Skip to main content

NVIDIA Building RAG Agents with LLMs

H45WQS

Table of Contents

Table of Contents

    Course ID

    H45WQS

    Duration

    1 day

    Format

    ILT/VILT

    Overview

    This course teaches you how to deploy a large language model (LLM) agent system in practice and scale up your system to meet the demands of users and customers. Along the way, you learn advanced LLM orchestration techniques for internal reasoning, dialog management, tooling, and retrieval.


    This course takes a deep dive into the world of large language model (LLM) inference interfaces and the strategic use of microservices. You explore the design of LLM pipelines, and how to create dynamic and efficient systems using tools like LangChain, Gradio, and LangServe. You also learn how to manage dialog states, integrate knowledge extraction techniques, and employ strategies for handling long-form documents. This course also covers embeddings for semantic similarity and guardrailing, and how to implement vector stores for document retrieval.

    Course ID

    H45WQS

    Duration

    1 day

    Format

    ILT/VILT

    Audience

    This course is ideal for AI practitioners like developers, data scientists, AI engineers, and technical artists, who need to execute language-related tasks daily, such as text classification, content generation, sentiment analysis, and customer chat support, and they seek to do so in the most cost-effective way.

    Prerequisites

    Before attending this course, you should have Introductory deep learning knowledge, intermediate Python experience (including object-oriented programming and libraries), and understand the fundamentals of working with PyTorch.

    Objectives

    After completing this course, you should be able to:

    • Compose an LLM system that can interact predictably with a user by leveraging internal and external reasoning components
    • Design a dialog management and document reasoning system that maintains state and coerces information into structured formats
    • Use embedding models for efficient similarity queries for content retrieval and dialog guardrailing
    • Implement, modularize, and evaluate a RAG agent that can answer questions about research papers in its dataset without any fine-tuning
    • Understand RAG agents and the tools necessary to develop own LLM applications

    Certifications and related exams

    Upon successful completion of this course, students receive an NVIDIA DLI certificate of competency.

    Divider

    Course outline

    Module 1: LLM Inference Interfaces

    Module 2: Pipeline Design with LangChain, Gradio, and LangServe

    Module 3: Dialog Management with Running States

    Module 4: Working with Documents

    Module 5: Embeddings for Semantic Similarity and Guardrailing

    Module 6: Vector Stores for RAG Agents

    Module 7: Evaluation, Assessment, and Q&A

    5 reasons to choose HPE as your training partner

    1. Learn HPE and in-demand IT industry technologies from expert instructors.
    2. Build career-advancing power skills.
    3. Enjoy personalized learning journeys aligned to your company’s needs.
    4. Choose how you learn: in-person , virtually , or online —anytime, anywhere.
    5. Sharpen your skills with access to real environments in virtual labs .

    Explore our simplified purchase options, including HPE Education Learning Credits .

    Recommended for you