Topic 16. Integrating artificial intelligence models into .NET applications (Microsoft.Extensions.AI)

Goal: get to know the principles of large language models and the Microsoft.Extensions.AI libraries; learn to send requests to a local model through IChatClient, receive streaming and structured responses, and describe C# functions as model tools; master the middleware client pipeline, embeddings, retrieval-augmented generation, and safe handling of API keys and user data.

Lecture contents

1. Language models and IChatClient — Large language models · The AI ecosystem in .NET · The IChatClient interface
2. Streaming and structured responses — Streaming responses · Structured output
3. Function calling and the client pipeline — Function calling · The middleware client pipeline
4. Embeddings, RAG, and security — Embeddings · Retrieval-augmented generation (RAG) · Security, cost, and testing
5. Common mistakes — Common mistakes

Practice and review

• Practice — 3 worked examples with complete code
• Tasks — 30 variants, each with tasks at three difficulty levels
• Summary — conclusions, self-check questions, and useful links