Retrieval-Augmented Generation (RAG) is a powerful way to build AI applications that combine large language models with your own data. Most RAG tutorials today are written for Python — this course is different.
In this course, you’ll learn how to build a RAG-based AI application in C# using .NET 10, focusing on understanding the full pipeline rather than memorizing theory or machine-learning internals. We start with a local-first approach, setting up a local AI runtime using Ollama and running models on your own machine. From there, you’ll build a Chat API in C#, explore prompt handling as application logic, and understand why resilience, retries, and timeouts matter when working with AI systems.
You’ll then dive into RAG fundamentals, including ingestion pipelines, chunking strategies, embedding models, and vector storage. You’ll implement an offline ingestion worker, store embeddings in a vector database, and retrieve relevant context before generating responses. Along the way, you’ll learn how tool calling and structured outputs fit into a real application flow.
