Paving a Painless Path to Production AI in your Java Applications

Artificial Intelligence is eating the world, and new and amazing use cases are being discovered every day. These uses for AI aren't just in new domains, but perhaps even more importantly, in areas that are broadly applicable in countless "everyday" mission-critical applications.

This places developers in a difficult position: how do you take advantage of these new capabilities without significant investments in both time and tooling to become an AI expert? How do you plug AI into your existing applications without massive rearchitecting and rewriting?

Come to this session for a dive-into-the-deep-end introduction of key concepts and tools at your disposal and even better, a *live-coding adventure* using Spring Boot, Java, and Azure OpenAI. You'll leave this session with the knowledge and confidence to pave a painless (and powerful) path to production AI in your Java applications.

Transcript

1. Paving a Painless Path to Production AI in your Java Applications Mark Heckler Principal Cloud Advocate, Java/JVM Languages markheckler@microsoft.com mark@thehecklers.com @mkheck
2. @mkheck Who am I? • Architect & Developer • Advocate • Author • Java Champion, Rockstar • Kotlin Developer Expert • Pilot 🛩
3. @mkheck The book https://bit.ly/springbootbook @springbootbook
4. @mkheck What this session IS NOT It isn’t an exhaustive introduction of AI, AI concepts, or AI tools. It isn’t a deep dive into the details of how to use the tools. It isn’t a deep dive into the details of how the tools work. It isn’t a deep dive into the details of how to architect your applications to use AI. It isn’t a deep dive into the details of how to deploy your applications that use AI. We have only 30 minutes! So…
5. @mkheck What this session IS • A fast-paced, selective introduction of key AI concepts • A quick review of tools at your disposal for building AI-enabled apps • A live-coding adventure™ demonstrating those concepts using Spring Boot, Java, and Azure OpenAI NOTE: Concepts are portable, tools “rhyme”
6. @mkheck What’s the plan? • Concepts • Translate concepts to reality • See it in action • Continue conversation after
7. @mkheck Concepts • Models* • Text • Images • Audio • Generative Pre-trained Transformer (GPT) • Tokens, tokenization • Embeddings • Retrieval Augmented Generation (RAG) * Currently. This is evolving.
8. @mkheck Translating Concepts to Reality • ChatGPT for text (and others, e.g. GitHub Copilot) • DALL-E for images • API-based models for audio • Developers access the underlying models • Most use cases are currently textual • Most models expose APIs • Useful abstractions add significant value to development
9. @mkheck VS Code • Cross platform, multiple languages • Great Java & Spring Boot plugins • Phenomenal AI plugins • https://code.visualstudio.com/
10. @mkheck GitHub Copilot • Copilot • Read my comments • Read my mind (code with me) • Copilot Chat: chat with me • https://github.com/features/copilot
11. @mkheck Azure Spring Apps, Azure Container Apps, etc. • Natural and intelligent platform evolution for developers • Leverages dominant framework for Java (ASA) • Leverages containerization for portability and versatility (ACA) • Easy to deploy, manage, monitor, scale apps • https://aka.ms/azurespringapps • https://aka.ms/azurecontainerapps
12. @mkheck
13. @mkheck Helpful resources • https://github.com/mkheck/production-ai • @springbootbook • @mkheck