Chapter 2. Deploying OpenShift AI in a disconnected environment

Procedure

1. Open a new terminal window.

2. In the OpenShift command-line interface (CLI), log in to your OpenShift Container Platform cluster as a cluster administrator, as shown in the following example:

   $ oc login <openshift_cluster_url> -u <admin_username> -p <password>

3. Create a namespace for installation of the Operator by performing the following actions:

   1. Create a namespace YAML file, for example, rhods-operator-namespace.yaml.

      apiVersion: v1
      kind: Namespace
      metadata:
        name: redhat-ods-operator 1

      1

      redhat-ods-operator is the recommended namespace for the Operator.

   2. Create the namespace in your OpenShift Container Platform cluster.

      $ oc create -f rhods-operator-namespace.yaml

      You see output similar to the following:

      namespace/redhat-ods-operator created

4. Create an operator group for installation of the Operator by performing the following actions:

   1. Create an OperatorGroup object custom resource (CR) file, for example, rhods-operator-group.yaml.

      apiVersion: operators.coreos.com/v1
      kind: OperatorGroup
      metadata:
        name: rhods-operator
        namespace: redhat-ods-operator 1

      1

      You must specify the same namespace that you created earlier in this procedure.

   2. Create the OperatorGroup object in your OpenShift Container Platform cluster.

      $ oc create -f rhods-operator-group.yaml

      You see output similar to the following:

      operatorgroup.operators.coreos.com/rhods-operator created

5. Create a subscription for installation of the Operator by performing the following actions:

   1. Create a Subscription object CR file, for example, rhods-operator-subscription.yaml.

      apiVersion: operators.coreos.com/v1alpha1
      kind: Subscription
      metadata:
        name: rhods-operator
        namespace: redhat-ods-operator 1
      spec:
        name: rhods-operator
        channel: stable 2
        source: redhat-operator-index
        sourceNamespace: openshift-marketplace

      1

      You must specify the same namespace that you created earlier in this procedure.

      2

      For channel, select a value of fast, stable, stable-2-latest, eus-2-latest, or alpha. The following table describes these channels. For more information, including the lifecycle associated with each of the available subscription channels, see Red Hat OpenShift AI Self-Managed Life Cycle.

      Channel	Support	Release frequency	Recommended environment
      fast	One month of full support	Every month	Production environments with access to the latest product features. Select this streaming channel with automatic upgrades to avoid manually upgrading every month.
      stable	Three months of full support	Every three months	Production environments with stability prioritized over new feature availability. Select this streaming channel with automatic upgrades to access the latest stable release and avoid manually upgrading.
      stable-x.y	Seven months of full support	Every three months	Production environments with stability prioritized over new feature availability. Select numbered stable channels (such as stable-2-latest) to plan and execute the upgrade to the next stable release while keeping your deployment under full support.
      eus-x.y	Seven months of full support followed by Extended Update Support for eleven months	Every nine months	Enterprise-grade environments that cannot upgrade within a seven month window. Select this streaming channel if you prioritize stability over new feature availability.
      alpha	One month of full support	Every month	Development environments with early-access features that might not be functionally complete. Select this channel to use early-access features that enable you to test functionality and provide feedback during the development process. Early-access features are not supported with Red Hat production service level agreements (SLAs). For more information about the support scope of Red Hat Technology Preview features, see Technology Preview Features Support Scope. For more information about the support scope of Red Hat Developer Preview features, see Developer Preview Features Support Scope.

      Note

      The embedded and beta channels are legacy channels that will be removed in a future release. Do not select the embedded or beta channels for a new installation of the Operator.

   2. As described in the preceding step, ensure that the subscription channel you specify is appropriate for your organization’s requirements.

   3. Create the Subscription object in your OpenShift Container Platform cluster to install the Operator.

      $ oc create -f rhods-operator-subscription.yaml

      You see output similar to the following:

      subscription.operators.coreos.com/rhods-operator created

Procedure

1. Log in to the OpenShift Container Platform web console as a cluster administrator.
2. In the web console, click Operators → OperatorHub.
3. On the OperatorHub page, locate the Red Hat OpenShift AI Operator by scrolling through available Operators or by typing Red Hat OpenShift AI into the Filter by keyword box.
4. Select the Operator to display additional information.
5. Read the information about the Operator and click Install.

