RAG at Scale: Building Production-Ready GenAI Solutions
This session serves as a deep dive into the strategies and best practices for data scientists aiming to build, fine-tune, and scale Retrieval Augmented Generation (RAG) based Generative AI (GenAI) applications. The core objectives for data scientists in the AI development cycle center around providing highly relevant results for end users and maintaining cost-effectiveness to support the sustainable growth of their products. RAG is a pivotal method that enables GenAI applications to operate effectively on proprietary data. At the heart of RAG are robust retrieval systems, which are crucial for delivering high-quality user experiences. Francesca Lazzeri will share best practices and tools designed to optimize RAG capabilities for GenAI applications across various scales. She will also highlight advanced capabilities and increased storage limits that allow for more detailed control of retrieval pipelines, ensuring that performance and cost are not compromised.
Francesca Lazzeri is Principal Director of AI Engineering at Microsoft, where she leads an organization of data scientists and machine learning scientists building AI applications on the Cloud, utilizing data and techniques spanning from generative AI, time series forecasting, experimentation, causal inference, computer vision, natural language processing, reinforcement learning. Before joining Microsoft, she was a Research Fellow at Harvard University in the Technology and Operations Management Unit, Technical Advisor at the Massachusetts Institute of Technology, and Adjunct Professor of Python for AI at Columbia University. You can find her on LinkedIn and Medium.