Introduction to NVIDIA NIM Microservices
NVIDIA Deep Learning Institute
Last updated June 16, 2026
Introduction to NVIDIA NIM Microservices is a free, two-hour course from NVIDIA's Deep Learning Institute on deploying AI models as ready-to-run microservices. You'll see what NIM microservices are, how to host them yourself with Docker, and how to connect them to build an AI chatbot that uses retrieval-augmented generation — plus a look at real applications built on them. A hands-on, practical introduction to getting generative-AI models running in your own environment.
What you'll learn
- What NVIDIA NIM microservices are and what they offer
- Deploying NIM microservices yourself with Docker
- Building an AI chatbot with retrieval-augmented generation
- Exploring applications built on NIM microservices
Frequently asked questions about Introduction to NVIDIA NIM Microservices
Who is Introduction to NVIDIA NIM Microservices for?
Developers and technically curious learners who want a hands-on first step in deploying AI models — basic AI familiarity helps.
Is Introduction to NVIDIA NIM Microservices free?
Yes — Introduction to NVIDIA NIM Microservices is completely free to take.
What are the prerequisites for Introduction to NVIDIA NIM Microservices?
Familiarity with artificial intelligence; the course uses Docker.
Why we suggest this course
For developers curious about moving AI from a notebook to a deployable service, this free course is a concrete, hands-on start — an accessible introduction to self-hosting and serving generative-AI models.