AI for Java Developers
summary
Java runs inference-grade AI in production and two thirds of AI compute is now inference with 55% of cloud spend on inference and 74% of builders saying most workload is inference. Spring AI gives a unified chat client and model abstraction so code swaps providers or local runners without change, exposes observability and token metrics, supports streaming responses, and enforces structured output by requesting JSON schemas that deserialize to Java types; one required config is the provider API key.
AI-written summary · about
chapters (14)
- 0:00AI for Java developers
- 1:32Java for AI workloads
- 5:27LLMs without a framework
- 6:32AI apps: framework challenges
- 8:38Spring AI out of the box
- 11:03Spring Boot with Spring AI
- 13:54Chat endpoint with Spring AI
- 17:49Prompt templates for inputs
- 18:33Token metrics for responses
- 19:17Observability with advisors
- 20:40Streaming responses
- 21:42Type-safe AI responses
- 23:30Guardrails with system messages
- 24:32Resources and closing
related talks
49mSpring AI: Seamlessly Integrating AI into Your Enterprise Java Applications
20mAI Solutions with Spring AI 2.0 and Java
28mSpring AI: Streamlining Java Enterprise AI Development and Deployment
52mAI for Busy Java Developers
55m"You can't use AI directly in Java!" Hold my prompt...
44mJava Meets AI: Empowering Spring Developers to Build Intelligent Apps
52mIntelligent Beans with Spring AI
24mBuilding Agentic Applications with Spring AI