Setup AI Services

AI Services Installation Guide for runtime OpenShift

This guide provides step-by-step instructions for installing and configuring AI Services in a OpenShift runtime. Ensure all prerequisites are met before starting.

Instructions

  1. Pull in AI Services binary

    Download the latest AI Services binary from the releases page.

    • Install on Linux
      # Detect system architecture
      ARCH=$(uname -m)
      
      # Download the correct binary based on architecture
      if [ "$ARCH" = "x86_64" ]; then
        curl -Lo ./ai-services https://github.com/IBM/project-ai-services/releases/download/v0.3.0/ai-services-linux-amd64
      elif [ "$ARCH" = "ppc64le" ]; then
        curl -Lo ./ai-services https://github.com/IBM/project-ai-services/releases/download/v0.3.0/ai-services-linux-ppc64le
      else
        echo "Unsupported architecture: $ARCH"
      fi
      
      # Make the binary executable
      chmod +x ./ai-services
      
      # Move it to a directory in PATH
      sudo mv ./ai-services /usr/local/bin/ai-service
    • Install on MacOS
      # Detect system architecture
      ARCH=$(uname -m)
      
      # Download the correct macOS binary
      if [ "$ARCH" = "arm64" ]; then
       curl -Lo ./ai-services https://github.com/IBM/project-ai-services/releases/download/v0.3.0/ai-services-darwin-arm64
      elif [ "$ARCH" = "x86_64" ]; then
       curl -Lo ./ai-services https://github.com/IBM/project-ai-services/releases/download/v0.3.0/ai-services-darwin-amd64
      else
       echo "Unsupported architecture: $ARCH"
      fi
      
      # Make the binary executable
      chmod +x ./ai-services
      
      # Move it to a directory in PATH
      sudo mv ./ai-services /usr/local/bin/ai-services
  2. Export or Set Your Kubeconfig

    1. If using an existing kubeconfig file:
      export KUBECONFIG=/path/to/your/kubeconfig
    2. To authenticate using the OpenShift CLI:
      oc login https://api.<cluster-domain>:6443 \  --username=<user> \  --password=<password>
  3. Run the binary to get started

    $ ai-services --help
    A CLI tool for managing AI Services infrastructure.
    
    Usage:
      ai-services [command]
    
    Available Commands:
      application Deploy and monitor the applications
      bootstrap   Initializes AI Services infrastructure
      completion  Generate the autocompletion script for the specified shell
      help        Help about any command
      version     Prints CLI version with more info
    
    Flags:
      -h, --help      help for ai-services
      -v, --version   version for ai-services
    
    Use "ai-services [command] --help" for more information about a command.
     

Bootstrap the environment

First-time setup requires bootstrapping the environment before you proceed to create an application.

ai-services bootstrap --runtime openshift

When running ai-services bootstrap on the OpenShift runtime, AI Services automatically installs and configures several required OpenShift operators. These operators enable scheduling, hardware discovery, certificate management, service mesh integration, and Spyre accelerator support.

Operators installed/configured by bootstrap
  • Cert‑Manager Operator
  • IBM Spyre Operator
  • Node Feature Discovery (NFD) Operator
  • Red Hat OpenShift AI Operator
  • Red Hat OpenShift Service Mesh 3 Operator
  • Secondary Scheduler Operator
Use the OpenShift Web Console to manage installed operators.

Next Steps

Deploy Digital Assistant effortlessly using pre-built templates and a streamlined setup process.