NVIDIA Building RAG Agents with LLMs

Overview

Agents powered by large language models (LLMs) are rapidly gaining traction across organisations. The course focuses on designing retrieval-augmented generation (RAG) systems that combine external knowledge with LLMs to answer questions, reason over documents, maintain dialog state, and operate at scale

Objectives

By the end of this course, leaner will be able to:

• Compose an LLM system that interacts predictably with users by leveraging internal and external reasoning components.
• Design a dialog-management and document-reasoning system that maintains state and converts information into structured formats.
• Leverage embedding models for efficient similarity queries for content retrieval and dialog guard-railing.
• Implement, modularise, and evaluate a retrieval-augmented generation agent that can answer questions about a dataset without any fine-tuning.

Prerequisites

Introductory deep learning experience, comfortable with frameworks like PyTorch and transfer-learning. Intermediate Python programming skills, including object-oriented programming and use of typical libraries.

Course Outline