Java’s GenAI Era: Getting Spring AI and Neo4j Applications to Production
summary
Quickly builds a Java 21 Maven Spring Boot app that adds an OpenAI embedding model bean, two REST endpoints (/query hits the LLM, /rag calls a Neo4j vector store advisor), and ingests FAA PDFs so RAG answers cite Piper Warrior II stall and emergency procedures instead of generic LLM text. Uses Spring AI + Neo4j vector store with OpenAI embeddings, then packages to Azure Container Apps; deployment works but notes cold starts, secret handling, and security/config tradeoffs.
AI-written summary · about
chapters (9)
- 0:00Introduction to GenAI in Java
- 2:16Choosing a real-world domain
- 4:02Setting up Spring project
- 6:49Configuring dependencies
- 9:16Building the application
- 13:54Live demo of LLM vs RAG
- 18:50Deploying to production
- 21:18Production deployment considerations
- 25:13Summary and resources
related talks
45mFrom RAG to Enterprise AI Agents: Building Intelligent Java Apps
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!
47mBlazingly Fast GenAI App Development Java and Spring AI
28mSpring AI: Streamlining Java Enterprise AI Development and Deployment
01h 00mSpring AI
44mJava Meets AI: Empowering Spring Developers to Build Intelligent Apps
01h 03mBuilding AI powered Applications with Java
52mIntelligent Beans with Spring AI