Core

Approximate Nearest Neighbor (ANN)

Brute-force vector search is O(N*d) per query and falls apart at millions of vectors, so ANN trades a sliver of recall for orders-of-magnitude speed. The two dominant families are IVF (cluster then probe nearby cells) and HNSW (walk a navigable graph), with product quantization to shrink memory. The non-negotiable habit is measuring recall@k against a brute-force baseline.

a free account unlocks the core curriculum tier · no card

RELATED CONCEPTS

Vector Databases Embeddings & Vector Representations Reranking and Two-Stage Retrieval Big-O That Actually Matters

PRACTICE THIS IN REAL QUESTIONS

LLM & GenAI FundamentalsWhat are embeddings, and how do they make semantic search work?→System Design & Production EngineeringEstimate the capacity and cost of an app with 50k DAU making 10 LLM calls each. What do you provision for?→ML System Design (Product)Design a landmark or image recognition system at scale.→Machine Learning & Data ScienceWhat does cosine similarity actually measure, and why is it the default for comparing embeddings?→ML Infrastructure & GPUsHow do you choose the tensor-parallel degree when serving a 70B model?→ML Infrastructure & GPUsHow many GPUs do you need to serve 1,000 requests/sec, walk me through the capacity math.→