Building AI Powered Applications with Java
summary
Java code wires external LLMs to private data using Spring AI and LangChain4j, vectorizing docs and storing embeddings in a DB (demo writes embeddings into an Oracle vector store via testcontainers). Retrieval-Augmented Generation works but is nondeterministic; parsing matters β no Asciidoc parser so results can be wrong. A batch run of 397 documents becomes 2,583 text segments and takes about a minute and a half to encode, illustrating real-world cost and latency.
AI-written summary Β· about
chapters (15)
- 0:00AI powered Java apps intro
- 3:20Why AI matters now
- 7:16Start AI in Java
- 10:27How LLMs work
- 12:13RAG with private data
- 13:16Vector DBs for AI
- 16:10Testcontainers for local AI
- 17:38Live RAG demo: LangChain4j & OpenAI
- 21:34Testing AI apps
- 24:24Optimize RAG doc processing
- 27:33Store embeddings in vector DB
- 31:07Model Context Protocol
- 34:41AI tools future impact
- 35:45Why Java developers should embrace AI tools
- 38:32Q&A
related talks
01h 03mBuilding AI powered Applications with Java
48mBuilding AI Powered Applications with Java
55mAI in Java? Meet LangChain4j and Build Intelligent Services
47mJava Meets AI: Integrating LLMs into Your Applications with LangChain4j
53mUnleash the Power of AI Agents with Java Building Intelligent Application
52mAI for Java Developers - From Buzzword to Code
53mJava meets AI: Build LLM-Powered Apps with LangChain4j
02h 44mUsing Generative AI with Java: Beyond Simple Chatbots
