GenAI and LLMs are currently a big hype topic within the IT industry and beyond. And while we should always be critical about “The next big thing” style hype waves, we also need to stay curious and make up our own mind. And how to better understand a technology as a developer, than by using it in practice?

In this talk, we want to look at how to use langchain4j, the Open-Source Java variant of the popular LLM framework langchain, together with Ollama as a local LLM model runtime, to create a local development experience for building GenAI applications. And to top things off, we will utilize Testcontainers’ infrastructure-as-code capabilities to set up this LLM development environment on demand and without requiring manual fiddling around.