Developing AI applications in Java with Quarkus and Langchain4j
summary
Quarkus plus Langchain4j shows concrete recipes: a 12‑line JBang joke endpoint hitting GPT‑3.5, an easy RAG demo that ingests 4 files into 8 documents and serves answers via an in‑memory or Neo4j embedding store, a SQL‑based RAG that asks an LLM to generate SQL against a 99‑movie Postgres dataset, and a tool-enabled agent that sends emails (demo duplicates observed with GPT‑3.5). Build‑time native support, Dev UI, OpenTelemetry traces and Micrometer metrics are enabled and observable.
AI-written summary · about
chapters (13)
- 0:00Introduction and setup
- 6:54Why use LangChain4j with Quarkus
- 8:18Getting started with JBang demo
- 11:56AI Services explained
- 14:31RAG with embeddings overview
- 18:25Easy RAG demo
- 26:21Persistent embedding stores
- 28:30Advanced RAG approaches
- 33:15SQL-based RAG demo
- 39:04Tools and code execution
- 43:05Observability features
- 45:15Dev UI and embedding store search
- 49:16Summary and closing
related talks
44mUnlocking the Future of Java: LLM Integration Unveiled by Quarkus & LangChain4j
43mCrafting Intelligent Applications with Quarkus/LangChain4j
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
36mCrafting Intelligent Cloud Native applications with Quarkus
47mCreating AI-infused Apps, the Easy Way 🤙
01h 01mScaling AI with Java: Building Production-Ready LLM Applications
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
44mCrafting Intelligent Supersonic Subatomic applications with Quarkus