# pgvector v0.5.0: Faster semantic search with HNSW indexes

DevFeed: [pgvector v0.5.0: Faster semantic search with HNSW indexes](<https://devfeed.tech/articles/pgvector-v0-5-0-faster-semantic-search-with-hnsw-indexes-402.md>)

Original publisher: [Read original article](<https://supabase.com/blog/increase-performance-pgvector-hnsw>)

Author: Greg Richardson

Published: 2023-09-06T07:00:00Z

Content type: article

Language: en

Sources: [Supabase Blog](<https://devfeed.tech/sources/supabase-blog.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [complexity](<https://devfeed.tech/tags/complexity.md>), [databases](<https://devfeed.tech/tags/databases.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [performance](<https://devfeed.tech/tags/performance.md>), [search](<https://devfeed.tech/tags/search.md>)

## AI overview

pgvector v0.5.0 adds HNSW indexes for faster semantic and approximate nearest-neighbor search. The article explains HNSW's hierarchical graph structure and contrasts it with IVF indexes.

## Source excerpt

Increase performance in pgvector using HNSW indexes