GenAI for .NET: Build LLM Apps with OpenAI and Ollama

Packt via Coursera

Go to class Write review

Details

Go to class

Provider

Coursera
Pricing

Paid Course
Languages

English
Certificate

Certificate Available
Effort

10 weeks, 1 hour a week
Sessions

Self-Paced
Level

Intermediate
Subtitles

English

Overview

Google, IBM & Meta Certificates – 40% Off

One plan covers every Professional Certificate on Coursera.

Unlock All Certificates

This course features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. Unlock the power of AI in your .NET applications with this hands-on course. You'll gain practical knowledge of Large Language Models (LLMs), Small Language Models (SLMs), and prompt engineering, empowering you to build intelligent applications for chat, text analysis, and search. Explore real-world projects that combine the latest OpenAI models and Ollama for local AI execution, giving you a complete understanding of both cloud-based and on-premise solutions. The course guides you step-by-step through setting up your .NET AI environment, integrating AI frameworks like Microsoft.Extensions.AI, working with vector databases, and implementing retrieval-augmented generation (RAG) applications. You'll develop AI chat apps, text completion tools, semantic and vector search apps, and even image analysis applications, with hands-on exercises for each concept. You'll also learn to deploy and extend AI solutions using GitHub-hosted models, Azure AI services, and local Ollama models. Projects culminate in a fully functional EShop vector search application, integrating semantic search, chat capabilities, and advanced AI services, giving you both technical depth and practical experience. This course is perfect for .NET developers, AI enthusiasts, and software engineers looking to expand their skills in AI application development. Prerequisites include basic familiarity with .NET and programming concepts. Difficulty is Intermediate, suitable for learners ready to implement AI-powered solutions confidently. By the end of the course, you will be able to build LLM-powered chat apps, implement vector-based search and embeddings, create RAG applications, integrate AI services in .NET, and deploy AI solutions using both cloud and local models.

Syllabus

Introduction

In this module, we will introduce the course and outline what you will learn about building LLM applications using .NET. We will review prerequisites, source code, and course slides to support your learning. Finally, we will explore the range of practical projects you’ll develop throughout the course.

GenAI Concepts: LLM, Token, SLM, Prompt Engineering

In this module, we will learn the fundamentals of generative AI, including LLMs and SLMs. We will explore tokens, tokenization, and how prompts guide model behavior. By the end, you will understand how to engineer prompts to produce accurate and efficient AI outputs.

.NET + AI Ecosystem: AI Development Tools and Libraries for .NET

In this module, we will explore the .NET ecosystem for AI development, including frameworks and SDKs. We will dive into Microsoft.Extensions.AI for unified AI building blocks. Additionally, you will learn how to use Semantic Kernel to add semantic intelligence to your .NET applications.

Setup LLM Providers: GitHub Models, Ollama, Azure AI Foundry

In this module, we will review AI providers including GitHub models, Ollama, and Azure AI Foundry. You will learn how to set up access credentials and download models locally. By the end, you will be ready to run LLMs both in the cloud and on your local environment.

Chat, Text Completions, Analysis and Function Calling w/ .NET

In this module, we will build practical AI applications in .NET, including chat apps and text completion tools. We will explore real-time streaming, classification, summarization, and structured data extraction. Additionally, you will learn how to invoke functions from LLMs to expand application functionality.

.NET AI Vector Search Using Vector Embeddings and Vector Store

In this module, we will dive into vector embeddings and vector databases for AI-driven search. You will generate embeddings, store them in-memory, and perform vector searches. By the end, you will develop a .NET vector search app capable of retrieving highly relevant results.

Retrieval Augmented Generation (RAG) Application w/ .NET AI

In this module, we will explore Retrieval-Augmented Generation (RAG) and its application in .NET chat apps. You will learn how to integrate external knowledge and extend chat functionality with custom documents and function calling. Additionally, you will incorporate vector databases to enhance data retrieval.

Image Analysis Apps w/ .NET AI

In this module, we will develop AI-powered image analysis applications in .NET. You will work with both cloud-hosted and local models to perform recognition tasks. By the end, you will be able to generate structured outputs from images for various use cases.

Build Eshop Vector Search App w/ .NET Aspire, gpt-5-mini and Qdrant Vector DB

In this module, we will build a full-featured EShop vector search application using .NET Aspire. You will integrate chat, semantic search, and vector databases into a distributed microservices architecture. Finally, you will develop both front-end and back-end components for a production-ready AI application.

Thanks

In this module, we will wrap up the course with a summary of what you have learned. You will review key concepts and project outcomes. Finally, we will outline next steps to continue building advanced AI applications with .NET.