Generative AI in Practice: Concrete LLM Use Cases in Java with the PaLM API
summary
Shows how Java calls Google Cloud’s PaLM API (the model trained on ~3.6 trillion tokens, with examples mentioning ~340B parameters) to do real tasks: a Micronaut + Docker app on Cloud Run generates kid stories in ~15–20s from a structured prompt, and a Groovy-doc chatbot uses retrieval-augmented generation with embeddings stored in a vector store. Code uses PaLM API endpoints, Java auth, and the Longchain4j orchestration layer; demos run and return grounded answers, with grounding and search used to reduce hallucinations.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 1:17Generative AI concepts
- 4:48How LLMs function
- 9:54Google AI offerings
- 13:51Demos and hallucinations
- 26:02Java application integration
- 36:15Orchestrating with LangChain4j
- 45:19Conclusion and Q&A
related talks
46mGenerative AI in Practice: Concrete Use Cases for an LLM in Java
02h 49mJava meets AI: Build LLM-Powered Apps with LangChain4j
53mJava meets AI: Build LLM-Powered Apps with LangChain4j
02h 44mUsing Generative AI with Java: Beyond Simple Chatbots
51mInternal AI solutions -from hype to production
38mThe Era of AAP: Ai Augmented Programming using only Java
15mLatest Generative AI products and solutions on
46mThe Era of AAP: Ai Augmented Programming using Modern Java