Concerto for Java & AI – Building Production-Ready LLM Applications
summary
Builds a Java "composer assistant" using Spring AI and LangChain4J, with embeddings stored in a vector store (PostgreSQL) to enable semantic search and retrieval augmented generation. Demonstrates text classification with enum-constrained outputs to mitigate prompt injection, speech transcription → structured data extraction, observability traces showing token usage and model calls, and human-in-the-loop validation. Live demo generates a composition plan and a performed soundtrack from preloaded instruments; end-to-end prototype works, but testing and cautious deployment are required for production in regulated environments.
AI-written summary · about
chapters (15)
- 0:00Intro
- 1:28GenAI
- 2:22The WHY factor
- 7:25Demo
- 10:21Text classification
- 10:43Demo
- 15:58Semantic search
- 17:10Demo
- 18:58Question answering with docs
- 19:50Demo
- 24:08Structured data extraction
- 24:33Speech transcription
- 24:52Demo
- 33:20Final product
- 34:00Outro
related talks
02h 37mDeveloping Cloud-Native Java AI applications with DJL and LangChain4J
01h 01mScaling AI with Java: Building Production-Ready LLM Applications
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
01h 02mJava + LLMs (Build LLM Apps in Java with JakartaEE)
46mGenerative AI and Java
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!
16mInterview of Josh Long
01h 59mLLM applications with LangChain