Semantic search, or search based on the meaning, analyzes the context and intent behind a query to deliver more relevant results. Using Vector embeddings, the data structure behind semantic search, you can enhance your search to include text, images, and other types of data. With vector databases, you can store and index vector embeddings and provide similarity search over these embeddings.

In this session, we will explore the fundamental concepts of semantic search, including vector embeddings and similarity metrics. You will learn how to generate embeddings using large language models with OpenAI. I will then demonstrate how to store, index, and query vector embeddings using the vector data type in Azure SQL Database or with the Microsoft SQL Server 2025. Additionally, you will see how to optimize the queries with the DiskANN vector index. Finally, you will see how to save and query these embeddings from .NET with Entity Framework Core and the SQL Server VectorSearch library.

Join me for a demo-rich session and learn how to implement semantic search in .NET with Azure SQL Database and Entity Framework Core.