Want to build generative AI applications without complex setups or sending your data to the cloud? Discover how Podman AI Lab makes it simple for developers to run large language models (LLMs) and build powerful apps directly on a laptop—even without a dedicated GPU.
Join Red Hat Senior Developer Advocate Cedric Clyburn as he demystifies local AI development. He demonstrates how you can run powerful models, like Granite, as a simple REST API service that integrates into your existing workflow. Learn how to use pre-built recipes to create a document summarizer in minutes and get a practical introduction to Retrieval-Augmented Generation (RAG) for securely using your own enterprise data. Stop just hearing about AI and start building with it.
00:00 Getting started with local AI development
00:55 Run AI models as a service (REST API)
02:08 Demo setup with Podman AI Lab
02:43 Building a document summarizer app
03:34 Behind the scenes: LangChain & model quantization
04:25 Using your own data with Retrieval-Augmented Generation (RAG)
05:08 The benefits of local, open source AI
Get started with Podman AI Lab today:
⚙️ Read the guide: Getting started with AI using Podman AI Lab → https://developers.redhat.com/articles/2024/05/07/podman-ai-lab-getting-started
🚀 Learn more about Red Hat Podman → https://www.redhat.com/en/topics/containers/what-is-podman
#RedHat #PodmanAILab #AIDeveloperTools
