Intelligent Beans with Spring AI
summary
Experimental Spring AI provides a Java-first SDK that actually wires GPT models (OpenAI/Azure) into Spring apps: an AI client with a generate method, template-based prompts and output parser that map JSON into POJOs, and a demoable retrieval pipeline that creates embeddings, stores them in a vector database (in-memory or Chroma), then uses retrieval augmented generation to answer queries. Token limits (demo used ~9k of a 16k window), function support is pending, and the workshop demos run end-to-end.
AI-written summary · about
chapters (11)
- 0:00Introduction and motivation
- 4:16Hello World with Spring AI
- 12:03Domain model and key concepts
- 21:38Demo: Joke generation
- 25:16Output parsing and structured data
- 29:10Model limitations and tokens
- 33:51Prompt stuffing and context
- 37:05Retrieval augmented generation
- 41:24Demo: Bike store Q&A
- 48:52Project status and future
- 49:14Q&A session
related talks
44mJava Meets AI: Empowering Spring Developers to Build Intelligent Apps
55mSpring into the AI Era: A Practical Exploration for Developers
48mSpring AI: Integrating Generative AI in Java Enterprise
49mSpring AI: Seamlessly Integrating AI into Your Enterprise Java Applications
01h 00mSpring AI
28mSpring AI: Streamlining Java Enterprise AI Development and Deployment
51mIntelligent Applications with Spring AI
45mThe Overwhelmed Spring Developer's Guide To AI