Scaling AI with Java: Building Production-Ready LLM Applications
summary
Builds a production-ready Java LLM app using Quarkus and LangChain4j, wires OpenAI or local container models (Podman/AI Lab) into a vector store (Postgres/Chroma), and adds a working RAG pipeline plus a tool that sends emails—demo shows ingestion, retrieval, model call and automatic email delivery all functioning. Covers running quantized models locally, CI/CD to container registry, Kubernetes sandbox deployment, and observability; notes live-edit dev UI, occasional network hiccups, and that fine-tuning is costly and brittle.
AI-written summary · about
chapters (9)
- 0:00Introduction and journey
- 11:18Quarkus framework overview
- 20:11Prompt engineering basics
- 24:05RAG implementation demo
- 35:13Running LLMs locally
- 44:31Fine-tuning fundamentals
- 49:05Production deployment path
- 53:43Scaling AI applications
- 1:00:06Q&A and closing
related talks
32mScaling Generative AI: Building Production-Ready LLM Applications
48mAgentic AI with Quarkus, LangChain4j and vLLM
02h 37mDeveloping Cloud-Native Java AI applications with DJL and LangChain4J
47mQuarkus and AI Integrating Java and LLM to build intelligent applications
50mDeveloping AI applications in Java with Quarkus and Langchain4j
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
51mNext-Level Features of LangChain4j for Production-Ready AI Applications
36mCrafting Intelligent Cloud Native applications with Quarkus