Java meets AI: Build LLM-Powered Apps with LangChain4j
summary
LangChain4j brings LLM features to Java: ready-made integrations with OpenAI, Google Gemini, HuggingFace, Dall‑E, Quarkus and Spring Boot, plus an in-memory embedding model and stores for fast semantic search. Examples include a car‑rental assistant that calls backend booking tools, a POJO recipe generator, streaming token output, and ingesting the library docs into a vector store for RAG search. Core abstractions are AI Services (interface-to-model implementations), prompt templates, memory and LangChain4j tool/function calling.
AI-written summary · about
chapters (9)
- 0:00LangChain4j and LLM apps
- 10:45Core components of LangChain4j
- 21:37AI Services in LangChain4j
- 28:19Adding tools and memory
- 32:40RAG with LangChain4j
- 42:21Advanced RAG techniques
- 46:13Demo: Quarkus app with RAG
- 51:48Security for LLM apps
- 52:32Resources and closing
related talks
47mJava Meets AI: Integrating LLMs into Your Applications with LangChain4j
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
45mBuilding Intelligent Enterprises: AI-Powered Java with LangChain4j & CDI
55mAI in Java? Meet LangChain4j and Build Intelligent Services
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
51mJava Meets AI: Empowering Developers to Build Intelligent Apps
02h 37mDeveloping Cloud-Native Java AI applications with DJL and LangChain4J
02h 44mUsing Generative AI with Java: Beyond Simple Chatbots