Crafting your own RAG system: Leveraging 30+ LLMs for enhanced performance
Conference (INTERMEDIATE level)
Paris 242AB
In this talk you'll learn how to set up a RAG (Retrieval-Augmented Generation) system against 30+ different Large Language Models using Java.
We'll show you step-by-step how to ingest documents, choose the best text splitter strategies, find similar documents, answer questions, and create a chatbot.
Then, we’ll see how to test and compare different AI models, both from open sources and private ones, and whether they are stored on your own computer or accessed online.
You'll walk away knowing how to setup a well balanced RAG system using Java and the best performing and/or cheapest LLM.
We'll show you step-by-step how to ingest documents, choose the best text splitter strategies, find similar documents, answer questions, and create a chatbot.
Then, we’ll see how to test and compare different AI models, both from open sources and private ones, and whether they are stored on your own computer or accessed online.
You'll walk away knowing how to setup a well balanced RAG system using Java and the best performing and/or cheapest LLM.
Stephan Janssen
Devoxx
As an organizer of Devoxx Belgium, I am passionate about conducting research and development (R&D) that leads to new features in Devoxx-related applications like the CFP web app. In recent years, I have been exploring and experimenting with cutting-edge technologies such as large language models (LLMs), convolutional neural networks (CNNs), and other artificial intelligence (AI) tools. In this talk, I will share my practical knowledge and experiences with the developer community, including code examples and hands-on demonstrations.
Français 
English