kernel-memory
kernel-memory copied to clipboard
Support SQL Server as a memory source
trafficstars
SQL Server works fine as a memory source to store vector embeddings. It is the most cost effective method. See: Azure OpenAI RAG Pattern using a SQL Vector Database
It is interesting for me too. Please support SQL Server
You can use it with this third-party extension: https://github.com/kbeaugrand/SemanticKernel.Connectors.Memory.SqlServer. You can find an example of its integration in my GitHub repository at https://github.com/marcominerva/OpenAIEmbeddingSample.
MS SQL server connector is now available in the repo, thanks to @kbeaugrand