Posted On: May 10, 2024
Amazon Relational Database Service (RDS) for PostgreSQL now supports pgvector 0.7.0, an open-source extension for PostgreSQL for storing vector embeddings in your database, letting you use retrieval-augemented generation (RAG) when building your generative AI applications. This release of pgvector includes features that increase the number of dimensions of vectors you can index, reduce index size, and includes additional support for using CPU SIMD in distance computations.
pgvector 0.7.0 adds two new vector data types: halfvec for storing dimensions as 2-byte floats, and sparsevec for storing up to 1,000 nonzero dimensions, and now supports indexing binary vectors using the PostgreSQL-native bit type. These additions let you use scalar and binary quantization for the vector data type using PostgreSQL expression indexes, which reduces the storage size of the index and lowers the index build time. Quantization lets you increase the maximum dimensions of vectors you can index: 4,000 for halfvec and 64,000 for binary vectors. pgvector 0.7.0 also adds functions to calculate both Hamming and Jaccard distance for binary vectors.
pgvector 0.7.0 is available on database instances in Amazon RDS running PostgreSQL 16.3 and higher, 15.7 and higher, 14.12 and higher, 13.15 and higher, and 12.19 and higher in all applicable AWS Regions, including the AWS GovCloud (US) Regions.
Amazon RDS for PostgreSQL makes it simple to set up, operate, and scale PostgreSQL deployments in the cloud. See Amazon RDS for PostgreSQL Pricing for pricing details and regional availability. Create or update a fully managed Amazon RDS database in the Amazon RDS Management Console.