In this session, we will explore the process of deploying a RAG based Document Q&A application (a use case of Large Language Models). This deployment will be performed on Gradio and Hugging Face Spaces, as a demonstration of how you can quickly provide a front-end visual interface to your LLM application to enable initial testing and feedback.
Agenda for the session
- How RAG improves on vanilla Prompt Engineering
- The RAG Workflow for a Document Q&A Chat Application
- Introduction to Gradio and Hugging Face Spaces
- Deploying your RAG Chat App to Hugging Face Spaces
About Speakers
Mr. Vinicio De Sola
Senior Data Scientist - Aspen Capital
-Specializes in Machine Learning Techniques and redeveloping models to include automation
-Studied Cryptocurrencies and Smart Beta Factors in the space.
-Before switching to finance, was an entrepreneur in diverse areas like E-learning, E-commerce, and Engineering
-Mentor at Great Learning
