Published:
Last updated:

Embeddings, Vector Search, and RAG

Authors
Time yourself:
Your progress:

00:30:00

0%

Filter by difficulty

33 of 33 questions shown

RAG and Embedding Foundations

1. What is retrieval-augmented generation, and what problem does it solve?

Junior
Flag important question
Mark as complete

2. What is an embedding?

Junior
Flag important question
Mark as complete

3. How do the offline indexing and online query pipelines work?

Junior
Flag important question
Mark as complete

4. How do cosine similarity, dot product, and Euclidean distance differ?

Mid-level
Flag important question
Mark as complete

5. Why split documents into chunks instead of embedding the whole document?

Junior
Flag important question
Mark as complete

Free preview complete

You’ve reached the end of the free preview

Get every remaining question and complete answer, plus progress tracking across the full Interview Question Library.

  • 28 more questions and complete answers in this topic
  • Full access to every interview topic
  • Progress tracking and question flags
  • New questions and improvements during your subscription

Full access from

$12/month

No long-term commitment. Cancel whenever you want.

6. How do you choose an embedding model and vector dimension?

Mid-levelPaid Question

7. Why must queries and documents use compatible embeddings?

JuniorPaid Question

8. Which changes require re-embedding or reindexing?

Mid-levelPaid Question

9. How do dense, sparse, and multimodal embeddings differ?

Mid-levelPaid Question

Vector Indexes and Search Infrastructure

10. What is the difference between exact kNN and approximate nearest-neighbor search?

JuniorPaid Question

11. How does an HNSW index work, and what are its tradeoffs?

SeniorPaid Question

12. How do IVF-style indexes work, and what are their tradeoffs?

SeniorPaid Question

13. How do you tune recall, latency, memory, and cost for vector search?

Mid-levelPaid Question

14. How do metadata filters interact with ANN search?

SeniorPaid Question

15. How do you choose between a vector database, search engine, and relational vector extension?

Mid-levelPaid Question

Ingestion, Chunking, and Freshness

16. How do you design an idempotent document-ingestion pipeline?

Mid-levelPaid Question

17. How do you choose a chunking strategy?

Mid-levelPaid Question

18. When does chunk overlap help, and when does it hurt?

JuniorPaid Question

19. How do you preserve tables, code, layout, and provenance during chunking?

Mid-levelPaid Question

20. Which metadata should a RAG chunk store?

JuniorPaid Question

21. How do you handle document updates, freshness, and deletion?

SeniorPaid Question

Retrieval, Reranking, and Context Assembly

22. When should you use keyword, semantic, or hybrid retrieval?

JuniorPaid Question

23. How do you combine lexical and vector rankings?

Mid-levelPaid Question

24. When do query rewriting, decomposition, and multi-query retrieval help?

Mid-levelPaid Question

25. What does a reranker do, and when is it worth the cost?

Mid-levelPaid Question

26. How do you assemble a useful context within a token budget?

SeniorPaid Question

27. How should citations and grounding work in a RAG answer?

JuniorPaid Question

Evaluation, Security, and Scale

28. How do you evaluate retrieval with Recall@k, Precision@k, MRR, and nDCG?

SeniorPaid Question

29. Why must you evaluate retrieval and answer generation separately?

SeniorPaid Question

30. How do you secure a multi-tenant RAG system end to end?

SeniorPaid Question

Advanced Retrieval Patterns

31. How does parent-child retrieval balance precise search with coherent context?

Mid-levelPaid Question

32. How do single-vector retrieval, late interaction, and cross-encoder reranking differ?

SeniorPaid Question

33. When should a RAG system route, change strategy, or skip retrieval?

SeniorPaid Question