Practical Applications of Generative AI: Building a Chatbot for Document Q&A

Explore the practical applications of Generative AI in building a chatbot capable of answering questions about specific documents in this 52-minute talk by Maxime Huvet, Lead Data Scientist at dunnhumby, presented at the Data Science Festival. Gain insights into the recent explosion of Generative AI and Large Language Models (LLMs), and discover how to leverage these breakthroughs beyond direct LLM integration. Learn about the Retrieval Augmented Generation (RAG) technique, which enables chatbots to answer questions related to previously unseen documents. Delve into an introduction to Generative AI and transformers, followed by an in-depth exploration of RAG logic, its benefits, and potential drawbacks. Suitable for anyone interested in generative AI and its potential applications, this talk provides a comprehensive overview of creating advanced document-based chatbots using cutting-edge AI technologies.