Creating AI-infused Apps, the Easy Way 🤙
summary
Demonstrates adding AI to Java apps with a few lines of code by adding the OpenAI extension and declaring an interface annotated like @RegisterAIService so Quarkus wires calls to LangChain4j and Quarkus; return types auto‑unmarshall to objects. Shows RAG via EasyRAG with pgvector/chroma, MCP/tool integration, input/output guardrails, and a DevMCP dev server. Builds a jokes REST endpoint and a customer‑support agent that queries a bookings DB and enforces cancellation rules from ingested terms — demo mostly works though an LLM timeout appears.
AI-written summary · about
chapters (15)
- 0:00Introduction to AI with Java
- 1:54Getting started with Quarkus
- 4:42Building an AI service
- 6:37Live coding demonstration
- 11:50Core AI concepts
- 13:33Memory management
- 15:09Retrieval augmented generation
- 17:19Tools and MCP integration
- 20:02Advanced customer agent demo
- 24:32Safety and guardrails
- 28:11Fault tolerance and observability
- 29:49Agentic AI orchestration
- 34:06Conditional and complex agents
- 37:21Developer experience and Devstar
- 41:49Q&A and closing
related talks
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
50mDeveloping AI applications in Java with Quarkus and Langchain4j
45mAI-infused command-line applications
01h 01mScaling AI with Java: Building Production-Ready LLM Applications
43mCrafting Intelligent Applications with Quarkus/LangChain4j
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
47mQuarkus and AI Integrating Java and LLM to build intelligent applications
31mBuilding and Orchestrating Real Production-ready Agentic AI Systems