- Newest
- Most votes
- Most comments
Current listing of AWS Vector DB support is here: https://aws.amazon.com/what-is/vector-databases/
How can AWS support your vector database requirements?
Amazon Web Services (AWS) offers many services for your vector database requirements:
- Amazon OpenSearch Service makes it easy for you to perform interactive log analytics, real-time application monitoring, website search, and more. For vector databases, you can read about k-Nearest Neighbor (k-NN) search in OpenSearch Service.
- Amazon Aurora PostgreSQL-Compatible Edition and Amazon Relational Database Service (Amazon RDS) for PostgreSQL support the pgvector extension to store embeddings from machine learning (ML) models in your database and to perform efficient similarity searches.
- Amazon Neptune ML is a new capability of Neptune that uses Graph Neural Networks (GNNs), an ML technique purpose-built for graphs, to make easy, fast, and more accurate predictions using graph data.
- Vector search for Amazon MemoryDB supports storing millions of vectors, with single-digit millisecond query and update response times, and tens of thousands queries per second (QPS) at greater than 99% recall.
- Amazon DocumentDB (with MongoDB compatibility) supports vector search, a new capability that enables you to store, index, and search millions of vectors with millisecond response times. With vector search for Amazon DocumentDB, you can simply set up, operate, and scale databases for your ML applications.
Currently, there is no direct equivalent to pgvector for RDS MySQL to store vector embeddings. The vector database capabilities and support for storing and querying vector embeddings are primarily available for PostgreSQL-compatible databases in the AWS ecosystem.
For PostgreSQL, both Amazon Aurora PostgreSQL-Compatible Edition and Amazon RDS for PostgreSQL support the pgvector extension. This allows users to store embeddings from machine learning and AI models, such as those from Amazon Bedrock or Amazon SageMaker, directly in their PostgreSQL databases. The pgvector extension enables vector similarity searches and provides efficient indexing methods for high-dimensional vector data.
If you specifically need to work with vector embeddings and are using RDS, the recommended approach would be to use either Amazon Aurora PostgreSQL-Compatible Edition or Amazon RDS for PostgreSQL with the pgvector extension. These options provide built-in support for vector operations, including storage, indexing, and similarity searches on vector data.
For MySQL users who require vector embedding capabilities, you may need to consider alternative solutions or potentially migrate to a PostgreSQL-based database to leverage these features within the AWS RDS ecosystem.
Sources
Relational Database – Amazon Aurora MySQL PostgreSQL Features – AWS
Cloud Relational Database – Amazon RDS Features – Amazon Web Services
As today, AWS RDS is only compatible with mysql 8... waiting for version 9 support which include already capabilities to store and query vectors: https://dev.mysql.com/doc/refman/9.3/en/vector.html
I could not find any announcement yet about aws RDS support in general for MySQL 9.x
answered 5 months ago
Relevant content
asked 2 years ago
asked 3 years ago
- AWS OFFICIALUpdated 9 months ago
