GenAI for .NET

In this hands-on course, you'll learn to integrate OpenAI, Ollama and .NET's new Microsoft-Extensions-AI (MEAI) abstraction libraries to build a wide range of GenAI applications—from chatbots and semantic search to Retrieval-Augmented Generation (RAG) and image analysis.

Throughout the course, you’ll learn:

.NET + AI Ecosystem

You'll learn about Microsoft's new abstraction libraries like Microsoft-Extensions-AI, which makes it super easy to integrate & switch different LLM providers like OpenAI, Azure AI, Ollama and even self-hosted models.

Setting Up LLM Providers

Configure the LLM providers—such as GitHub Models, Ollama, and Azure AI Foundry—so you can choose the best fit for your use case.

Text Completion LLM w/ GitHub Models OpenAI gpt-5-mini and Ollama llama3.2 Model model

You’ll learn how to use .NET to integrate LLM models and performs Classification, Summarization, Data extraction, Anomaly detection, Translation and Sentiment Analysis use cases.

Build AI Chat App with .NET and gpt-5-mini model

You'll develop back-and-forth conversation based messaging with LLM and user where the AI maintains context across multiple user turns. We will use Chat Streaming features when developing AI Chat Application.

Function Calling with .NET and gpt-5-mini model

Develop a function that will trigger from OpenAI GPT-5-mini. The model returns structured JSON specifying which .NET function to invoke, along with arguments for retrieving real-time data.

.NET AI Vector Search using Vector Embeddings and Vector Store

We’ll also cover Vector Search, a powerful feature that allows semantic search based on meaning—not keywords.

You’ll learn how to:

Generate embeddings using OpenAI’s text-embedding-3-small or Ollama’s all-MiniLM embeddings model,
Store these in a vector database like Qdrant
Query the vector store with user embedding to find top matches by similarity
Retrieve relevant data based on similarity searches—all in our .NET applications.

RAG – Retrieval-Augmented Generation with .NET

You’ll learn how to combine vector search results with LLM responses to:

Retrieve relevant data from your own sources
Break documents into chunks → embed them → store in vector DB
At query time, embed the question → retrieve relevant chunks → pass them along with the user’s query to the LLM
Get accurate, context-specific answers using your internal data from LLM

We’ll implement the full RAG flow with real examples using .NET and Qdrant.

Image Analysis with .NET AI

Cover image recognition and analysis, showing how to send images to AI models, receive tags, captions or visual summaries and integrate those capabilities directly into your .NET apps

Vision models for object recognition, classification, or captioning
Combining text and image processing to build more powerful, multi-modal applications for traffic cam analysis operations

Final Project: E-Shop Semantic Search with .NET Aspire

You’ll build a complete full-stack AI-powered EShop Vector Search app step by step.

We’ll use:

.NET Aspire for service orchestration
Qdrant as our Vector Database
and GPT-5 Mini or Ollama’s local models to generate embeddings and respond intelligently to user queries

In this project, you’ll:

Generate product embeddings with OpenAI text-embeddings or Ollama all-minilm
Store them in Qdrant Vector DB for fast similarity search
Implement a RAG flow that provides semantic search over our EShop product catalog
Enable users to search products by meaning—not just keywords

This project brings everything you learn in this course into a single, full-stack, real-world app.

By the end of this course, you'll have the tools and confidence to build intelligent, GenAI-powered apps in .NET.

What's inside

Learning objectives

Genai concepts: llm, token, slm, prompt engineering
.net + ai ecosystem: ai development tools and libraries for .net
Setup llm providers: github models, ollama, azure ai foundry
Chat, text completions, analysis and function calling w/ .net
Text completion llm with github models openai gpt-5-mini model
Classification, summarization, sentiment analysis llm other use cases
Structured output in llm for data extraction use case
Build ai chat app with .net and gpt-5-mini model
Invoke .net functions using gh gpt-5-mini model with function calling
.net ai vector search using vector embeddings and vector store
Generate embeddings and calculate similarity w/ cosinesimilarity

