Learn to implement semantic search using vector embeddings in this comprehensive conference talk that explores search based on meaning rather than keyword matching. Discover the fundamental concepts of semantic search, vector embeddings, and similarity metrics while exploring how to generate embeddings using large language models with OpenAI. Master the storage, indexing, and querying of vector embeddings using the vector data type in Azure SQL Database and Microsoft SQL Server 2025, and optimize queries with the DiskANN vector index. Gain practical experience saving and querying embeddings from .NET applications using Entity Framework Core and the SQL Server VectorSearch library. Through demo-rich examples, explore how semantic search can analyze context and intent behind queries to deliver more relevant results across text, images, and other data types, including cross-language matching capabilities where query terms can be in different languages than the stored data.