RAG-based AI Assistants: from demo to product, addressing real-world challenges
2024-12-11 , Auditorium

Let’s explore our journey to bring an enterprise assistant into production, addressing the real-world complexities of development and deployment, sharing our experience with security, advanced ETL integrations, automation, and frontend/backend customizations. From a prototype based on Azure OpenAI Chat Playground (aka Bring-Your-Own-Data), we’ll walk you through how we moved to a custom architecture, optimized to meet specific user and business needs, using Microsoft technologies, including Azure AI Search, Semantic Kernel, and Kernel Memory.

Gianni is a Microsoft MVP for the AI category, former Windows Embedded/Development since 2011, focused on emerging technologies, AI and Virtual/Augmented/Mixed Reality since 2013. Currently he is R&D Technical Lead in Deltatre's Innovation Lab, designing and prototyping next generation solutions for sport related experiences and services, from apps, tools and end-to-end cloud architectures. Besides that, he's an active member of the local community “Torino Technologies Group” (TTG), Pluralsight online courses author, writes articles on his blog and he's speaker in national and international tech conferences and events.

With a master's degree in Biomedical Engineering from Politecnico di Torino and a 2nd-level master's in Sports Engineering, I joined Deltatre's Innovation Lab in 2019, an R&D team focused on areas ranging from computer vision to ML and NLP. As a Data Scientist, my expertise lies in handling diverse data formats and pioneering exploratory analysis techniques. Recently, within the Innovation Lab, my focus includes collaborating on the exploration of RAG-based solutions to enhance our NLP capabilities.