Building an application allows you to operationalize the data you have in Microsoft Fabric, such that it can be consumed by stakeholders in your organization to generate business insights. Streamlit is easy to use to build simple applications without needing to know front-end application frameworks like Flask, Django etc. It makes it easier to pro...
Project Mission The way people work and manage information is changing rapidly in our digital age. More and more people are struggling to keep track of all the online resources they use daily. They need a better way to save, organize, and retrieve important information from websites, articles, and other online sources. This is especially true fo...
I recently presented at Python Day 2024 on Langchain integration. I created a slide deck that I believe can be useful beyond just the session, so I wanted to share it here for everyone's benefit. The deck covers the most common topics for a Python developer: The slide deck, which I created using the Sli.dev SDK, so t...
LangChain Integration for Vector Support for Azure SQL and SQL database in Microsoft Fabric Microsoft SQL now supports native vector search capabilities in Azure SQL and SQL database in Microsoft Fabric. We also released the langchain-sqlserver package, enabling the management of SQL Server as a Vectorstore in LangChain. In this step-by-step tutor...
The Football (aka Soccer in US 😀) Analisys Copilot provides an intuitive interface for users to interact with complex football data without needing advanced technical skills. By utilizing natural language processing, users can ask questions and retrieve detailed insights from vast datasets, including competitions, matches, teams, players, and e...
Hey Azure SQL enthusiasts! 👋 We had a hiring event last week, and as I was going through a stack of digital resumes, I thought, "There has to be an easier way to do this." That's when it hit me—why not use Azure SQL DB’s new vector data type to revolutionize our hiring process? Not only could we find the perfect candidate faster, but we could al...
In today’s data-driven world, finding similar items within large datasets is a common challenge. Whether it’s recommending products, identifying similar documents, or clustering data points, efficient similarity search is crucial. This blog post will explore how to leverage FAISS (Facebook AI Similarity Search) and Azure SQL to perform similarity s...
This semester long project was completed by Master's students at Cornell University with mentorship from the Azure SQL database product team at Microsoft. Project Mission The purpose of this project is to design a high-fidelity university course registration system utilizing Microsoft Azure cloud services. Our target audience includes uni...
In a previous article I already mentioned how vectors can be easily stored in Azure SQL already and how to calculate dot product and cosine distance using just T-SQL. In this article I will show how to improve the performance in vector search by using a technique that has many name but is really based on something very well know already: KMeans Clu...
Creating a Kubernetes Application for Azure SQL Database Buck Woody, Principal Applied Data Scientist, Microsoft Modern application development has several challenges. From selecting a "stack" of front-end through data storage and processing from several competing standards, through ensuring the highest levels of security and performance, dev...
