ai-center
2022.4
true
- Getting Started
- Network requirements
- Single-node requirements and installation
- Multi-node requirements and installation
- Post-installation
- Accessing AI Center
- Provision an AI Center tenant
- Updating Orchestrator and Identity Server certificates
- Resizing PVC
- Adding a new node to the cluster
- ML packages offline installation
- Configuring the cluster
- Configuring the FQDN post-installation
- Backing up and restoring the cluster
- Using the monitoring stack
- Setting up a Kerberos authentication
- Provisioning a GPU
- Using the configuration file
- Node scheduling
- Migration and upgrade
- Basic Troubleshooting Guide
Upgrading AI Center
AI Center Installation Guide
Last updated Jun 6, 2024
Upgrading AI Center
To upgrade AI Center from 2021.10 to 2022.4 or from one minor version to another (for example, from 2022.4.1 to 2022.4.2), use the procedures from this page.
Note: Make sure that there are no new deployments while upgrading.
Important:
If you upgrade from AI Center 2021.10.3 or 2021.10.4 to a newer version, a downgrade from Ceph 16.2.6 to 15.2.9 is required to prevent data corruption.
For more information, check the Downgrading Ceph from 16.2.6 to 15.2.9 page.
Note:
- Upgrading UiPath AI Center enables maintenance mode on the cluster, which causes downtime for the entire upgrade duration.
- Make sure that there are no new deployments while upgrading.
- Make sure you meet the hardware and software requirements for new AI Center version single-node or multi-node .
- Download the required installer and bundle files:
Installation type | Files to download |
---|---|
Online | sf-installer.zip – Mandatory. See sf-installer.zip for download instructions. |
Offline |
|
The following illustration shows the steps you need to take for a successful upgrade operation.
For a complete upgrade operation, follow these steps:
- Configure a backup before upgrading the cluster to a new version, if possible.
- Enable maintenance mode on the cluster, by bringing down the cluster network, to avoid any writes during upgrade. This step ensures the upgrade is consistent.
- Upgrade Kubernetes and other infrastructure components on all the cluster nodes.
- For offline installations, hydrate Private Docker Registry with the new container images.
- Upgrade the fabric and shared components on the cluster.
- Upgrade the services.
- Bring back the cluster by disabling the maintenance mode on the cluster.