Skip to main content
🎤 Luca Berton is speaking at Red Hat Summit & KubeCon EU 2026!Learn more →
intermediate

GenAI Ops on Your Mac: RAG, Guardrails and Evaluations

Build a handbook assistant that cites its sources, measure retrieval quality, and add guardrails and evaluations before release.

6 lessons21mUpdated November 2026

What you'll learn

  • Index and query documents with Chroma and Ollama
  • Compare chunking, filters, and reranking
  • Run evaluation gates in CI and review the results

Who this is for

  • • DevOps engineers deepening their expertise
  • • SREs building production-grade systems
  • • Backend developers expanding into infrastructure

Prerequisites

  • • An Apple Silicon Mac, Python, and Ollama.

Course content

2 modules, 6 lessons, 21m of video

Module 1

3 lessons, 11 min
1

5 min

Local embeddings, a Chroma vector store and a chat model, all on your Mac.

2
Choose what to index, and how to chunk it

4 min

Chunk size, overlap, metadata filters and re-indexing, measured on the same questions.

3
Retrieval quality: top-k, reranking and I don't know

4 min

How many chunks to send, whether a reranker helps, and a minimum score.

Module 2

3 lessons, 10 min
4
Guardrails with NeMo Guardrails

4 min

Input and output rails on the local model: off-topic, jailbreak, personal data, secrets.

5
Evaluate before you ship

4 min

Faithfulness and answer relevancy with Ragas, judged by the local model.

6
Evaluations in CI

3 min

Minimum scores and a baseline, run on every change by a runner on the Mac.

Get started

Start Free Lesson

First lesson is always free — no signup required

This course includes

6 hands-on lessons
Intermediate level
21m total
Final assessment

Want all courses?

See Pro plan →

Your instructor

Luca Berton

Founder and CEO, Open Empower. About the author

More in AI Agents

All courses in this track