Develop .net ai vector search app w/ ollama and all-minilm embedding model
Retrieval augmented generation (rag) application w/ .net ai
Build .net chat app w/ rag template w/ openai gpt-5-mini model
Build .net chat app w/ rag template using ollama and all-minilm
Build image analysis app w/ .net and gh models - openai gpt-5-mini
Build image analysis app w/ .net and ollama llava
Build eshop vector search app w/ .net aspire, gpt-5-mini and qdrant vector db
Add qdrant vector database into .net aspire
Unified ai building blocks: microsoft extensions ai (meai)
Show more
Show less

Genai concepts: llm, token, slm, prompt engineering
.net + ai ecosystem: ai development tools and libraries for .net
Setup llm providers: github models, ollama, azure ai foundry
Chat, text completions, analysis and function calling w/ .net
Text completion llm with github models openai gpt-5-mini model
Classification, summarization, sentiment analysis llm other use cases
Structured output in llm for data extraction use case
Build ai chat app with .net and gpt-5-mini model
Invoke .net functions using gh gpt-5-mini model with function calling
.net ai vector search using vector embeddings and vector store
Generate embeddings and calculate similarity w/ cosinesimilarity
Develop .net ai vector search app w/ ollama and all-minilm embedding model
Retrieval augmented generation (rag) application w/ .net ai
Build .net chat app w/ rag template w/ openai gpt-5-mini model
Build .net chat app w/ rag template using ollama and all-minilm
Build image analysis app w/ .net and gh models - openai gpt-5-mini
Build image analysis app w/ .net and ollama llava
Build eshop vector search app w/ .net aspire, gpt-5-mini and qdrant vector db
Add qdrant vector database into .net aspire
Unified ai building blocks: microsoft extensions ai (meai)
Show more
Show less

Syllabus

Introduction

What are Small Language Models (SLMs) ?

Prerequisites, Source Code and Course Slides

Course Projects: Chat, Text Analysis, Vector Search, RAG, EShop Vector Search

Career center

Learners who complete GenAI for .NET: Build LLM Apps with OpenAI and Ollama will develop knowledge and skills that may be useful to these careers:

Generative AI Developer

A Generative AI Developer is at the forefront of building intelligent applications that leverage large language models and other generative artificial intelligence technologies. This course offers a direct path to excel as a Generative AI Developer by providing hands-on experience in integrating OpenAI, Ollama, and .NET's Microsoft-Extensions-AI libraries. Learners will gain confidence in developing a wide range of GenAI applications, including advanced chatbots, semantic search systems, Retrieval-Augmented Generation (RAG) solutions, and even image analysis capabilities. The practical focus on building full-stack AI-powered applications, such as an E-Shop Vector Search app using .NET Aspire and Qdrant, directly equips individuals with the skills to design, implement, and deploy sophisticated GenAI solutions using the .NET ecosystem. This course is particularly beneficial for those aiming to craft cutting-edge AI-driven user experiences.

See salaries and explore the career path for Generative AI Developer

Artificial Intelligence Engineer

An Artificial Intelligence Engineer is responsible for designing, building, and deploying AI systems and models into production environments. This course prepares individuals to become a proficient Artificial Intelligence Engineer by imparting critical skills in developing GenAI applications using the robust .NET framework. You'll learn the practicalities of integrating various LLM providers, implementing vector search with embeddings and vector databases like Qdrant, and constructing Retrieval-Augmented Generation (RAG) applications to deliver context-specific answers. The comprehensive content, covering everything from text completion and function calling to image analysis and full-stack AI application development with .NET Aspire, ensures that learners are well-equipped to tackle complex AI engineering challenges and contribute effectively to innovative AI projects.

See salaries and explore the career path for Artificial Intelligence Engineer

Software Developer Artificial Intelligence

A Software Developer Artificial Intelligence specializes in creating software that incorporates AI capabilities, from intelligent features to full-fledged AI-powered applications. This course is exceptionally relevant for aspiring Software Developers Artificial Intelligence, as it provides a deep dive into building GenAI applications using .NET. You will learn to integrate powerful LLM providers like OpenAI and Ollama, implement core AI functionalities such as classification, summarization, sentiment analysis, and data extraction, and develop interactive AI Chat Apps. The emphasis on hands-on project work, including an E-Shop Semantic Search application, demonstrates how to craft robust, high-performance AI solutions within the .NET ecosystem, enabling you to build intelligent systems with confidence and technical expertise.

