pgvectorscale
Open-source PostgreSQL extension that builds on pgvector with higher-performance embedding search and cost-efficient storage. Features StreamingDiskANN index inspired by Microsoft's DiskANN algorithm. This is an OSS solution under PostgreSQL license.
About this tool
Overview
pgvectorscale is an open-source extension for PostgreSQL that complements pgvector with higher-performance embedding search and more cost-efficient storage for AI applications. Developed by Timescale, it brings production-grade vector search capabilities to PostgreSQL.
Key Features
- StreamingDiskANN Index: New index type inspired by Microsoft's DiskANN algorithm for scalable vector search
- Statistical Binary Quantization: Advanced compression method improving on standard Binary Quantization
- Label-based Filtered Search: Based on Microsoft's Filtered DiskANN research for precise, efficient filtering
- High Performance: Works seamlessly with pgvector for enhanced performance
- Cost Efficient: Optimized for storage and query efficiency
Performance Benchmarks
On 50 million Cohere embeddings (768 dimensions):
- 28x lower p95 latency vs. Pinecone's storage optimized index
- 16x higher query throughput at 99% recall
- 75% less cost when self-hosted on AWS EC2
Architecture
Built as a PostgreSQL extension using the pgrx framework, pgvectorscale integrates natively with PostgreSQL's query planner and can be used alongside pgvector.
Compatibility
- Works with vanilla PostgreSQL (TimescaleDB not required)
- Compatible with pgvector extension
- Available on Timescale Cloud with pgai for complete AI stack
Use Cases
- Large-scale embedding search (millions to billions of vectors)
- Cost-sensitive production deployments
- Applications requiring filtered vector search
- RAG systems with metadata filtering
Pricing
Free and open-source under PostgreSQL license. No licensing costs for self-hosted deployments. Timescale Cloud offers managed hosting with usage-based pricing.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)PostgreSQL extension for scalable, low-latency vector search written in Rust. Features 20x faster HNSW than pgvector, with support for FP16, INT8, and binary vectors. This is an OSS extension.
PostgreSQL extension for scalable, high-performance vector search, successor to pgvecto.rs. Features RaBitQ quantization enabling 6x cost savings vs Pinecone. Fully compatible with pgvector. This is an OSS extension.
Open-source PostgreSQL extension and Python library that automates embedding generation and synchronization for RAG and semantic search applications. Features pgai Vectorizer for declarative embedding pipelines. This is an OSS solution.
Open-source toolkit for developing AI applications using Postgres and pgvector. Provides managed PostgreSQL with built-in vector support, Python client (vecs), and AI features. This is a commercial managed service with OSS components.
PostgreSQL supports vector indexing and similarity search via the PGVector extension, allowing relational databases to manage and retrieve vector embeddings efficiently.
Open-source AI-native database layer that adds vector search, model integration, and AI workflows on top of existing databases like MongoDB and Postgres.