ConceptANN / Approximate Nearest Neighbor Search

Approximate Nearest Neighbor Search (ANN)

A core technique of vector retrieval that reduces the O(N) complexity of exact nearest neighbor search to approximately O(log N) at the cost of a small amount of recall, enabling millisecond-level retrieval. Common indexes include HNSW, IVF and PQ.

Timeline (last 90 days)

Nov 1

ANN trades a small amount of recall for order-of-magnitude speed improvements, and its core metric is recall@K.

Unverified50%

All Facts (1)

Unverified

ANN trades a small amount of recall for order-of-magnitude speed improvements, and its core metric is recall@K.

50%

Source Articles

Vector Database Architecture Explained: The Core Component Behind AI SystemsNov 1 The Battle of Tool Discovery Architectures: Plan First or Retrieve First?Oct 15