AI Glossary Term

What does “HNSW” mean?

Definition

A graph-based index structure for fast approximate nearest-neighbor search over high-dimensional vectors.

Browse the full AI Glossary Explore all free AI guides

How HNSW works

Example

A search enters at the sparse top layer, hops toward the query across long links, drops a layer, and repeats, ending in the dense bottom layer with the closest vectors. It is like using highways, then streets, then your destination's block.

Why it matters

HNSW is one of the most widely used indexes in vector databases because it gives fast, accurate searches.

Common questions

What does HNSW stand for?

Hierarchical Navigable Small World, introduced by Malkov and Yashunin in 2016.

What is the trade-off?

It uses a fair amount of memory and takes time to build the index.

Can it be updated?

Yes, vectors can be added, though deleting and heavy updates need care.

ANN (Approximate Nearest Neighbor)Algorithms that find vectors close to a query without exhaustive comparison, trading exactness for speed.Vector DatabaseA database optimized for storing and querying high-dimensional embedding vectors.Knowledge GraphA graph structure of entities and relationships used for reasoning or retrieval.Embedding ModelA model specialized for converting data into vectors used for semantic search, clustering, and retrieval.Hybrid SearchA retrieval approach that combines keyword (lexical) search with vector (semantic) search for better recall and precision.Data DriftA shift in real-world input data over time that can degrade model performance.