Announcing pgvector 0.8.0 support in Aurora PostgreSQL
Amazon Aurora PostgreSQL-Compatible Edition now supports pgvector 0.8.0, an open-source extension for PostgreSQL for storing vector embeddings in your database. pgvector provides vector similarity search capabilities that enables Aurora use in generative artificial intelligence (AI) semantic search and retrieval-augemented generation (RAG) applications. pgvector 0.8.0 includes improvements to PostgreSQL query planner’s selection of index when filters are present, which can deliver better query performance and improve search result quality.
pgvector 0.8.0 improves data filtering using conditions in WHERE clauses and joins that can improve query performance and usability. Additionally, the iterative index scans help prevent ‘overfiltering’, ensuring generation of sufficient results to satisfy the conditions of a query. If an initial index scan doesn't satisfy the query conditions, pgvector will continue to search the index until it hits a configurable threshold. pgvector 0.8.0 also has performance improvements for searching and building HNSW indexes.
pgvector 0.8.0 is available in Amazon Aurora clusters running PostgreSQL 16.8, 15.12, 14.17, and 13.20 and higher in all AWS Regions including AWS GovCloud (US) Regions, except China. You can initiate a minor version upgrade by modifying your DB cluster. Please review the Aurora documentation to learn more.
Amazon Aurora is designed for unparalleled high performance and availability at global scale with full MySQL and PostgreSQL compatibility. It provides built-in security, continuous backups, serverless compute, up to 15 read replicas, automated multi-Region replication, and integrations with other AWS services. To get started with Amazon Aurora, take a look at our getting started page.