AI
Introduction to GitHub Copilot
This GitHub Copilot training course teaches attendees how to get the most out of the Artificial Intelligence (AI) capabilities of Copilot through prompting and iteration.
GitHub Copilot is powered by OpenAI’s language model, which has been trained on a massive dataset of public code repositories. It helps developers write code by suggesting lines and entire functions. This course teaches attendees how to leverage GitHub Copilot’s AI capabilities with proper prompting so that Copilot can produce code that they would have to write themselves.
Objectives
- Gain foundational knowledge of generative AI and Large Language Models (LLMs)
- Gain practical experience in prompt engineering (crafting) for coding tasks
- Iterate with Copilot
Duration
1 day
Audience
- This course is best suited for the following student profiles:
- Software developers
- IT architects
- Technical managers
Prerequisites
Experience coding in Python or other programming languages.
- Chapter 1 – GitHub Copilot: The Worlds First At-Scale Generative AI Coding Tool
- What is GitHub Copilot?
- Machine Learning and Generative Models
- Generative AI and Large Language Models (LLMs)
- AI-Powered Chatbots
- Retrieval-Based Chatbots
- Generative Chatbots
- Enhancing Chatbot Performance with LLMs
- Context-aware conversation handling
- OpenAI Codex
- The Pair Programming Paradigm
- The Pragmatic Programmer’s Rubber Duck Debugging Modality
- Benefits of Copilot
- Copilot Privacy
- Copilot Individual and Business Plans
- Summary
- A Brief History of Machine Learning
- Generative AI and Large Language Models (LLMs): Applications
- What is Transfer Learning?
- Benefits of Transfer Learning
- Challenges of Transfer Learning
- Chapter 2 – Getting Started with GitHub Copilot
- Getting started in Visual Studio (VS) Code
- Enable GitHub Copilot in Visual Studio Code
- Enable Inline Suggestions in Visual Studio Code
- Prompt a Copilot code Suggestion
- Copilot Quick Fix
- Question Answering
- HTML & CSS: Live Preview Extension
- JavaScript: Regular Expressions
- JavaScript: Unit Testing
- Evaluating Multiple Suggestions
- Synthesizing Solutions
- Summary
- Chapter 3 – Copilot Chat
- What is Copilot Chat?
- Open Copilot Chat
- Why Build a Chat Feature Directly in VS Code?
- Inline Copilot Chat Experience
- Open Chat Session in the Editor Space
- Chat History
- Slash commands
- /createWorkspace command
- /explain command
- /tests command
- Summary
- Chapter 4 – Prompt Engineering for Copilot
- What is prompt engineering?
- Prompt Types
- Prompt Context
- Prompt Word Choice
- Prompt Formatting
- Python: Process a JSON File Using Prompt Engineering
- Summary: Best Practices for Prompt Engineering
- LLMs as 0-Shot Learning
- Zero-Shot Prompting
- LLMs as 1-Shot Learning
- LLMs as Multi-Shot Learning
- Few-Shot Prompting
- Chain-of-Thought Prompting
- How is Standard prompting different than Chain-of-Thought Prompting:
- How does Cot works better than N-shot prompting
- Context Aware Chatbots
- Chapter 5 – Data Analysis with Copilot
- GitHub Copilot can also be used in Jupyter Notebooks
Lab Exercises
- Lab 1. Leverage GitHub Copilot to Enhance a Website Using Bootstrap
- Lab 2. Develop a Webpage using Copilot Chat
- Lab 3. Develop a REST API
- Lab 4. Analyze Gapminder Data
Is there a discount available for current students?
UMBC students and alumni, as well as students who have previously taken a public training course with UMBC Training Centers are eligible for a 10% discount, capped at $250. Please provide a copy of your UMBC student ID or an unofficial transcript or the name of the UMBC Training Centers course you have completed. Asynchronous courses are excluded from this offer.
What is the cancellation and refund policy?
Student will receive a refund of paid registration fees only if UMBC Training Centers receives a notice of cancellation at least 10 business days prior to the class start date for classes or the exam date for exams.