Embeddings & Vector SearchYu. A. Malkov, D. A. Yashunin
Malkov and Yashunin present HNSW
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Presented HNSW — approximate nearest neighbor search at logarithmic scale using hierarchical navigable small world graphs
Why it matters
The default indexing algorithm of almost every vector DB today
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1603.09320Added in Week 35, 2026 · See that week
On the map — ⑰ Embeddings line
- Previous stopword2vec
- This recordHNSW
- Next stopFAISS