Amazon DocumentDB now supports vector search with HNSW index
Amazon DocumentDB (with MongoDB compatibility) now supports vector search with Hierarchical Navigable Small World (HNSW) index. HNSW index lets you execute vector similarity searches with low latency and produce highly relevant results. Vectors are numerical representations of unstructured data, such as text, created from machine learning (ML) models that help capture the semantic meaning of the underlying data. Vector search for Amazon DocumentDB can store vectors from Amazon Bedrock, Amazon SageMaker, and more.
Amazon DocumentDB (with MongoDB compatibility) now supports vector search with Hierarchical Navigable Small World (HNSW) index. HNSW index lets you execute vector similarity searches with low latency and produce highly relevant results. Vectors are numerical representations of unstructured data, such as text, created from machine learning (ML) models that help capture the semantic meaning of the underlying data. Vector search for Amazon DocumentDB can store vectors from Amazon Bedrock, Amazon SageMaker, and more.
With vector search for Amazon DocumentDB, you can simply set up, operate, and scale databases for your ML, including generative AI enabled applications. You no longer have to spend time managing separate vector infrastructure, writing code to connect with another service, and duplicating data from your source database. The vector search capability together with large language models (LLMs) enable you to search the database based on meaning, unlocking a wide range of use cases, including semantic search, product recommendations, personalization, and chatbots.
Vector search for Amazon DocumentDB is available on DocumentDB 5.0 instance-based clusters in all regions where Amazon DocumentDB is available.
You can get started by launching an Amazon DocumentDB cluster directly from the AWS Console or the AWS CLI. Learn more about vector search on our features page and developer guide.