Pluralsight – Getting Started with Docker and AI 2025-7

Getting Started with Docker and AI. This course teaches participants how to run AI models, especially large language models (LLMs), locally using Docker Model Runner. Running these models is often complex without the right tools, but this course simplifies the process by providing a structured approach. Participants will first learn about the Docker Model Runner architecture and how to integrate it with OpenAI-compatible applications. They will then learn how to install, manage, and interact with models via Docker Hub and the command line. Finally, participants will learn how to integrate the tool into Compose applications and third-party tools to develop local AI applications, such as private chatbots like ChatGPT. By the end of the course, participants will have the knowledge and skills to confidently run and integrate AI models in a Docker environment.

What you will learn

• How Docker Model Runner works, its architecture, and its integration with OpenAI-compatible applications.
• Install Docker Model Runner, manage models, and interact with them via Docker Hub and the command line.
• Docker Model Runner integration into Compose applications and third-party tools.
• Building local AI-based applications such as private chatbots.

This course is suitable for people who:

• Software developers and engineers who want to run AI models locally using Docker.
• Artificial intelligence and machine learning professionals looking to simplify their model deployment processes.
• Anyone interested in building private chatbots or AI-based applications using native tools.