NVIDIA Instructor-Led Workshop: Building RAG Agents with LLMs (UNN)

What's This Event About?

This hands-on workshop teaches participants how to build RAG (Retrieval-Augmented Generation) agents using Large Language Models from scratch[1]. Attendees will learn advanced LLM composition techniques, including how to design retrieval-augmented generation systems, implement dialog management, and leverage embedding models for efficient content retrieval[3]. The workshop covers practical skills such as pipeline design, state management, and bundling systems into deliverable formats[1][3].

Who Is It For?

The workshop is designed for developers and AI enthusiasts interested in AI, NLP, and chatbot development[1]. It's particularly suited for developers looking to integrate AI into their projects and anyone seeking to enhance their skills in building intelligent agent systems[1].

What to Expect

Participants will receive step-by-step guidance from a certified NVIDIA instructor in a hands-on learning environment[1]. The workshop covers LLM inference interfaces, pipeline design with tools like LangChain and Gradio, dialog management with running states, and practical implementation of retrieval-augmented generation agents[7]. Attendees will work through real examples and learn how to design systems that can answer questions about datasets without fine-tuning[3].

Why Attend?

RAG agents represent a powerful emerging capability for improving productivity through retrieval-based LLM systems that can hold informed conversations using tools and documents[3]. This workshop provides practical, hands-on experience implementing these systems efficiently, along with networking opportunities with fellow AI enthusiasts[1].