Vector Databases & ANN Indexes

Exact vs approximate search, HNSW and IVF-PQ, recall vs latency, filtered ANN, sharding, and pgvector.

0 / 5 solved

Question Tags Difficulty Success

1. One Store or Two

pgvectorvector-database +1

Medium —

2. Turning the Dial (2)

hnswrecall-at-k +1

Medium —

3. Half a Percent

filtered-vector-searchmulti-tenancy +1

Hard —

4. Ninety Six Bytes Each

product-quantizationvector-compression +2

Hard —

5. The Recall Ceiling

hnswann-index +3

Hard —

Learning Resources

HNSW, efficient approximate nearest neighbor search

Up next

5 of 5 questions here are still unsolved.

Next module Agent Memory Systems