Skip to main content

🎮 ANN Search (Practice)

Companion to the ANN Search guide. Cosine similarity search over vectors — the core of embedding retrieval. Edit and run the code right here — it executes in your browser.

🐍 Your turn​

Loading editor…

🧠 Challenge yourself​

  1. Normalize vectors once so search is just a dot product.
  2. Why do HNSW/IVF trade a little recall for huge speedups?
  3. How would you shard this over a million vectors?

Continue the learning path → Tokenization