Setting Up the Development Environment for Generative AI for Java

January 25, 2026 · View on GitHub

Quick Start: Code in the Cloud in 2 minutes - Jump to GitHub Codespaces Setup - no local installation required and uses github models!

Interested in Azure OpenAI?, see our Azure OpenAI Setup Guide with steps to create a new Azure OpenAI resource.

What You'll Learn

  • Set up a Java development environment for AI applications
  • Choose and configure your preferred development environment (cloud-first with Codespaces, local dev container, or full local setup)
  • Test your setup by connecting to GitHub Models

Table of Contents

Introduction

This chapter will guide you through setting up a development environment. We'll use GitHub Models as our primary example because it's free, easy to set up with just a GitHub account, requires no credit card, and provides access to multiple models for experimentation.

No local setup required! You can start coding immediately using GitHub Codespaces, which provides a full development environment in your browser.

Screenshot: GitHub Models

We recommend using GitHub Models for this course because it's:

  • Free to get started
  • Easy to set up with just a GitHub account
  • No credit card required
  • Multiple models available for experimentation

Note: The GitHub Models used in this training have these free limits:

  • 15 requests per minute (150 per day)
  • ~8,000 words in, ~4,000 words out per request
  • 5 concurrent requests

For production use, upgrade to Azure AI Foundry Models with your Azure account. Your code doesn't need to change. See the Azure AI Foundry documentation.

Step 1: Set Up Your Development Environment

We've created a preconfigured development container to minimize setup time and ensure you have all the necessary tools for this Generative AI for Java course. Choose your preferred development approach:

Environment Setup Options:

Start coding in 2 minutes - no local setup required!

  1. Fork this repository to your GitHub account

    Note: If you want to edit the basic config please have a look at the Dev Container Configuration

  2. Click Code → Codespaces tab → ... → New with options...
  3. Use the defaults – this will select the Dev container configuration: Generative AI Java Development Environment custom devcontainer created for this course
  4. Click Create codespace
  5. Wait ~2 minutes for the environment to be ready
  6. Proceed to Step 2: Create GitHub Token
Screenshot: Codespaces submenu Screenshot: New with options Screenshot: Create codespace options

Benefits of Codespaces:

  • No local installation required
  • Works on any device with a browser
  • Pre-configured with all tools and dependencies
  • Free 60 hours per month for personal accounts
  • Consistent environment for all learners

Option B: Local Dev Container

For developers who prefer local development with Docker

  1. Fork and clone this repository to your local machine

    Note: If you want to edit the basic config please have a look at the Dev Container Configuration

  2. Install Docker Desktop and VS Code
  3. Install the Dev Containers extension in VS Code
  4. Open the repository folder in VS Code
  5. When prompted, click Reopen in Container (or use Ctrl+Shift+P → "Dev Containers: Reopen in Container")
  6. Wait for the container to build and start
  7. Proceed to Step 2: Create GitHub Token
Screenshot: Dev container setup Screenshot: Dev container build complete

Option C: Use Your Existing Local Installation

For developers with existing Java environments

Prerequisites:

Steps:

  1. Clone this repository to your local machine
  2. Open the project in your IDE
  3. Proceed to Step 2: Create GitHub Token

Pro Tip: If you have a low-spec machine but want VS Code locally, use GitHub Codespaces! You can connect your local VS Code to a cloud-hosted Codespace for the best of both worlds.

Screenshot: created local devcontainer instance

Step 2: Create a GitHub Personal Access Token

  1. Navigate to GitHub Settings and select Settings from your profile menu.
  2. In the left sidebar, click Developer settings (usually at the bottom).
  3. Under Personal access tokens, click Fine-grained tokens (or follow this direct link).
  4. Click Generate new token.
  5. Under "Token name", provide a descriptive name (e.g., GenAI-Java-Course-Token).
  6. Set an expiration date (recommended: 7 days for security best practices).
  7. Under "Resource owner", select your user account.
  8. Under "Repository access", select the repositories you want to use with GitHub Models (or "All repositories" if needed).
  9. Under "Account permissions", find Models and set it to Read-only.
  10. Click Generate token.
  11. Copy and save your token now – you won't see it again!

Security Tip: Use the minimum required scope and shortest practical expiration time for your access tokens.

Step 3: Test Your Setup with the GitHub Models Example

Once your development environment is ready, let's test the GitHub Models integration with our example application in 02-SetupDevEnvironment/examples/github-models.

  1. Open the terminal in your development environment.

  2. Navigate to the GitHub Models example:

    cd 02-SetupDevEnvironment/examples/github-models

  3. Set your GitHub token as an environment variable:

    # macOS/Linux
export GITHUB_TOKEN=your_token_here

# Windows (Command Prompt)
set GITHUB_TOKEN=your_token_here

# Windows (PowerShell)
$env:GITHUB_TOKEN="your_token_here"

  4. Run the application:

    mvn compile exec:java -Dexec.mainClass="com.example.githubmodels.App"

You should see output similar to:

Using model: gpt-4.1-nano
Sending request to GitHub Models...
Response: Hello World!

Understanding the Example Code

First, let's understand what we just ran. The example under examples/github-models uses the OpenAI Java SDK to connect to GitHub Models:

What this code does:

  • Connects to GitHub Models using your personal access token
  • Sends a simple "Say Hello World!" message to the AI model
  • Receives and displays the AI's response
  • Validates your setup is working correctly

Key Dependency (in pom.xml):

<dependency>
    <groupId>com.openai</groupId>
    <artifactId>openai-java</artifactId>
    <version>2.12.0</version>
</dependency>

Main Code (App.java):

// Connect to GitHub Models using OpenAI Java SDK
OpenAIClient client = OpenAIOkHttpClient.builder()
    .apiKey(pat)
    .baseUrl("https://models.inference.ai.azure.com")
    .build();

// Create chat completion request
ChatCompletionCreateParams params = ChatCompletionCreateParams.builder()
    .model(modelId)
    .addSystemMessage("You are a concise assistant.")
    .addUserMessage("Say Hello World!")
    .build();

// Get AI response
ChatCompletion response = client.chat().completions().create(params);
System.out.println("Response: " + response.choices().get(0).message().content().orElse("No response content"));

Summary

Great! You now have everything set up:

  • Created a GitHub Personal Access Token with the right permissions for AI model access
  • Got your Java development environment running (whether that's Codespaces, dev containers, or local)
  • Connected to GitHub Models using the OpenAI Java SDK for free AI development
  • Tested it all works with a simple example that talks to AI models

Next Steps

Chapter 3: Core Generative AI Techniques

Troubleshooting

Having issues? Here are common problems and solutions:

  • Token not working?

    • Ensure you copied the entire token without any extra spaces
    • Verify the token is set correctly as an environment variable
    • Check that your token has the correct permissions (Models: Read-only)

  • Maven not found?

    • If using dev containers/Codespaces, Maven should be pre-installed
    • For local setup, ensure Java 21+ and Maven 3.9+ are installed
    • Try mvn --version to verify installation

  • Connection issues?

    • Check your internet connection
    • Verify GitHub is accessible from your network
    • Ensure you're not behind a firewall blocking the GitHub Models endpoint

  • Dev container not starting?

    • Ensure Docker Desktop is running (for local development)
    • Try rebuilding the container: Ctrl+Shift+P → "Dev Containers: Rebuild Container"

  • Application compilation errors?

    • Ensure you're in the correct directory: 02-SetupDevEnvironment/examples/github-models
    • Try cleaning and rebuilding: mvn clean compile

Need help?: Still having issues? Open an issue in the repository and we'll help you out.