From Prompt to Production: LLMs in Java

Overview (short):
Join us for a fast-paced, hands-on session exploring how to build Large Language Model (LLM) applications in Java using LangChain4j, Spring AI, and Quarkus. We’ll compare frameworks, wire in retrieval-augmented generation (RAG), and run models locally (Ollama) or via APIs—then ship a small, real app.

## Who should attend

Java developers, solution architects, and tech leads exploring AI features—chatbots, copilots, policy/FAQ assistants, or smart workflow automation.

## What you’ll learn

• LLM building blocks: prompts, tools/functions, embeddings, RAG, guardrails
• Three Java paths:
• LangChain4j + Spring Boot (tooling & RAG pipeline)
• Spring AI (starter patterns & AI abstractions)
• Quarkus (native-fast services, dev mode, LangChain4j extension)
• Hooking to local models (Ollama) or hosted providers
• RAG with pgvector (Postgres) for trustworthy answers
• Prod tips: evals, caching, rate limits, safety, and observability