Time Commitment: The entire workshop can be completed online without local setup. The environment setup takes 2 minutes, with exploring the samples requiring 1-3 hours depending on exploration depth.
Quick Start
- Fork this repository to your GitHub account
- Click Code → Codespaces tab → ... → New with options...
- Use the defaults – this will select the Development container created for this course
- Click Create codespace
- Wait ~2 minutes for the environment to be ready
- Jump straight to The first example
Arabic | Bengali | Bulgarian | Burmese (Myanmar) | Chinese (Simplified) | Chinese (Traditional, Hong Kong) | Chinese (Traditional, Macau) | Chinese (Traditional, Taiwan) | Croatian | Czech | Danish | Dutch | Estonian | Finnish | French | German | Greek | Hebrew | Hindi | Hungarian | Indonesian | Italian | Japanese | Korean | Lithuanian | Malay | Marathi | Nepali | Norwegian | Persian (Farsi) | Polish | Portuguese (Brazil) | Portuguese (Portugal) | Punjabi (Gurmukhi) | Romanian | Russian | Serbian (Cyrillic) | Slovak | Slovenian | Spanish | Swahili | Swedish | Tagalog (Filipino) | Tamil | Thai | Turkish | Ukrainian | Urdu | Vietnamese
- Core Concepts: Understanding Large Language Models, tokens, embeddings, and AI capabilities
- Java AI Ecosystem: Overview of Spring AI and OpenAI SDKs
- Model Context Protocol: Introduction to MCP and its role in AI agent communication
- Practical Applications: Real-world scenarios including chatbots and content generation
- → Start Chapter 1
- Multi-Provider Configuration: Set up GitHub Models, Azure OpenAI, and OpenAI Java SDK integrations
- Spring Boot + Spring AI: Best practices for enterprise AI application development
- GitHub Models: Free AI model access for prototyping and learning (no credit card required)
- Development Tools: Docker containers, VS Code, and GitHub Codespaces configuration
- → Start Chapter 2
- Prompt Engineering: Techniques for optimal AI model responses
- Embeddings & Vector Operations: Implement semantic search and similarity matching
- Retrieval-Augmented Generation (RAG): Combine AI with your own data sources
- Function Calling: Extend AI capabilities with custom tools and plugins
- → Start Chapter 3
- Pet Story Generator (
petstory/): Creative content generation with GitHub Models - Foundry Local Demo (
foundrylocal/): Local AI model integration with OpenAI Java SDK - MCP Calculator Service (
calculator/): Basic Model Context Protocol implementation with Spring AI - → Start Chapter 4
- GitHub Models Safety: Test built-in content filtering and safety mechanisms (hard blocks and soft refusals)
- Responsible AI Demo: Hands-on example showing how modern AI safety systems work in practice
- Best Practices: Essential guidelines for ethical AI development and deployment
- → Start Chapter 5
-9333EA?style=for-the-badge&labelColor=E5E7EB&color=9333EA){kind=icon}
-C084FC?style=for-the-badge&labelColor=E5E7EB&color=C084FC){kind=icon}
-E879F9?style=for-the-badge&labelColor=E5E7EB&color=E879F9){kind=icon}
If you get stuck or have any questions about building AI apps, join:
If you have product feedback or errors while building visit:
![@github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=64&v=4){kind=small}