6. For Update channel, select a value of fast, stable, stable-2-latest, eus-2-latest, or alpha. The following table describes these channels. For more information, including the lifecycle associated with each of the available subscription channels, see Red Hat OpenShift AI Self-Managed Life Cycle.

   Channel	Support	Release frequency	Recommended environment
   fast	One month of full support	Every month	Production environments with access to the latest product features. Select this streaming channel with automatic upgrades to avoid manually upgrading every month.
   stable	Three months of full support	Every three months	Production environments with stability prioritized over new feature availability. Select this streaming channel with automatic upgrades to access the latest stable release and avoid manually upgrading.
   stable-x.y	Seven months of full support	Every three months	Production environments with stability prioritized over new feature availability. Select numbered stable channels (such as stable-2-latest) to plan and execute the upgrade to the next stable release while keeping your deployment under full support.
   eus-x.y	Seven months of full support followed by Extended Update Support for eleven months	Every nine months	Enterprise-grade environments that cannot upgrade within a seven month window. Select this streaming channel if you prioritize stability over new feature availability.
   alpha	One month of full support	Every month	Development environments with early-access features that might not be functionally complete. Select this channel to use early-access features that enable you to test functionality and provide feedback during the development process. Early-access features are not supported with Red Hat production service level agreements (SLAs). For more information about the support scope of Red Hat Technology Preview features, see Technology Preview Features Support Scope. For more information about the support scope of Red Hat Developer Preview features, see Developer Preview Features Support Scope.

   Note

   The embedded and beta channels are legacy channels that will be removed in a future release. Do not select the embedded or beta channels for a new installation of the Operator.

7. For Installation mode, observe that the only available value is All namespaces on the cluster (default). This installation mode makes the Operator available to all namespaces in the cluster.
8. For Installed Namespace, select redhat-ods-operator (Operator recommended).
9. Under Update approval, select either Automatic or Manual.

10. Click Install.

    An installation pane opens. When the installation finishes, a checkmark appears beside the Operator name in the installation pane.

Procedure

1. Open a new terminal window.

2. In the OpenShift command-line interface (CLI), log in to your on your OpenShift Container Platform cluster as a cluster administrator, as shown in the following example:

   $ oc login <openshift_cluster_url> -u <admin_username> -p <password>

3. Create a DataScienceCluster object custom resource (CR) file, for example, rhods-operator-dsc.yaml.

   apiVersion: datasciencecluster.opendatahub.io/v1
   kind: DataScienceCluster
   metadata:
     name: default-dsc
   spec:
     components:
       codeflare:
         managementState: Removed
       dashboard:
         managementState: Removed
       datasciencepipelines:
         managementState: Removed
       kserve:
         managementState: Removed 1 2
       kueue:
         managementState: Removed
       modelmeshserving:
         managementState: Removed
       ray:
         managementState: Removed
       workbenches:
         managementState: Removed

   1

   To fully install the KServe component, which is used by the single-model serving platform to serve large models, you must install Operators for Red Hat OpenShift Service Mesh and Red Hat OpenShift Serverless and perform additional configuration. See Serving large models.

   2

   If you have not enabled the KServe component (that is, you set the value of the managementState field to Removed), you must also disable the dependent Service Mesh component to avoid errors. See Disabling KServe dependencies.

4. In the spec.components section of the CR, for each OpenShift AI component shown, set the value of the managementState field to either Managed or Removed. These values are defined as follows:

   Managed

   The Operator actively manages the component, installs it, and tries to keep it active. The Operator will upgrade the component only if it is safe to do so.

   Removed

   The Operator actively manages the component but does not install it. If the component is already installed, the Operator will try to remove it.

   Important

   • To learn how to fully install the KServe component, which is used by the single-model serving platform to serve large models, see Serving large models.
   • To learn how to configure the distributed workloads feature that uses the CodeFlare, KubeRay, and Kueue components, see Configuring distributed workloads.

