Embed textual data in Amazon RDS for SQL Server using Amazon Bedrock
Database Blog
This article explains how to generate vector embeddings from text data stored in an Amazon RDS for SQL Server database using Amazon Bedrock, and perform similarity searches on the embedded vector data.
Specifically, the article covers:
- Overview of Amazon RDS for SQL Server and Amazon Bedrock
- Steps to integrate RDS for SQL Server with Amazon Bedrock
- Solution overview for generating vector embeddings and storing them back in RDS for SQL Server
- Prerequisites and detailed steps to generate embeddings using an Amazon SageMaker notebook and the Amazon Bedrock API
- Creating a vector table and columnstore index in RDS for SQL Server for efficient similarity searches
- Example of generating an embedding for a search query and performing a similarity search in RDS
- Conclusion and cleanup instructions
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Apr 7
2026
2026
Text-to-SQL solution powered by Amazon Bedrock
Apr 14
2025
2025
Dynamic text-to-SQL for enterprise workloads with Amazon Bedrock Agents
Feb 1
2024
2024
Getting started with Amazon Titan Text Embeddings in Amazon Bedrock
Jun 4
2024
2024
Amazon Titan Text Embeddings V2 now available for use with Bedrock Knowledge Bases
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.