Building a Custom AI Chatbot with Spring Boot, React, and LangChain4j
summary
Builds a full stack RAG chatbot using Spring Boot backend, React + Hilla frontend, LangChain4j and OpenAI GPT-4, with a 500‑token windowed chat memory and a tokenizer matched to the model. Ingests terms_of_service.txt into an in-memory vector store via an All-MiniLM embedding model, uses a retriever (1 result, min score 0.6) to ground answers, streams replies as streaming token responses, and exposes two safe tools (getBookingDetails, cancelBooking) that successfully cancel booking 105 in the demo.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:05RAG Spring Boot app
- 4:38Streaming chat model
- 8:35Customer support agent
- 14:11Retrieval augmented generation
- 15:55Embedding models and vector stores
- 18:22Ingesting documents
- 22:37Booking tools
- 27:10Live demo
- 27:52Q&A
related talks
46mBuilding a custom AI chatbot with Spring Boot, React, and LangChain4j
44mBuilding AI Chatbot with Spring Boot, React and ChatGPT (Live Code)
01h 12mBuild Your Own AI Chatbot with OpenAI & LangChain
48mBuilding AI Powered Applications with Java
25mLets Build A Node.js ChatGPT-Like Bot With AI APIs
01h 02mBuilding full stack AI chatbots with Java - livecoding
55mAI in Java? Meet LangChain4j and Build Intelligent Services
46mCodepocalypse Now Lang Chain4j vs Spring Al