# pgvector 0.4.0 performance

DevFeed: [pgvector 0.4.0 performance](<https://devfeed.tech/articles/pgvector-0-4-0-performance-490.md>)

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

Author: Egor Romanov; Pavel Borisov

Published: 2023-07-13T07:00:00Z

Content type: article

Language: en

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

Topics: [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Databases](<https://devfeed.tech/topics/databases.md>), [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Supabase](<https://devfeed.tech/topics/supabase.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Concurrency](<https://devfeed.tech/topics/concurrency.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [concurrency](<https://devfeed.tech/tags/concurrency.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data](<https://devfeed.tech/tags/data.md>), [databases](<https://devfeed.tech/tags/databases.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [openai](<https://devfeed.tech/tags/openai.md>), [performance](<https://devfeed.tech/tags/performance.md>), [python](<https://devfeed.tech/tags/python.md>)

## AI overview

This article benchmarks pgvector for vector database workloads, comparing its performance with Qdrant and examining the effects of concurrency, hardware, and pre-warming. It reports production-oriented results for running large-scale OpenAI embeddings at different query-throughput and accuracy levels.

## Source excerpt

There's been a lot of talk about pgvector performance lately, so we took some datasets and pushed pgvector to the limits to find out its strengths and limitations.