// Stage 8 · RAG, Agents & AI Engineering
RAG Engineering & Evaluation
Chunking, query rewriting, HyDE, GraphRAG, citations and evaluation metrics.
about 8 hours4 algorithms3 paperslesson text ready
01Goals
- Build an end-to-end RAG system
- Experiment with chunking and query rewriting
- Evaluate faithfulness and relevance with tools such as RAGAS
Do these first: Embeddings, Vector Search & Reranking
02Read on this site
03Algorithms to master
Each card has the original paper, prerequisites and resources.
04Must-read papers
05Courses & videos
- developers.llamaindex.ai ↗Official docsEN
- docs.ragas.io ↗Official docsEN
- microsoft.github.io ↗Official docsEN
- OpenAI Cookbook ↗Official docsEN
06Hands-on: project, code & exercises
Free, official or author-published pages. Most run in the browser or on a free Colab GPU.
PROJECT
Build RAG Q&A over a set of product docs and record evaluation scores for three chunking strategies and two retrieval methods.
- 1Hugging Face Open-Source AI Cookbook ↗Notebooks
Run the Cookbook’s advanced-RAG and RAG-evaluation notebooks.
- 2developers.llamaindex.ai ↗Official docs
Build a Q&A system over your own documents with the starter tutorial.
- 3
07Self-test
Answer in your head, then open to check.
What does RAG “faithfulness” measure?
Whether the answer is supported by the retrieved content.
What kind of question is GraphRAG good at?
Thematic questions that need a global summary.
Problems with chunks that are too large or too small?
Too large adds noise; too small loses context.
On these routes: Everyday Users · Application Developers · Product Managers & Leaders · Domain Scientists