant YAML code.
Procedure
- Log in to the OpenShift console.
From a trusted source, copy the YAML code that you want to use for your project resource.
For example, if you can access an existing project-scoped resource in one of your projects, you can copy the YAML code as follows:
-
In the Administrator perspective, click Home
Search. - From the Projects list, select the appropriate project.
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 serving runtimes, search for
Template. From the resulting list, find the templates that have theobjects.kindspecification set toServingRuntime.
-
For workbench images, search for
- Select a resource, and then click the YAML tab.
- Copy the YAML content, and then click Cancel.
-
In the Administrator perspective, click Home
- From the Project list, select your project name.
- From the toolbar, click the + icon to open the Import YAML page.
- Paste the example YAML content into the code area.
-
Edit the
metadata.namespacevalue to specify the name of your project. -
If necessary, edit the
metadata.namevalue to ensure that the resource name is unique within the specified project. 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-namevalue. -
For hardware profiles, edit the
spec.displayNamevalue. -
For serving runtimes, edit the
objects.metadata.annotations.openshift.io/display-namevalue.
-
For workbench images, edit the
- Click Create.
Verification
- Log in to the OpenShift AI console.
Verify that the project-scoped resource is shown in the specified project:
- For workbench images, when you create a workbench in the project, as described in Creating a workbench, the workbench image that you added is available in the Image selection list.
- For model-serving runtimes, see Deploying models.
- For workbench images, when you create a workbench in the project, as described in Creating a workbench, the workbench image that you added is available in the Image selection list.
- For serving runtimes, see Deploying models.