Skip to main content

Fundamentals of Retrieval Augmented Generation

Track:
PyData: LLMs
Type:
Talk
Level:
intermediate
Room:
Terrace 2A
Start:
10:45 on 12 July 2024
Duration:
30 minutes

Abstract

Retrieval Augmented Generation (RAG) has emerged in recent years as a popular technique at the crossroads of Information Retrieval and Natural Language Generation. It represents a promising new approach that combines the strengths of both retrieval-based systems and generative AI models, aiming to address the limitations of each, while enhancing their overall performance on document intelligence tasks. This talk will introduce the key frameworks, methodologies and advancements in RAG, exploring its ability to empower Large Language Models with a deeper comprehension of context, by leveraging pre-existing knowledge from external corpora. We will review the theoretical foundations, practical applications, and technical challenges associated with RAG, showcasing its potential to impact various fields, such as document summarization or database management. Through this talk, attendees will gain insights into the most relevant topics related to RAG, including token embedding, vector indexing and semantic similarity search.


The speaker

Catalin Hanga

Catalin Hanga

Catalin Hanga (PhD) is a Data Scientist, currently working at the Open Innovation - AI Lab of Iveco Group in Switzerland. His main focus is research and development of advanced machine learning algorithms for solving technical or business problems in the automotive industry. His recent projects include designing a document intelligence chatbot based on Retrieval Augmented Generation, as well as implementing autonomous LLM agents using the ReAct framework. Prior to this, he briefly worked in a similar role for a startup in the insurtech industry. He has obtained a PhD in Mathematics from the University of York, UK, and holds an M.Sc. in Physics from the University of Bucharest, Romania. During his M.Sc. studies, he also worked as a researcher at CERN in Geneva, Switzerland, analyzing experimental data collected by the detectors of the Large Hadron Collider.