AI-Assisted Installation
This repository includes a skill definition that provides AI-assisted MaaS installation. The /install-maas skill wraps the same setup-maas.sh script used in the Automated Setup, letting your AI coding agent handle cluster detection, error diagnosis, and interactive troubleshooting.
The skill works with any AI coding tool that supports skill definitions:
-
Other AI coding agents with skill support
All file paths and oc apply commands in this guide are relative to the rhoai-maas-guide repository root. Make sure you have cloned it and are working from its root directory (see Getting Started).
|
| This guide is not a replacement for the official Red Hat OpenShift AI Models as a Service documentation. It is a companion resource with opinionated Kustomize manifests and automation scripts to accelerate deployment. |
Prerequisites
-
An AI coding tool installed (see list above)
-
ocCLI authenticated as cluster-admin -
This repository cloned locally
Usage
Open the repository in your AI coding tool and invoke the skill:
/install-maas
Arguments
All arguments from setup-maas.sh are supported:
/install-maas --model simulator
/install-maas --from-phase 4
/install-maas --with-observability
/install-maas --skip-models --skip-verify
| Option | Description |
|---|---|
|
Model to deploy: |
|
Start from phase N (0-7) |
|
Skip Phase 5 (model deployment) |
|
Skip Phase 6 (verification) |
|
Also run Phase 7 (COO + telemetry) |
What the Skill Does
The skill runs ./scripts/setup-maas.sh from the repository root with the provided arguments. Your AI coding agent monitors the output, detects failures, and can help diagnose issues interactively.
The skill has access to oc, envsubst, curl, jq, and other CLI tools needed for MaaS deployment.