Quarkus and AI Integrating Java and LLM to build intelligent applications
summary
Shows how to train and serve models in pure Java: uses Deep Java Library to train a ResNet on rock‑paper‑scissors (training run ~30 minutes) and to load ONNX models, warns to bake ONNX runtimes into containers and set DL_CACHE_DIR. Builds a Quarkus REST endpoint that serves an ONNX fraud model, returning probabilities (example: 49% -> false, 96% -> true). Demonstrates LLM integration with LineChain for J for prompting, memory, agents (execute a Java method to send email) and Redis document storage.
AI-written summary · about
chapters (11)
- 0:00AI in enterprise Java
- 6:11Java vs Python for AI
- 9:04Deep Java Library training
- 19:00ONNX inferencing in Java
- 26:29LangChain4j for AI models
- 31:06Quarkus chatbot with LangChain4j
- 36:28Memory in AI interactions
- 40:01AI agents for automation
- 41:28AI-generated emails
- 44:39Domain chatbot with RAG
- 46:45Key takeaways
related talks
01h 01mScaling AI with Java: Building Production-Ready LLM Applications
48mAgentic AI with Quarkus, LangChain4j and vLLM
36mCrafting Intelligent Cloud Native applications with Quarkus
44mUnlocking the Future of Java: LLM Integration Unveiled by Quarkus & LangChain4j
44mCrafting Intelligent Supersonic Subatomic applications with Quarkus
02h 37mDeveloping Cloud-Native Java AI applications with DJL and LangChain4J
50mDeveloping AI applications in Java with Quarkus and Langchain4j
57mPure Java Enterprise AI/LLM Integration (EAI 2.0)