Earn an NVIDIA DLI certificate in Building RAG Agents with LLMs with this free live instructor-led one-day online workshop!
Building RAG Agents with LLMs
Friday November 13, 2026 from 9 AM to 5 PM EST
💡 INFO ABOUT THE WORKSHOP
1 – This is a hands-on technical workshop. You should be comfortable with Python programming.
2 – You will code, debug, and test several different RAG Agent solutions and earn a numbered traceable certificate from NVIDIA – all in one day!
3 – Current ECPI University student/faculty/alumni researchers with an email ending in “ecpi.edu” can attend from home for FREE. No voucher is required.
4 – You should have at least basic familiarity with the concepts listed below. You do not need to be an expert in all of them.
5 – More details on the workshop are here: https://www.nvidia.com/en-au/training/instructor-led-workshops/building-rag-agents-with-llms/
HOW TO REGISTER:
➡️ Send an email to NVIDIA Ambassador Paul Nussbaum at PNussbaum@ECPI.edu.
CONCEPTS YOU SHOULD BE FAMILIAR WITH
⬇️ Read the list below.
✔️ If these topics already sound familiar, you are probably ready for the workshop.
💬 If some are unfamiliar, copy and paste everything below into your favorite chatbot and ask follow-up questions until you have a basic understanding.
Hello chatbot. Please explain each item below in brief, layperson terminology. Include a small Python example and its expected output when appropriate. Do not assume I already understand technical jargon. If one item depends on another concept, explain that concept first. Keep each explanation brief unless I ask a follow-up question.
➜ FAMILIARITY WITH CHATBOTS
- Using ChatGPT or another chatbot to answer questions
- Adding a document to a chatbot question
- Trying the same question with two or more different chatbots
- Spotting an incorrect or irrelevant chatbot answer
- Asking a chatbot to use a tool, such as web search
➜ FAMILIARITY WITH PYTHON
- Python basics (variables, functions, lists, dictionaries, loops)
- Python libraries (using code written by others)
- Object-oriented Python (objects and classes – basic familiarity is enough)
- JSON (structured key/value data)
- Calling an API from Python (one program requesting information from another)
➜ FAMILIARITY WITH DEEP LEARNING AND LLMS
- Neural networks (software that learns patterns from examples)
- Deep learning (large neural networks with many layers)
- Transfer learning (adding layers and/or re-training a neural network)
- LLMs (AI models that understand and generate language)
- Using an LLM from a Python program
- Prompts and context (instructions and information supplied to an LLM)
➜ FAMILIARITY WITH RAG AND AI AGENTS
- RAG (Retrieve useful information, Augment the prompt with it, Generate an answer)
- Embeddings (representing meaning with numbers)
- Vector search (finding information with similar meaning)
- AI tools / tool calling (letting an AI application use other software)
- AI agents (software that can choose actions or tools)
- AI evaluation (checking whether retrieval and answers are actually good)
➜ FAMILIARITY WITH HOW AI APPLICATIONS ARE BUILT
- Web basics (browser, server, URL, port, request, response)
- Gradio (a browser interface for Python programs)
- Software pipelines (one processing step feeds the next)
- LangChain (software for connecting AI application components)
- Application state (information carried from one step to another)
- Containers / Docker (packaging software so it runs consistently)
- Microservices (separate software services that work together)
➜ After explaining the list, ask me which topics I would like you to explain further.
