# pgvector 0.6.0: 30x faster with parallel index builds

DevFeed: [pgvector 0.6.0: 30x faster with parallel index builds](<https://devfeed.tech/articles/pgvector-0-6-0-30x-faster-with-parallel-index-builds-489.md>)

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

Author: Egor Romanov

Published: 2024-01-30T07:00:00Z

Content type: article

Language: en

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

Topics: [Database](<https://devfeed.tech/topics/database.md>), [build performance](<https://devfeed.tech/topics/build-performance.md>), [Concurrency](<https://devfeed.tech/topics/concurrency.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Algorithm](<https://devfeed.tech/topics/algorithm.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [dataset](<https://devfeed.tech/topics/dataset.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [build](<https://devfeed.tech/tags/build.md>), [build-performance](<https://devfeed.tech/tags/build-performance.md>), [database](<https://devfeed.tech/tags/database.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [thread](<https://devfeed.tech/tags/thread.md>), [time](<https://devfeed.tech/tags/time.md>), [vectors](<https://devfeed.tech/tags/vectors.md>)

## AI overview

pgvector 0.6.0 introduces parallel HNSW index builds, reducing build times substantially while preserving query throughput and index accuracy. Benchmarks show improvements of up to 30x for unlogged tables and up to 13.5x with more powerful instances.

## Source excerpt

pgvector 0.6.0 brings a significant improvement: parallel index builds for HNSW. Building an HNSW index is now up to 30x faster for unlogged tables.