Skip to main content

Deploy PaletteAI

This is the final guide in the PaletteAI appliance installation process. In this guide, you will trigger the actual cluster creation process and install PaletteAI on the cluster.

Prerequisites​

Deploy Cluster and Install PaletteAI​

  1. Log in to Local UI on the leader host. Use the IP address of the leader host and port 5080 to access the Local UI. For example, if the IP address of the leader host is 10.10.10.10, access Local UI at https://10.10.10.10:5080.

  2. Verify all linked Edge hosts are ready and the content is synced.

    All nodes are ready and the content is synced

  3. From the left main menu, select Cluster > Create cluster.

  4. Assign the cluster a name and provide tags, if desired. Select Next.

  5. The Cluster Profile screen displays the imported cluster configuration. Review the configuration and select Next.

  6. Complete all applicable fields on the Profile Config screen. Refer to the following table for guidance on certain fields. Select Next when finished.

    FieldDescriptionExample
    Root DomainThe domain you provided in Prepare Helm Chart Values section. Do not include the network protocol (http/https). This value will be added to apiServer's certSAN field. Do not add any paths to the URL.example.acme.org
    Ingress DomainThe same value as Root Domain.example.acme.org
    OCI Pack Registry PasswordThe password for the OCI registry. Use the OCI password you configured in the fleetConfig and hue sections of the PaletteAI Helm chart values.yaml file.Replac3MeWithaGoodPassword!
    Value File URLThe URL of the file server hosting the values.yaml file.https://mycompany.com:8443/mural-values.yaml
    Mural Install VersionThe desired PaletteAI version. This must match value used for global.muralVersion in your Helm chart. Use semantic versioning.0.5.0
    Admin Grafana PasswordThe password for the Grafana administrator user. This is used to access the Grafana dashboard.""

  7. On the Cluster Config screen, specify the any of the following, as necessary. Select Next when finished.

    • Network Time Protocol (NTP) server
    • SSH keys
    • VIP address to assign to the cluster

    warning

    Do not assign the leader node's IP address as the VIP address. It must be a different IP address.

  8. On the Node Config screen, add three control plane nodes and three worker nodes. There are additional options that you can configure. The following tables describe additional configuration options. Select Next when finished.

    Node Pool Options​

    OptionDescriptionTypeDefault
    Node pool nameThe name of the control plane node pool. This is used to identify the node pool in .Stringcontrol-plane-pool
    Allow worker capabilityAllow applications to be scheduled on this control plane node pool. This option must be enabled.Booleantrue
    Additional Kubernetes Node Labels (Optional)Tags for the node pool in key:value format. These tags are used to filter and search for node pools in .StringNo default
    TaintsTaints for the node pool in key=value:effect format. Taints are used to prevent pods from being scheduled on the nodes in this pool unless they tolerate the taint.- Key - String
    - Value - String
    - Effect - String (enum)    		No default
    Pool Configuration​

    The following options are available for both the control plane and worker node pools. Configure these options to your requirements. You can also remove worker pools if not needed.

    OptionDescriptionTypeDefault
    ArchitectureThe CPU architecture of the nodes. This is used to ensure compatibility with the applications operating on the nodes.String (enum)amd64
    Add Edge HostsSelect Add Item and choose the other hosts that you installed using the ISO. These hosts will be added to the node pool. Each pool must contain at least one node.N/A- Control Plane Pool - Current host selected
    - Worker Pool - No host selected
    NIC NameThe name of the network interface card (NIC) to use for the nodes. Leave on Auto to let the system choose the appropriate NIC, or select one manually from the drop-down menu.N/AAuto
    Host Name (Optional)The hostname for the nodes. This is used to identify the nodes in the cluster. A generated hostname is provided automatically, which you can adjust to fit your requirements.Stringedge-*

    Adding Control Plane and Worker Nodes

  9. On the Review screen, ensure that your configuration is correct. If you need to make changes, select the applicable section on the left sidebar to go back and edit the configuration.

    When you are satisfied with your configuration, select Deploy Cluster to begin the cluster creation process.

    The cluster creation process takes approximately 30 to 45 minutes to complete. You can monitor the cluster's progress by navigating to the left main menu and selecting Cluster > Overview. The cluster is fully provisioned when the status changes to Running and the health status is Healthy.

Validation​

  1. Log in to Local UI on the leader host.

  2. Verify the cluster is running and the health status is Healthy. Download the kubeconfig file for the cluster.

  3. Set up the kubeconfig file to access the cluster. This will allow you to use kubectl to access the cluster.

    export KUBECONFIG=path/to/kubeconfig

  4. Verify all pods are in the Running state.

    kubectl get pods --all-namespaces

  5. Verify you can access the following components. Replace <domain-or-vip-address> with the domain or VIP you configured for the cluster.

    • Palette system console - https://<domain-or-vip-address>/system.
    • Palette - https://<domain-or-vip-address>
    • PaletteAI - https://<domain-or-vip-address>/ai

Next Steps​

Once Palette and PaletteAI are installed on your new cluster, you must integrate Palette with PaletteAI using PaletteAI's Settings resource. This resource requires a Palette tenant, project, and API key in order to communicate with Palette and deploy AI/ML applications to the appropriate location.

Proceed to the Integrate with Palette guide to learn how to prepare your Palette environment.