Ornella Vaccarelli
Ornella Vaccarelli is a Senior Research Scientist at iCoSys and the Lead Scientist at SCAI (Swiss Center for Augmented Intelligence), where she pioneers innovative AI solutions across diverse domains. With expertise ranging from computer vision and computational physics to the latest developments in large language models (LLMs), she bridges cutting-edge research and practical application.
Her collaborative projects span from fundamental research at EPFL, focused on sustainable materials for solar cells, to developing an LLM-RAG system for the Swiss parliament and the Parliamentary Library. Ornella’s work not only advances scientific understanding but also transforms how industry and government leverage AI for informed decision-making.
A prolific researcher, her findings have been published in high-impact journals, and she is a regular speaker at international conferences. Ornella earned her PhD in Computational Physics from Sorbonne University in Paris and holds a Master’s in Theoretical Physics from the University of Bari.
Her career exemplifies a commitment to pushing the boundaries of AI while ensuring its responsible and effective integration into real-world applications.
Session
This hands-on workshop offers a deep dive into the development of intelligent AI systems using the Retrieval-Augmented Generation (RAG) framework and open-source tools. Participants will learn how to build a fully functional AI chatbot that can search and understand large collections of documents to generate accurate, context-aware responses.
Throughout the session, you’ll be guided through the complete RAG pipeline: from data ingestion and embedding generation to vector database integration and connection to an open-source LLM. Using frameworks such as LangChain, Hugging Face Transformers, and Ollama, you will set up each component yourself. The workshop also covers practical aspects like data handling and strategies to ensure data privacy and security during deployment.
Whether you're a developer looking to integrate LLMs into real-world applications or simply curious about how open-source AI chatbots work under the hood, this session will give you the skills and insights to build and deploy your own system.
By the end of the workshop, you'll walk away with a working open-source chatbot and a clear understanding of how to customize and expand it for your own use cases.