Prerequisites

Ensure that all AI Services prerequisites are fulfilled before proceeding with application creation. Refer to the Configuration and Installation section. AI Services supports two runtime environments: Podman and OpenShift.

Hardware Requirements

Before deploying Digital Assistant, ensure the following hardware components are available and configured:

Runtime: OpenShift
  1. Storage: 256 GB
  2. Memory: 256 GB
  3. CPU: 24 cores (48 vCPU with SMT2) - SMT2 is recommended.
  4. Spyre Cards(5):
    • 4 cards for Granite Instruct model
    • 1 card for Re-ranker model

    Ensure that the worker node can allocate a minimum of 5 Spyre cards

Runtime: Podman
  1. Storage:

    The following values specify the minimum required disk capacity. The directories do not need separate disks; if they share a filesystem, ensure the total available capacity meets the combined requirement. Additional capacity is recommended for production use.

    • /var/lib/containers1 : 128 GB (container images and logs)
    • /var/lib/ai-services1 : 64 GB+ (AI models, caddy assets; scale as needed)

    If the required storage is not available, see the Troubleshooting Storage Issues for workarounds.

  2. Memory: 256 GB
  3. CPU: 15 cores for high concurrency and AI workloads
  4. Spyre Cards(5)
    • 4 cards for Granite Instruct model
    • 1 card for Re-ranker model
Runtime: Podman - CPU-only
  1. Storage:

    The following values specify the minimum required disk capacity. The directories do not need separate disks; if they share a filesystem, ensure the total available capacity meets the combined requirement. Additional capacity is recommended for production use.

    • /var/lib/containers1 : 128 GB (container images and logs)
    • /var/lib/ai-services1 : 64 GB+ (AI models, caddy assets; scale as needed)

    If the required storage is not available, see the Troubleshooting Storage Issues for workarounds.

  2. Memory: 256 GB
  3. CPU: 15 cores for high concurrency and AI workloads
Runtime: Podman - PowerVS-IBM watsonx
  1. Storage:

    The following values specify the minimum required disk capacity. The directories do not need separate disks; if they share a filesystem, ensure the total available capacity meets the combined requirement. Additional capacity is recommended for production use.

    • /var/lib/containers1 : 128 GB (container images and logs)
    • /var/lib/ai-services1 : 64 GB+ (AI models, caddy assets; scale as needed)

    If the required storage is not available, see the Troubleshooting Storage Issues for workarounds.

  2. Memory: 75 GB
  3. CPU: 10 cores for high concurrency and AI workloads
Note: CPU-only deployments are supported for Digital Assistant with the Podman runtime.
1/var/lib is the default base directory for Podman runtime. The base directory can be overridden during initial catalog configuration using the --basedir flag.