Home / Topics

02

RAG & Vector Search

Retrieval-augmented generation end to end: chunking, embeddings, indexes, reranking and evaluation.

Start reading Take the quiz Flashcards

Guides

01

The RAG pipeline end to end

Ingestion, chunking, embedding, retrieval, reranking and generation, plus where each step goes wrong.

 11 min 02

Embeddings and vector indexes

Similarity metrics, exact vs. approximate search, HNSW and IVF, quantization, and filtering.

 9 min 03

Evaluating RAG systems

Separate retrieval metrics from generation metrics, build a golden set, and use LLM-as-judge carefully.

 7 min

Interview questions

All 12 with answers →
  1. Walk me through how you'd build a RAG system over a company's internal docs.
  2. How do you choose chunk size?
  3. Why use hybrid search instead of only vector search?
  4. What is a reranker and why is it more accurate than the first-stage retriever?
  5. Explain HNSW and its main parameters.