Amazon S3 Vectors Reaches GA, Introducing "Storage-First" Architecture for RAG

"AWS recently announced the general availability of S3 Vectors, a cloud object storage service with native support for storing and querying vector data. With the GA release, the company increases per-index capacity forty-fold to 2 billion vectors and introduces sub-100ms query latencies. Earlier this year, in July, the service was available as a preview, and the company reports that users have already created over 250,000 vector indexes and ingested more than 40 billion vectors."

"In addition, the company enhances query performance, with infrequent queries returning results in under 1 second and frequent queries achieving latencies of 100ms or less, which is beneficial for interactive applications like conversational AI. Furthermore, according to the company, up to 100 search results can now be retrieved per query, improving the context for retrieval-augmented generation (RAG) applications. Finally, write performance now supports up to 1,000 PUT transactions per second for single-vector updates,"

AWS S3 Vectors is generally available with per-index capacity increased forty-fold to 2 billion vectors and sub-100ms query latencies. During preview users created over 250,000 vector indexes and ingested more than 40 billion vectors. A single index can now hold up to 2 billion vectors, removing the need to shard indexes or implement complex query federation. Infrequent queries can return results in under one second while frequent queries can achieve latencies of 100ms or less, supporting interactive applications like conversational AI. Queries can retrieve up to 100 search results and write throughput supports up to 1,000 PUTs per second for single-vector updates. Integrations with Amazon Bedrock Knowledge Base and Amazon OpenSearch are available.

Read at InfoQ