Course · Interview foundations
RAG for Data Engineers
Free RAG course for AI engineers: how retrieval-augmented generation works, chunking, embeddings, hybrid search, reranking and evaluation, with runnable code.
- Lessons
- 6
- Interview questions
- 0
- Projects & case studies
- 1
- Reading time
- ~1 h
Your progress
Saved in this browser onlyCourse structure
- 1 lessonStart hereThe complete overview of the course in one read.
- 4 lessonsIntermediatePatterns used in production pipelines.
- 1 lessonAdvancedPerformance, internals and edge cases.
Practise
Lessons
Work through the lessons in order. Completed lessons show a tick; lessons you have opened are outlined.
Start here
The complete overview of the course in one read.
Intermediate
Patterns used in production pipelines.
- Chunking Strategies for RAG: How to Split DocumentsHow to split documents for RAG: fixed-size chunks with overlap, splitting by headings, adding titles to chunks, and choosing a chunk size, with runnable Python.
- Hybrid Search and Reranking for RAG, Explained with CodeWhy RAG systems combine keyword search (BM25) with semantic search, how reciprocal rank fusion merges them, and what rerankers add, with runnable Python.
- How to Evaluate a RAG System: Retrieval and Answer QualityHow to evaluate a RAG system: build a test set, measure retrieval with recall@k and MRR, check answers for faithfulness, and find fixes, with runnable Python.
- Vector Databases and Vector Indexes Explained for RAGWhat a vector database does, how approximate indexes like IVF and HNSW trade a little accuracy for a lot of speed, and how to choose one, with runnable code.
Projects and case studies
Apply what you learned and prepare material to discuss in interviews.
Projects
Resources
Related courses
- LLMsFree LLM course for AI engineers: how large language models work, tokens, embeddings, attention, generation and prompting, explained simply with runnable code.
- PythonFree Python course for Data Engineering: generators, CSV and JSON files, APIs, pandas, error handling and pytest, with runnable code and interview questions.
