Code and examples from Practical RHEL AI — Designing, Deploying and Scaling AI Solutions with Red Hat Enterprise Linux by Luca Berton (Apress, 2026).
🌐 Book website: lucaberton.com/practical-rhel-ai
| Chapter | Title | Code |
|---|---|---|
| 1 | Introduction to RHEL AI | — (no code) |
| 2 | Setting Up RHEL AI | chapter-02.md |
| 3 | Exploring Core Components | chapter-03.md |
| 4 | Advanced Features of RHEL AI | chapter-04.md |
| 5 | Developing Custom AI Applications | chapter-05.md |
| 6 | Monitoring and Maintenance | chapter-06.md |
| 7 | Use Cases and Best Practices | chapter-07.md |
| 8 | Future Trends in RHEL AI | chapter-08.md |
| 9 | Community and Support | — (no code) |
Each chapter file contains only the code blocks and command-line examples from the book, with section headings preserved for context. Topics covered:
- Ch 2 —
ilabCLI usage, subscription-manager repos, kickstart configs, cloud provider setup (AWS, Azure, GCP, IBM Cloud), GPU verification - Ch 3 — InstructLab skill recipes (
qna.yaml), taxonomy structure, SDG, model serving, chat - Ch 4 — DeepSpeed training pipeline, Ansible playbooks, GPU acceleration, scale-out topologies
- Ch 5 — Custom model development, InstructLab bootstrap, taxonomy curation, model evaluation
- Ch 6 — BLEU/BERTScore evaluation, Prometheus/Grafana monitoring, SLO verification, GPU telemetry
- Ch 7 — RAG with ChromaDB, REST API (FastAPI), LangChain, CrewAI agents, vLLM tuning, Ansible automation
- Ch 8 — SPDX lineage YAML, governance-as-code CI/CD, explainability pipelines
Book content is copyright © 2026 by Luca Berton, published by Apress.