Vector Support Public Preview in Azure SQL Database & Managed Instance | Data Exposed

Join Anna Hoffman , Pooja Kamath & Amit Khandelwal as they explore the exciting Public Preview of Native vector support in Azure SQL Database and SQL Managed Instance. Azure SQL provides a dedicated Vector data type that simplifies the creation, storage, and querying of vector embeddings directly within a relational database. This eliminates the need for separate vector databases and related integrations, increasing the security of your solutions while reducing the overall complexity. This episode highlights the features and practical use cases, demonstrating how to leverage Azure SQL for building AI-ready applications. It includes sneak peeks into demos such as Resume matching (Document RAG) and LangChain integration, showcasing the real-world applications of vector functions. Additionally, discover how these features are now available in SQL on Linux, expanding the versatility and reach of Azure SQL from ground SQL 2025 on Windows and Linux to cloud solutions like SQL DB and SQL MI, and even to Fabric. 0:00 Introduction 3:57 Demo 1: Vector Support 14:15 Demo 2: Smart Resume Matching 18:00 Demo 3: Langchain with SQL Vector store 19:45 Getting started ✅ Resources: To learn everything about Native Vector Support in SQL, take a look at the official documentation: https://learn.microsoft.com/en-us/sql/t-sql/functions/vector-functions-transact-sql?view=azuresqldb-current You can also use this GitHub Repo full of samples: https://github.com/Azure-Samples/azure-sql-db-vector-search. If you are looking for end-to-end samples, take a look here https://aka.ms/sqlai-samples where you’ll find: - Retrieval Augmented Generation (RAG) on your own data using LangChain - RAG and Natural-Language-to-SQL (NL2SQL) together to build a complete chatbot on your own data, using Semantic Kernel - A tool to quickly vectorize data you already have in your database and enable it for AI And much more! We’d love to hear your thoughts on this feature! Please share how you’re using it in th