This lab will go into the basics of Retrieval Augmented Generation (RAG) through hands on access to a dedicated environment.

Explore the hidden dangers of prompt injection in Large Language Models (LLMs). This lab reveals how attackers manipulate LLMs to disclose private information and behave in ways that they were not intended to. Discover the intricacies of direct and indirect prompt injection and learn to implement effective guardrails.

NVIDIA Blueprints: PDF Ingestion, also known as NVIDIA-Ingest, or NV-Ingest, this blueprint is a scalable, performance-oriented document content and metadata extraction microservice. Including support for parsing PDFs, Word and PowerPoint documents, it uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images for use in downstream generative applications.

NVIDIA DGX H100 integration and validation environment for enterprise AI workflows.

Red Hat OpenShift AI, formerly known as Red Hat OpenShift Data Science, is a platform designed to streamline the process of building and deploying machine learning (ML) models. It caters to both data scientists and developers by providing a collaborative environment for the entire lifecycle of AI/ML projects, from experimentation to production. In this lab, you will explore the features of OpenShift AI by building and deploying a fraud detection model. This environment is built ontop of Dell R660's and Intel Xeon's 5th generation processors.

The Dell Reference Architecture environment is a full-stack solution that includes Dedicated Dell PowerSwitch High-Speed Networking, Dell PowerEdge Accelerator Optimized Compute nodes (XE9680 and R760xa servers), and Dell PowerScale Storage (F600 Array) as the hardware components and includes multiple MLOps and Kubernetes Platform solutions.

HPE Private Cloud AI, a pioneering turnkey solution, integrates NVIDIA and HPE technologies to simplify and accelerate AI development. It offers scalable configurations and enables experimentation and innovation in a secure on-premises environment. Explore its capabilities through hands-on lab experiences and easily streamline your AI journey.

This hands-on lab provides a comprehensive introduction to NVIDIA Run:ai, a powerful platform for managing AI workloads on Kubernetes. Designed for AI practitioners, data scientists, and researchers, this lab will guide you through the core concepts and practical applications of Run:ai's workload management system.

This lab provides hands-on experience with LiteLLM, an open-source AI gateway that centralizes and manages access to Large Language Models (LLMs). Throughout the five modules, you'll learn how to set up and use LiteLLM to control, monitor, and optimize your AI model interactions.

The AI Proving Ground GPU-as-a-Service environment is a fully automated solution that enables WWT engineers to build physical server environments with different server, CPU, GPU, and Operating System options.

In this lab, we'll be focusing on the programatic steps of Retrieval Augmented Generation (RAG). First, we'll discuss data chunking, how we break down our documents. Then, we'll explore how these chunks become embeddings, numerical representations. Finally, we'll see how a vector database helps us efficiently retrieve this information.

This lab will demonstrate how the Cisco Nexus Dashboard Fabric Controller can easily set up an AI/ML fabric with a simple point-and-click GUI. It will only do this easily without knowing the protocols or best practices. The controller will do the work.