Learn Live: Developing a production level RAG workflow

Full series information: https://aka.ms/learnlive-microsoft-learn-ai-skills-challenge More info here: https://aka.ms/learnlive-microsoft-learn-ai-skills-challenge-Ep8 Follow on Microsoft Learn: - Complete the Learn module: https://aka.ms/learnlive-20240417A Copilots can work alongside you to provide suggestions, generate content, or help you make decisions. Copilots use language models as a form of generative artificial intelligence (AI) and will answer your questions using the data they were trained on. To ensure a copilot retrieves information from a specific source, you can add your own data when building a copilot with the Azure AI Studio (preview). --------------------- Learning objectives - Identify the need to ground your language model with Retrieval Augmented Generation (RAG) - Index your data with Azure AI Search to make it searchable for language models - Build a copilot using RAG on your own data in the Azure AI Studio --------------------- Chapters -------- 00:00 - Introduction 05:36 - Learning objectives 06:36 - What is a copilot? 11:48 - Copilot Development Lifecycle 14:49 - Building a copilot on your data 17:50 - Incorporating domain knowledge 21:26 - Retrieval Augmented Generation (RAG) 28:23 - Demo - Adding data and indexes in Azure AI Studio 38:52 - Q&A 43:25 - Prompt flow 50:02 - Demo - Using a RAG pattern in a prompt flow 1:07:11 - Knowledge check 1:15:13 - Summary --------------------- Presenters Graeme Malcolm Principal Content Dev Manager, Data & Ai Microsoft - Twitter: https://twitter.com/graeme_malcolm - LinkedIn: https://www.linkedin.com/in/graemesplace/ Carlotta Castelluccio Cloud advocate Microsoft - Twitter: https://twitter.com/carlottacaste - LinkedIn: https://www.linkedin.com/in/carlotta-castelluccio Moderators Hamid Sadeghpour Saleh Cloud Solutions Architect, Microsoft MVP Avanade - LinkedIn: https://www.linkedin.com/in/h-sadeghpour/