RAG Interview Questions, issue 8, Jul 12, 2026
The IVF-PQ Compression Trick
Staff ML Engineer interview at Google, and the interviewer asks:
“Your RAG system hits 99% recall on HNSW in the demo. Now it’s 200M vectors and your RAM bill just triggered a budget review. Do you keep HNSW? Why or why not?”
Don’t say: “HNSW is faster and more accurate, so we keep it and add more RAM.”
Why blindly scaling HNSW is a scaling nightmare, and how to gracefully trade imperceptible coverage loss for massive infrastructure savings.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.