Embedding models and dimensions: optimizing the performance to resource-usage ratio
Since the release of vector preview, we’ve been working with many customers that are building AI solution on Azure SQL and SQL Server and one of the most common questions is how to support high-dimensional data, for example more than 2000 dimensions per vector. In fact, at the moment, the vector type supports “only” up […]
The post Embedding models and dimensions: optimizing the performance to resource-usage ratio appeared first on Azure SQL Devs’ Corner.
Published on:
Learn more