Amazon S3 Vectors is a new cloud storage solution that allows businesses to store and query large vector datasets in a cost-effective manner. This service reduces the total cost of uploading, storing, and querying vectors by up to 90 percent. It’s the first cloud object store with native support for storing large vector datasets and providing subsecond query performance.
Vector search is an emerging technique used in generative AI applications to find similar data points by comparing their vector representations using distance or similarity metrics. S3 Vectors introduces vector buckets, a new bucket type with dedicated APIs to store, access, and query vector data without provisioning any infrastructure.
Creating a vector index is simple and allows users to organize their vector data within the index, making it easy to run similarity search queries against the dataset. Each vector bucket can have up to 10,000 vector indexes, and each index can hold tens of millions of vectors. Users can attach metadata as key-value pairs to each vector to filter future queries.
S3 Vectors is natively integrated with Amazon Bedrock Knowledge Bases, including within Amazon SageMaker Unified Studio, for building cost-effective Retrieval-Augmented Generation (RAG) applications. It also integrates with Amazon OpenSearch Service to lower storage costs by moving infrequent queried vectors to OpenSearch as demands increase or to support real-time, low-latency search operations.
This service enables businesses to economically store vector embeddings representing massive amounts of unstructured data and supports scalable generative AI applications including semantic and similarity search, RAG, and build agent memory. It also supports industry use cases such as personalized recommendations, automated content analysis, and intelligent document processing without the complexity and cost of managing vector databases.
To get started with S3 Vectors, users can create a vector bucket, index, and insert vector data using the AWS Command Line Interface (AWS CLI), AWS SDKs, or Amazon S3 REST API. The service is available in preview in multiple regions, including US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Frankfurt), and Asia Pacific (Sydney).
Source: https://aws.amazon.com/blogs/aws/introducing-amazon-s3-vectors-first-cloud-storage-with-native-vector-support-at-scale