Systems engineer with over twenty-five years of software development and IT consulting experience. Currently working with AWS as a Senior Solutions Architect specialized on RDS. Microsoft Consulting Services veteran with more than fifteen years of experience working on challenging SQL Server engagements with Fortune 500 companies across the globe.
Todas las sesiones por Camilo Leon
A Generative AI Use Case Leveraging Amazon RDS for SQL Server as a Vector Data Store
This session is focused on how to use Amazon RDS SQL Server as a vector data store to implement a Generative AI use case based on similarity search in which both, the source Operational Data Store and the Vector Data store, are co-located and hosted on Amazon RDS for SQL Server. The embeddings generated to vectorize free form text source data should be stored and managed close to your domain-specific datasets. Doing so allows you to combine them with additional metadata without using additional, external data sources. Your data is also not static, but changes over time, and storing the embeddings near your source data simplifies your data pipelines for keeping the embeddings up to date. For the demo included in this session, the specific workflow in use to demonstrate this functionality is based on a typical chat bot scenario in which we leverage RAG to augment a Foundation Model and provide a domain relevant response to the user.