pgvectorscale

Use pgvectorscale to build scalable AI applications with higher performance, embedding search and cost-efficient storage.

pgvectorscale complements pgvector, the open-source vector data extension for PostgreSQL, and introduces the following key innovations:

• A DiskANN index: based on research from Microsoft
• Statistical Binary Quantization: developed by Timescale researchers, This feature improves on standard Binary Quantization.

Timescale’s benchmarks reveal that with pgvectorscale, PostgreSQL achieves 28x lower p95 latency, and 16x higher query throughput for approximate nearest neighbor queries at 99% recall.

In contrast to pgvector, which is written in C, pgvectorscale is developed in Rust, offering the PostgreSQL community a new avenue for contributing to vector support.

Timescale offers the following high performance journeys:

• App developer and DBA: try out pgvectorscale functionality in Timescale Cloud.
  • Enable pgvectorscale in a Timescale service
• Extension contributor: contribute to pgvectorscale.
  • Build pgvectorscale from source in a developer environment
• Everyone: check the benchmark results for yourself.
  • Test pgvectorscale performance

Enable pgvectorscale in a Timescale service

To enable pgvectorscale:

1. Create a new Timescale Service.

   If you want to use an existing service, pgvectorscale is added as an available extension on the first maintenance window after the pgvectorscale release date.

2. Connect to your Timescale service:

   psql -d "postgres://<username>:<password>@<host>:<port>/<database-name>"
   

3. Create the pgvectorscale extension:

   CREATE EXTENSION IF NOT EXISTS vectorscale CASCADE;
   

   The CASCADE automatically installs the dependencies.

Test pgvectorscale performance

To check the Timescale benchmarks in your pgvectorscale environment:

1. Jonetas, this is for you :-).

Get involved

pgvectorscale is still at an early stage. Now is a great time to help shape the direction of this project; we are currently deciding priorities. Have a look at the list of features we're thinking of working on. Feel free to comment, expand the list, or hop on the Discussions forum.

About Timescale

Timescale Cloud is a high-performance developer focused cloud that provides PostgreSQL services enhanced with our blazing fast vector search. Timescale services are built using TimescaleDB and PostgreSQL extensions, like this one. Timescale Cloud provides high availability, streaming backups, upgrades over time, roles and permissions, and great security.

TimescaleDB is an open-source time-series database designed for scalability and performance, built on top of PostgreSQL. It provides SQL support for time-series data, allowing users to leverage PostgreSQL's rich ecosystem while optimizing for high ingest rates and fast query performance. TimescaleDB includes features like automated data retention policies, compression and continuous aggregates, making it ideal for applications like monitoring, IoT, AI and real-time analytics.