- This event has passed.
RAG, How and Why to Build It?
January 17 @ 9:00 am – 9:30 am PST
In this session, we explore the foundations and benefits of Retrieval Augmented Generation (RAG) in building custom Large Language Models (LLMs) using proprietary company data. RAG provides an efficient, cost-effective alternative to full model retraining, allowing companies to ensure a consistent voice and tap into specific knowledge outside the capabilities of general LLMs. This approach combines search-engine-like retrieval with LLM queries, delivering up-to-date, targeted answers.
This recording of our 11th “Approachable AI” webinar is designed for decision-makers who want to explore AI through customer, product, and business lenses. While AI can be highly technical, we view technology as a means to an end—creating impactful and accessible solutions.
Throughout the webinar, we demonstrate a simple RAG setup using Microsoft Azure, comprising a search engine, query augmentation middleware, and adaptable front-end applications. We discuss the importance of tailored prompts to meet diverse use cases and offer a practical guide to deploying RAG for enhanced AI customization. This session is for business and technical professionals looking to put RAG into practice.