Java Meets AI: Integrating LLMs into Your Applications with LangChain4j
summary
LangChain4j, a Java library, provides concrete glue code to connect LLM providers (OpenAI, Google Vertex, HuggingFace, and local models) to a unified Java API. It shows how to load documents and create embeddings for vector stores (in-memory, SQL/Postgres vectors, etc.) to support RAG, and how agents can call external actions or Java tools to execute functions, query databases, or run dynamic JavaScript. Live demos include a Spring Boot booking assistant that enforces cancellation policy and a feedback analyzer that ingests docs, builds vectors, and returns typed Java objects end-to-end.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:24LangChain4j overview
- 8:35Reservation assistant demo
- 13:15Hello World with LangChain4j
- 15:25Conversation memory
- 19:21Java objects and AI services
- 25:33Using Tools
- 28:23RAG basics
- 35:34Advanced RAG optimizations
- 38:45Feedback analyzer demo
- 44:52RAG tips and conclusion
related talks
53mJava meets AI: Build LLM-Powered Apps with LangChain4j
55mAI in Java? Meet LangChain4j and Build Intelligent Services
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
45mBuilding Intelligent Enterprises: AI-Powered Java with LangChain4j & CDI
42mBuilding AI Powered Applications with Java
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
53mUnleash the Power of AI Agents with Java Building Intelligent Application
02h 37mDeveloping Cloud-Native Java AI applications with DJL and LangChain4J