Generative AI and Java
summary
Shows a concrete RAG pipeline: chunk PDFs into embeddings, store vectors, run semantic search and send retrieved passages into an LLM to generate answers; demos include a chat that retains context, image generation via OpenAI, and Java REST calls. Recommends LangChain for Java for 5–10 line integrations, reports a working 13B model deployment and uses 768-dimensional embeddings. Covers code generation, COBOL→Java conversion, and a 200‑page docs summarizer that saves hours a day.
AI-written summary · about
chapters (14)
- 0:00Introduction and speaker background
- 1:47Foundational models and LLMs overview
- 8:04Prompt engineering techniques
- 14:05Prompt lab demo and model parameters
- 20:11Enterprise use cases for generative AI
- 22:19Retrieval augmented generation explained
- 25:24Java’s role in generative AI
- 27:08Code explanation and generation with AI
- 31:31AI as a developer tool
- 33:31Calling LLMs via REST in Java
- 36:03LangChain for Java framework
- 39:11Building a chat application with LangChain4j
- 40:15Generating images with Java and AI
- 41:03Q&A and closing remarks
related talks
48mBuilding AI Powered Applications with Java
01h 03mBuilding AI powered Applications with Java
55mAI in Java? Meet LangChain4j and Build Intelligent Services
53mUnleash the Power of AI Agents with Java Building Intelligent Application
02h 44mUsing Generative AI with Java: Beyond Simple Chatbots
47mJava Meets AI: Integrating LLMs into Your Applications with LangChain4j
44mJava Meets AI: Empowering Spring Developers to Build Intelligent Apps
41mFrom Chat to RAG to MCP: Enhancing Java Applications with AI