What is HNSW?

Why does HNSW matter?

It is a common way to make high-recall vector search practical at scales where exhaustive comparison is too slow.

HNSW in practice

Tune construction and query parameters against latency, memory, and Recall@K targets, then rebuild the index when embedding versions change.

What is the common confusion about HNSW?

HNSW is an index algorithm, not a similarity metric, embedding model, or complete vector database.

Learn HNSW in the course

Lessons that name HNSW in a title or section

• Embeddings & Vector Representations

  Text is discrete. Math is continuous. Every time you ask an LLM to find "similar" documents, compare meanings, or search beyond keywords, you're relying on a bridge between these two worlds.

  Phase 11: LLM Engineering

Covered in Phase 11: LLM Engineering.

Related terms

• Approximate Nearest Neighbor (ANN)A search method that returns vectors likely to be among the nearest to a query without exhaustively comparing the query with every stored…
• Vector DatabaseA storage and indexing system that supports nearest-neighbor queries over vector representations, often with metadata filtering,…
• EmbeddingA learned mapping from discrete items (words, images, users) to dense vectors in continuous space, where similar items end up close together
• Recall@KFor one query, Recall@K is `|relevant items intersecting the top k| / |relevant items|`.

Sources

• Efficient and Robust Approximate Nearest Neighbor Search Using HNSW

More terms in Retrieval & generation

• Approximate Nearest Neighbor (ANN)
• BM25
• Chunking
• Dense Retrieval
• Grounding
• Hybrid Retrieval
• Maximum Marginal Relevance (MMR)
• RAG (Retrieval-Augmented Generation)
• Recall@K
• Reciprocal Rank Fusion (RRF)
• Reranker
• Semantic Search
• Vector Database

Open the Retrieval & generation list in the glossary