AI-infused command-line applications
summary
Builds a Java CLI that sends prompts to OpenAI via LangChain4j, uses Quarkus Dev mode for hot reload and build-time code generation, and packages to a GraalVM native binary with one Maven flag. Uses PicoCLI for command parsing, supports templated saved prompts, streaming token output, and tool invocation (local MCP server for file ops and image generation). Native compile of the demo finishes in about 1–2 minutes, reports ~70,000 reachable methods, and the demo commands work end-to-end.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:28Building AI CLI tools
- 3:01How LLMs work
- 6:16LangChain4j for Java
- 10:10Quarkus overview
- 11:16Quarkus + LangChain4j benefits
- 14:44CLI apps with PicoCLI
- 17:16Live demo: Quarkus AI
- 22:44REST to CLI conversion
- 27:24GraalVM native binary
- 30:19Advanced MCP use case
- 32:26Summary
related talks
45mAI-infused command-line applications
50mDeveloping AI applications in Java with Quarkus and Langchain4j
51mAI-Powered Development: Hands-On Techniques for Immediate Impact
44mUnlocking the Future of Java: LLM Integration Unveiled by Quarkus & LangChain4j
01h 01mCreate #AI Infused #Java Apps with #LangChain4j
47mCreating AI-infused Apps, the Easy Way 🤙
51mSupercharge Agentic AI Apps: A DevEx Driven Approach to Cloud-Native Scaffolding
01h 06mSupercharge #AgenticAI Projects A DevEx Driven Approach to #CloudNative Scaffolding