NetApp AIPod Mini Environment

NetApp AIPod Mini Sandbox is a hands-on, validated reference architecture for deploying enterprise RAG solutions quickly and securely. It combines Intel Xeon 6 compute, NetApp AFF storage, Intel OPEA Enterprise RAG, and Kubernetes to deliver a production-ready generative AI platform.

The lab allows for the following: 

• Provides a complete stack for enterprise AI using private data—without model retraining.
• Supports automated, one-click deployment with Ansible.
• Includes performance optimizations such as HPA and NUMA-aware CPU pinning.
• Delivers enterprise security with Keycloak IAM, RBAC, and guardrails.
• Offers observability with Prometheus, Grafana, Tempo, and Loki.
• Features the ChatQA reference app, demonstrating full RAG flow:
  • ingestion → chunking → embeddings → vector retrieval → LLM response.
• Enables practical experience building domain-specific, compliant AI assistants for real enterprise use cases.

This lab is designed for AI decision makers, data engineers, MLOps practitioners, and IT professionals who want to understand and deploy enterprise-grade RAG solutions. Whether you're evaluating infrastructure for production AI workloads, learning about generative AI deployment patterns, or exploring how to operationalize large language models with proprietary data, this sandbox provides the foundation you need.

Objectives

Through the course of this lab you will gain hands-on experience with managing an enterprise RAG solution on the NetApp AIPod Mini architecture.

Here are the goals of this lab:
✅ Understand the NetApp AIPod Mini architecture and components
✅ Explore the OPEA (Open Platform for Enterprise AI) framework
✅ Understand vector databases and embedding services
✅ Deploy and test the ChatQnA application
✅ Explore monitoring and observability with Grafana and Prometheus
✅ Implement enterprise security features (IAM, guardrails, RBAC)
✅ Test RAG inferencing with your own enterprise documents