Microsoft Reactor Toronto

AI in Microsoft Fabric is designed to help you work smarter with your data. In this session, you will learn how Copilot accelerates analytics by generating queries, building models, and creating visualizations using natural language.

We will explore AI functions in notebooks, which make it easy to apply enrichment such as summarization, sentiment analysis, and entity extraction with a single line of code. You will also see how AI-powered transforms on OneLake shortcuts can automatically process text files for summarization, translation, or PII detection without building pipelines.

Finally, we will show how Data Wrangler provides an interactive way to clean and shape your data inside notebooks while generating reusable code.

Through a live demo, you will see how these capabilities combine to help you deliver insights and intelligent features quickly for your hackathon project.

What you will learn

• How to use Copilot for modelling and analytics
• How to enrich data with AI functions and shortcut transforms
• How to prepare and transform data efficiently with Data Wrangler

In our fourth Python + AI session, we'll explore one of the most popular techniques used with LLMs: Retrieval Augmented Generation.

RAG is an approach that sends context to the LLM so that it can provide well-grounded answers for a particular domain.

The RAG approach can be used with many kinds of data sources like CSVs, webpages, documents, databases.
In this session, we'll walk through RAG flows in Python, starting with a simple flow and culminating in a full-stack RAG application based on Azure AI Search.

Our third stream in the Python + AI series is all about vision models!

Vision models are LLMs that can accept both text and images, like GPT 4o and 4o-mini. You can use those models for image captioning, data extraction, question-answering, classification, and more!

We'll use Python to send images to vision models, build a basic chat-on-images app, and build a multimodal search engine.