Unlocking the Future of Java: LLM Integration Unveiled by Quarkus & LangChain4j
summary
Five demos show Quarkus + LangChain4j actually wired up: a REST endpoint that forwards prompts to OpenAI GPT‑3.5, a conversational chain keeping a 20‑minute memory implemented as an in‑memory map, a test generator limited to 15 lines of code, an agent using a Quarkus mailer + Mailpit tool to send poems (it works), and an embedding-based chatbot that enforces terms‑of‑use rules for cancellations. Also demonstrates running a local ~70B model (39 GB) for offline inference; code and configs are on GitHub.
AI-written summary · about
chapters (10)
- 0:00Introduction and setup
- 1:54AI and LLM fundamentals
- 4:04Understanding LangChain4j
- 7:40First steps with LangChain4j
- 14:46Conversational AI and memory
- 21:58Advanced chain management
- 26:27Agents, tools, and orchestration
- 32:35RAG and business data integration
- 38:37Local LLM execution
- 40:27Resources and Q&A
related talks
50mDeveloping AI applications in Java with Quarkus and Langchain4j
42mCrafting Intelligent Applications in Java with Quarkus / LangChain4j
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
43mCrafting Intelligent Applications with Quarkus/LangChain4j
36mCrafting Intelligent Cloud Native applications with Quarkus
44mCrafting Intelligent Supersonic Subatomic applications with Quarkus
47mQuarkus and AI Integrating Java and LLM to build intelligent applications
01h 01mScaling AI with Java: Building Production-Ready LLM Applications