5. Create the DataScienceCluster object in your OpenShift Container Platform cluster to install the specified OpenShift AI components.

   $ oc create -f rhods-operator-dsc.yaml

   You see output similar to the following:

   datasciencecluster.datasciencecluster.opendatahub.io/default created

Procedure

1. Log in to the OpenShift Container Platform web console as a cluster administrator.
2. In the web console, click Operators → Installed Operators and then click the Red Hat OpenShift AI Operator.

3. Create a DataScienceCluster object to install OpenShift AI components by performing the following actions:

   1. Click the Data Science Cluster tab.
   2. Click Create DataScienceCluster.

   3. For Configure via, select YAML view.

      An embedded YAML editor opens showing a default custom resource (CR) for the DataScienceCluster object.

   4. In the spec.components section of the CR, for each OpenShift AI component shown, set the value of the managementState field to either Managed or Removed. These values are defined as follows:

      Managed

      The Operator actively manages the component, installs it, and tries to keep it active. The Operator will upgrade the component only if it is safe to do so.

      Removed

      The Operator actively manages the component but does not install it. If the component is already installed, the Operator will try to remove it.

      Important

      • To learn how to install the KServe component, which is used by the single-model serving platform to serve large models, see Serving large models.
      • If you have not enabled the KServe component (that is, you set the value of the managementState field to Removed), you must also disable the dependent Service Mesh component to avoid errors. See Disabling KServe dependencies.
      • To learn how to configure the distributed workloads feature that uses the CodeFlare and KubeRay components, see Configuring distributed workloads.
4. Click Create.

Procedure

1. Log in to the OpenShift Container Platform web console as a cluster administrator.
2. In the web console, click Operators → Installed Operators and then click the Red Hat OpenShift AI Operator.
3. Click the Data Science Cluster tab.
4. On the DataScienceClusters page, click the default object.

5. Click the YAML tab.

   An embedded YAML editor opens showing the custom resource (CR) file for the DataScienceCluster object.

6. In the spec.components section of the CR, for each OpenShift AI component shown, set the value of the managementState field to either Managed or Removed. These values are defined as follows:

   Note

   If a component shows with the component-name: {} format in the spec.components section of the CR, the component is not installed.

   Managed

   The Operator actively manages the component, installs it, and tries to keep it active. The Operator will upgrade the component only if it is safe to do so.

   Removed

   The Operator actively manages the component but does not install it. If the component is already installed, the Operator will try to remove it.

   Important

   • To learn how to install the KServe component, which is used by the single-model serving platform to serve large models, see Serving large models.
   • If you have not enabled the KServe component (that is, you set the value of the managementState field to Removed), you must also disable the dependent Service Mesh component to avoid errors. See Disabling KServe dependencies.

   • If they are not already present in the CR file, you can install the CodeFlare, KubeRay, and Kueue components by adding the codeflare, ray, and kueue entries to the spec.components section of the CR and setting the managementState field for the components to Managed.
   • To learn how to configure the distributed workloads feature that uses the CodeFlare, KubeRay, and Kueue components, see Configuring distributed workloads.

7. Click Save.

   For any components that you updated, OpenShift AI initiates a rollout that affects all pods to use the updated image.

Procedure

1. Log in to the OpenShift web console as a cluster administrator.
2. In the web console, click Operators → Installed Operators and then click the Red Hat OpenShift AI Operator.

3. Disable the OpenShift Service Mesh component as follows:

   1. Click the DSC Initialization tab.
   2. Click the default-dsci object.
   3. Click the YAML tab.

   4. In the spec section, add the serviceMesh component (if it is not already present) and configure the managementState field as shown:

      spec:
       serviceMesh:
         managementState: Removed

   5. Click Save.

Verification

1. In the web console, click Operators → Installed Operators and then click the Red Hat OpenShift AI Operator.

   The Operator details page opens.

2. In the Conditions section, confirm that there is no ReconcileComplete condition with a status value of Unknown.