microsoft/Generative-AI-for-beginners-java

Learn Generative AI fundamentals through Java programming.

What it solves

This course gives Java developers a clear, beginner-friendly path into generative AI. It removes the guesswork by offering a structured curriculum that can be completed entirely online, without needing to set up a local development environment. It covers everything from understanding core AI concepts to building real-world applications, so learners can go from zero to working AI features quickly.

How it works

The workshop is divided into five chapters. Chapter 1 introduces large language models, tokens, embeddings, and the Java AI ecosystem. Chapter 2 walks you through provisioning Azure AI Foundry services and setting up a Spring Boot project with Spring AI. Chapter 3 dives into core techniques like prompt engineering, embeddings, retrieval-augmented generation (RAG), and function calling. Chapter 4 offers practical samples—a pet story generator, a local AI model demo, and an MCP calculator—to apply what you've learned. Chapter 5 focuses on responsible AI, including content safety and best practices. The environment is pre-configured via GitHub Codespaces, so you can start exploring in about two minutes after cloning the repository.

Who it's for

This is for Java developers who are new to generative AI and want a practical, hands-on introduction. It's also suitable for students, hobbyists, or professionals who prefer learning in a browser without local installation friction. The course assumes some Java familiarity but no prior AI experience.

Highlights

  • Five-chapter curriculum that moves from fundamentals to responsible AI
  • Pre-built development container and GitHub Codespaces support for instant start
  • Uses Azure AI Foundry, Spring AI, and the official OpenAI Java SDK
  • Includes real projects like a pet story generator and an MCP calculator service
  • Translated into 50+ languages, making it accessible worldwide

Related

  • Project
    harshaneel/humanize

    humanize is an MIT‑licensed repo that ships two static, rule‑based skills—`humanize` (rewrites AI text to sound human) and `ai-check` (produces a forensic AI‑detection report). The skills work with any LLM agent (Claude Code, Codex CLI, ChatGPT desktop, Gemini, etc.) via a simple install script or marketplace command. Benchmarked on 25 diverse inputs, both internal and external perplexity‑based detectors rate the rewritten output as human‑like. The approach is offline, zero‑dependency, but cannot evade learned classifiers like GPTZero.

  • Project
    google/dotprompt

    Dotprompt is a cross‑language framework that defines an executable `.prompt` file format for generative AI. Each file bundles the prompt text, model configuration, input schema, and expected output schema, enabling validation, type‑safe execution, and reuse across JavaScript/TypeScript, Python, Go, Rust, and Java. The project ships core libraries, IDE extensions, web editors, a tree‑sitter grammar, and a CLI tool, all backed by CI testing. It is ideal for developers and prompt engineers who want structured, version‑controlled prompts that can be run directly from code or the command line.

  • Project
    swuecho/chat

    A self-hosted chat platform that supports multiple LLM providers like OpenAI, Claude, and Ollama, featuring a built-in API gateway and conversation management.

  • Project
    cropflre/nowen-note

    A self-hosted, private knowledge base and task management platform that features AI RAG capabilities, MCP support for AI agents, and multi-device synchronization.