deploy-existing-openshift

Deploy the private AI serving stack on an existing OpenShift cluster using Helm.

8|4|Updated Jun 30, 2026

Search Tags:#deployment #helm #guardrails #openshift #vllm #llm-d

Ready to run

npx skills add https://github.com/rh-ai-quickstart/private-coding-assistant --skill deploy-existing-openshift

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deploy-existing-openshift
Source: https://github.com/rh-ai-quickstart/private-coding-assistant/tree/main/.cursor/skills/deploy-existing-openshift
Command: npx skills add https://github.com/rh-ai-quickstart/private-coding-assistant --skill deploy-existing-openshift

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you deploy and operate the private AI serving stack for a coding assistant on an existing OpenShift cluster without exposing source code to external model providers.

Core Features & Use Cases

Cluster deployment: Installs the AI serving components with Helm on a running OpenShift environment.
Operational validation: Checks cluster access, namespace ownership, and gateway prerequisites before deployment.
Production workflow support: Handles existing-cluster adoption, ARO-specific overrides, optional observability, guardrails, and teardown guidance.
Use Case: Use this Skill when you need to redeploy the model serving stack, enable optional MCP or guardrails, or safely remove an existing installation.

Quick Start

Ask me to deploy the private AI serving stack on your existing OpenShift cluster and I will verify prerequisites, choose the correct namespaces, and run the appropriate Helm-based deployment path.

Frequently Asked Questions about deploy-existing-openshift

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I deploy a private AI coding assistant on an existing OpenShift cluster?▼

Deploying a private AI model serving stack on OpenShift uses Helm to install llm-d, vLLM, and gateway components. The workflow verifies cluster access, manages namespaces, and applies cluster-specific overrides for ARO or shared Kuadrant environments.

What prerequisites do I need to run an llm-d and vLLM deployment on OpenShift?▼

Deploying llm-d and vLLM on OpenShift requires active cluster access, namespace management permissions, and Helm for release orchestration. The deployment process validates gateway prerequisites and namespace ownership before proceeding with component installation.

Can I enable guardrails and observability when deploying vLLM on OpenShift?▼

You can enable optional guardrails and observability workflows when deploying vLLM on OpenShift. The Helm-based deployment supports configuring these production features alongside the core model serving stack components during installation or redeployment.

What is the best way to redeploy an AI model serving stack on OpenShift without external provider exposure?▼

Redeploying an AI model serving stack on OpenShift without external provider exposure involves using Helm to manage llm-d and vLLM releases. This approach handles existing-cluster adoption and applies ARO-specific overrides to maintain a fully private environment.

How do I safely tear down a private LLM deployment from an OpenShift cluster?▼

Safely tearing down a private LLM deployment from OpenShift involves following specific teardown guidance to cleanly remove Helm releases. This ensures llm-d, vLLM, and gateway components are properly uninstalled from their managed namespaces without leaving residual resources.

Does deploying llm-d on OpenShift support ARO-specific configurations?▼

Deploying llm-d on OpenShift supports ARO-specific configurations through cluster-specific overrides. The Helm-based deployment workflow applies these overrides to accommodate ARO environments and shared Kuadrant setups during the installation process.