APIs and GenAI : Your Perfect Combo with LLM-Powered Frameworks.
summary
Shows how LongChain4J plus a Spring Boot starter builds LLM-driven chat endpoints with a few config lines, demonstrates a basic GPT assistant, a RAG pipeline that indexes an 80‑page SNCF terms PDF into a Qdrant vector store using Bing embeddings, and a tools demo where tool annotations invoke Java methods for inventory CRUD. Demos mostly work but one update call flakes; cautions cover security, token costs, GPU needs, and “don’t use RAG to kill a fly.”
AI-written summary · about
chapters (13)
- 0:00Introduction
- 1:55Reimagining APIs with chatbots
- 4:24LangChain for Java
- 5:49Demo: GPT assistant
- 8:42RAG and its benefits
- 11:18Demo: PDF with RAG
- 15:20Tool integration in LangChain
- 16:25Demo: Inventory with tools
- 21:44Real-world use cases
- 23:09Warnings and considerations
- 24:40When to use LangChain
- 25:45Conclusion
- 27:13Q&A
related talks
48mBuilding AI Powered Applications with Java
01h 03mBuilding AI powered Applications with Java
51mAI-Powered Development: Hands-On Techniques for Immediate Impact
48mGoing Beyond Prompt Engineering
21mChatGPT, LLMs, and LangChains - A Beginner's Guide
24mHow Generative AI Apps Use APIs
01h 59mLLM applications with LangChain
53mJava meets AI: Build LLM-Powered Apps with LangChain4j