info_outline
After Show With Pamela Fox
05/18/2024
After Show With Pamela Fox
After Show With Pamela Fox Presented "Building a RAG app to chat with your data" on March 28, 2024 Talk abstract: One of the most popular use cases for generative AI is RAG (Retrieval-Augmented-Generation), a technique that feeds context to an LLM (large language model) so that it can answer questions according to sources. Thousands of developers have deployed RAG applications to chat with their data, both for internal enterprise data (like HR or support) and external public data (like government or retail). In this talk, I'll show how to build a RAG with Azure technology, like Azure AI search and Azure OpenAI, and share best practices for data ingestion, orchestration, and evaluation. Pamela Fox Pamela Fox is a Cloud Advocate in Python at Microsoft. Previously, she was a lecturer for UC Berkeley and the creator of the computer programming curriculum for Khan Academy. She has founded GDI chapters globally and develops curriculum for GDI. Questions Can you introduce yourself? When did you get started with python? Can you give us a little information about RAG and how you got started with it? Since starting RAG, has your opinion changed any? If people were not using RAG, what is the alternative? What is your experience using small language models with RAG? What about entitlements/authorization/access control with RAG? What do you think large context windows leads us? Do you remember your first technical presentation? What do you like to do for fun? Do you remember when you first started using Azure? What was the background story for the presentation? Was there anything you didn't get to mention that you wanted to? Were there any questions you wished people would ask that they didn't? What you recommend for anyone getting started with RAG or LLMs in general? Links Presentation Recording: Slides from presentation: Blog: Github: Twitter/X: LinkedIn:
/episode/index/show/e07b924e-cba3-43ca-9ee2-5c2d93df0649/id/31366527
