ReleaseBytes
aws AWS What's New ·

Amazon DynamoDB adds general availability for real-time vector search

aiawsgaengineeraws-dynamodbaws-bedrock
feature announcement

Amazon DynamoDB now supports real-time vector search, enabling indexing and searching of vector embeddings with single-digit millisecond latency and high recall at scale. This feature allows engineers to integrate semantic retrieval and other AI-driven applications directly within DynamoDB, leveraging its existing serverless benefits. It is now generally available and can be used for AI agent memory, recommendation systems, and personalized advertising.

  • →General availability of real-time vector search in DynamoDB
  • →Improved AI application capabilities with vector search
  • →DynamoDB maintains serverless benefits
Features (1) ›
  • General availability of real-time vector search in DynamoDB

    DynamoDB now supports native vector search, allowing for indexing and real-time searching of vector embeddings with high recall and low latency. This feature is designed to scale to trillions of vectors and operates with the same serverless benefits as other DynamoDB features.

Enhancements (1) ›
  • Improved AI application capabilities with vector search

    The addition of vector search enables new use cases such as semantic retrieval for AI agent grounding, product similarity search, personalized advertising, retrieval augmented generation, and recommendation systems. Developers can store vector embeddings alongside other attributes and generate them using various models, including those from Amazon Bedrock.

Notes (1) ›
  • DynamoDB maintains serverless benefits

    Vector search in DynamoDB inherits the existing serverless advantages, including zero infrastructure management, zero downtime, zero maintenance windows, and a pay-for-use model.

Read the original announcement →

https://aws.amazon.com/about-aws/whats-new/2026/08/amazon-dynamodb-vector-search

Related releases