Home > AI Solutions > Artificial Intelligence > Guides > Design Guide—Implementing a Digital Assistant with Red Hat OpenShift AI on Dell APEX Cloud Platform > Digital assistant deployment and configuration
Deploying a digital assistant involves multiple steps, which includes preparing the environment and validating, deploying, and configuring the components. In this section we will briefly discuss the digital assistant deployment process.
The following sections describe perquisites to the solution deployment.
OpenShift Container Platform provides an internal, integrated container image registry that can be deployed to locally manage container images in the Red Hat OpenShift Container Platform cluster environment.
Follow the steps described in the GitHub repository to configure OpenShift Internal registry.
The Node Feature Discovery Operator (NFD) manages the detection of hardware configuration and features in an OpenShift Container Platform cluster by labeling the nodes with node-specific attributes, such as PCI cards, kernel, operating system version, and so on.
Follow the steps described in GitHub repository to Install NFD Operator.
The NVIDIA GPU Operator uses the operator framework available within Kubernetes to automate the management of all NVIDIA software components needed to provision GPU. The Node Feature Discovery (NFD) Operator is a prerequisite for the NVIDIA GPU Operator.
Follow the steps described in GitHub repository to Install Nvidia GPU Operator.
Red Hat OpenShift AI is an open-source machine learning platform. Red Hat OpenShift AI provides pre-configured tools and libraries that allows data scientists and developers to rapidly train, deploy, and monitor ML workloads and models on-premises and in the public cloud.
Installing Red Hat OpenShift AI involves the following high-level tasks:
For more information regarding installing Red Hat OpenShift AI, see the Red Hat web page.