Rectangle 11806-min
Guided Hackathon

Azure OpenAI Fundamentals Hackathon

Gain hands-on experience with prompt engineering and machine learning best practices in this 1-day guided hackathon. 

Book Your Hackathon
View Hackathon Topics
Students in a classroom-min

Overview

This hack is for anyone who wants to gain hands-on experience experimenting with prompt engineering and machine learning best practices, and apply them to generate effective responses from ChatGPT and OpenAI models. 

Participants will learn how to: 

  • Compare OpenAI models and choose the best one for a scenario 
  • Use prompt engineering techniques on complex tasks 
  • Manage large amounts of data within token limits, including the use of chunking and chaining techniques 
  • Grounding models to avoid hallucinations or false information 
  • Implement embeddings using search retrieval techniques 
  • Evaluate models for truthfulness and monitor for PII detection in model interactions 

About this course

Challenges

Challenge 00: Prerequisites - Ready, Set, GO! 
  • Prepare your workstation to work with Azure. 
Challenge 01: Prompt Engineering 
  • What's possible through Prompt Engineering 
  • Best practices when using OpenAI text and chat models 
Challenge 02: OpenAI Models & Capabilities 
  • What are the capacities of each Azure OpenAI model? 
  • How to select the right model for your application 
Challenge 03: Grounding, Chunking, and Embedding 
  • Why is grounding important and how can you ground a Large Language Model (LLM)? 
  • What is a token limit? How can you deal with token limits? What are techniques of chunking? 
Challenge 04: Retrieval Augmented Generation (RAG) 
  • How do we create ChatGPT-like experiences on Enterprise data? In other words, how do we "ground" powerful LLMs to primarily our own data? 
Challenge 05: Responsible AI 
  • What are services and tools to identify and evaluate harms and data leakage in LLMs? 

What are ways to evaluate truthfulness and reduce hallucinations? What are methods to evaluate a model if you don't have a ground truth dataset for comparison? 

Duration

1 Day

Level

Level 200

Ready to get started?

 
Book Your OpenHack