MENU

Fun & Interesting

RAG in Azure AI Studio

Microsoft Reactor 2,821 5 months ago
Video Not Working? Fix It Now

RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Learn how to build a RAG-based custom copilot end-to-end using Azure AI Studio, code-first. We'll walk through "Contoso Chat", a retail copilot scenario with product and customer data. We'll explore prompt engineering using prompty assets, orchestration with promptflow flex-flows and automated provisioning and deployment with azd. You'll learn how to build & test your copilot locally (in VS Code), then deploy & test it in production on Azure. Presented by Leah Bar-On Simmons (Azure AI PM) and Nitya Narasimhan (Azure AI Advocate) ** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack ** #microsoftreactor #raghack 📌Check out the RAGHack 2024 series here! https://aka.ms/RAGHack2024 [eventID:23334]

Comment