Microsoft Reactor London

Modern apps need a fast operational store and a simple path to analytics and AI. Fabric Databases give you both inside Microsoft Fabric.

You will see how SQL database in Fabric provides a developer‑friendly relational database based on the Azure SQL Database engine, while automatically making your data available in OneLake for analytics without extra pipelines. This lets you power notebooks, BI, and real‑time scenarios from the same operational data.

We will also introduce Cosmos DB in Fabric, an AI‑optimized NoSQL database that supports vector indexing and hybrid search for intelligent application experiences. You will learn when to use each database, how automatic replication to OneLake works, and how to expose data to applications using familiar tools and a GraphQL endpoint pattern.

The demo shows a small app that writes to a Fabric database, lights up analytics in Fabric, and surfaces AI features for a complete, end‑to‑end workflow.

What you will learn

• When to choose SQL database in Fabric for relational workloads versus Cosmos DB in Fabric for semi‑structured data and AI features like vector and hybrid search.
• How automatic replication to OneLake enables analytics and BI on operational data without building ETL first.
• How to connect your app and expose data using standard connection strings and a GraphQL pattern for modern APIs

Join us for a hands-on livestream where you'll learn how to unlock the full potential of VS Code and GitHub Copilot and elevate your coding experience. Whether you're a beginner or an experienced developer, this session will introduce you to AI-assisted development workflows, helping you write better code, faster.

Join us for the first session in our Python + AI series!

In this session, we'll talk about Large Language Models (LLMs), the models that power ChatGPT and GitHub Copilot. We'll use Python to interact with LLMs using popular packages like the OpenAI SDK and Langchain. We'll experiment with prompt engineering and few-shot examples to improve our outputs.

We'll also show how to build a full stack app powered by LLMs, and explain the importance of concurrency and streaming for user-facing AI apps.

In our second session of the Python + AI series, we'll dive into a different kind of model: the vector embedding model.

A vector embedding is a way to encode a text or image as an array of floating point numbers. Vector embeddings make it possible to perform similarity search on many kinds of content.

In this session, we'll explore different vector embedding models, like the OpenAI text-embedding-3 series, with both visualizations and Python code. We'll compare distance metrics, use quantization to reduce vector size, and try out multimodal embedding models.