From RAG to Enterprise AI Agents: Building Intelligent Java Apps
summary
Concrete how-to and working code: a Spring Boot app wires Spring AI to Azure OpenAI with a Postgres vector store using Postgres + PGVector and JDBC, exposing a RAG service and controller that returns context-aware answers (demo answers work and a live doc injection adds two documents). A dual-agent blog writer/evaluator runs iterative refinement (three iterations to approval), logs interactions via the simple logger advisor, and the demo deploys to Azure Container Apps — all components shown wiring, models, and deployment steps.
AI-written summary · about
chapters (14)
- 0:00Enterprise AI agents in Java
- 1:04AI app components
- 7:03Understanding RAG
- 8:06AI app platform for Java
- 9:50Spring Boot & LangChain4j stacks
- 11:57RAG roles for developers
- 12:17Intelligent Java app with Spring Boot
- 25:38Beyond RAG to AI agents
- 27:05AI agent patterns
- 28:10Dual-agent blog workflow
- 35:56Deploying to Azure Container Apps
- 37:43Java AI resources
- 41:59Modernizing with GitHub Copilot
- 44:10Q&A
related talks
50mModular RAG Architectures with Java and Spring AI
50mPractical Agentic RAG with SpringAI in Modern Enterprise Applications
26mJava’s GenAI Era: Getting Spring AI and Neo4j Applications to Production
28mSpring AI: Streamlining Java Enterprise AI Development and Deployment
01h 00mSpring AI
55mSpring into the AI Era: A Practical Exploration for Developers
49mBuilding AI Agents with Spring & MCP
28mPaving a Painless Path to Production AI in Your Java Applications