Join Maria from Databricks for a comprehensive two-part workshop on Large Language Models (LLMs), aimed at transforming how we think about GenAI applications. In Part 1, we will discuss the world of open and proprietary LLMs, including a detailed exploration of a RAG (Retrieval Augmented Generation) use case. The exercise that follows focuses on the practical application of RAG, guiding you through the process of building a fully fledged RAG-powered chat-application. The second part of the talk is all about finetuning foundational models using your company data where we will discuss the complexities involved and the cost implications of building your own custom models. Seize this opportunity to revolutionize the internal business processes and elevate customer experiences with the power of Large Language Models.