See salaries and explore the career path for Software Developer Artificial Intelligence

Machine Learning Engineer

A Machine Learning Engineer builds, deploys, and maintains machine learning models and systems. While focusing on Generative AI, this course significantly enhances the capabilities of an aspiring Machine Learning Engineer by providing direct experience with the practical implementation of large language models and related technologies. Learners will gain proficiency in using Microsoft-Extensions-AI for integrating different LLM providers, developing vector search applications with embeddings and vector databases, and constructing Retrieval-Augmented Generation (RAG) systems. The course's exploration of image analysis and full-stack AI application development with .NET, alongside critical concepts like prompt engineering, provides a strong foundation for building and operationalizing various machine learning solutions, particularly those involving advanced natural language processing and computer vision.

See salaries and explore the career path for Machine Learning Engineer

Backend Software Engineer

A Backend Software Engineer is responsible for building and maintaining the server-side logic and databases that power applications. This course is highly beneficial for a Backend Software Engineer looking to specialize in artificial intelligence. It focuses extensively on .NET backend development for GenAI applications, including the integration of OpenAI, Ollama, and Microsoft-Extensions-AI. Learners develop skills in setting up LLM providers, implementing text completion, function calling, vector search, and Retrieval-Augmented Generation (RAG) within .NET applications. The course's hands-on projects, such as building an E-Shop Semantic Search application, involve significant backend development, including storing data in Qdrant Vector DB, developing services, and exposing endpoints, directly equipping you to build robust, AI-powered backend systems.

See salaries and explore the career path for Backend Software Engineer

Full Stack Software Engineer

A Full Stack Software Engineer is proficient in both front-end and back-end development, handling all layers of an application. This course offers valuable skills for a Full Stack Software Engineer aiming to integrate advanced AI capabilities into their projects. While the primary focus is on the GenAI backend in .NET, the final project, building a complete full-stack AI-powered E-Shop Vector Search app with .NET Aspire, provides practical experience in orchestrating services and connecting front-end experiences to intelligent backend systems. Learners will understand how to generate product embeddings, store them in Qdrant, implement RAG for semantic search, and develop both the service layer and UI pages, enabling them to construct holistic, intelligent applications from end to end.

See salaries and explore the career path for Full Stack Software Engineer

Solutions Architect Artificial Intelligence

A Solutions Architect Artificial Intelligence designs and oversees the implementation of complex AI systems, ensuring they align with business requirements and technical best practices. This course provides a strong practical understanding for a Solutions Architect Artificial Intelligence, as it covers the foundational building blocks of modern GenAI applications. You will learn to configure and integrate diverse LLM providers like OpenAI, Ollama, and Azure AI, understand the role of vector databases like Qdrant, and implement architectural patterns such as Retrieval-Augmented Generation (RAG). This detailed exposure to the .NET + AI ecosystem, including Microsoft-Extensions-AI and .NET Aspire for service orchestration, allows you to make informed decisions about technology choices and design scalable, intelligent solutions, which often requires an advanced degree or significant professional experience.

See salaries and explore the career path for Solutions Architect Artificial Intelligence

Research Engineer Artificial Intelligence

A Research Engineer Artificial Intelligence bridges the gap between theoretical AI research and practical implementation, often prototyping new models or integrating cutting-edge techniques into systems. This course may be useful for a Research Engineer Artificial Intelligence as it provides a hands-on understanding of how to apply and integrate contemporary generative AI models. While not focused on developing novel algorithms, the course teaches how to work with various LLM providers, implement advanced techniques like vector embeddings, semantic search, and Retrieval-Augmented Generation (RAG) in a .NET environment. This practical experience with the .NET AI ecosystem, custom models like Ollama, and tools like Qdrant, is valuable for prototyping and evaluating new AI capabilities, a role that typically requires an advanced degree.

See salaries and explore the career path for Research Engineer Artificial Intelligence

Technical Consultant Artificial Intelligence

A Technical Consultant Artificial Intelligence advises clients on the strategic implementation and technical execution of AI solutions. This course significantly benefits a Technical Consultant Artificial Intelligence by providing a comprehensive, hands-on understanding of how GenAI applications are built and integrated. You will learn about the practicalities of using various LLM providers, constructing advanced chatbots, implementing RAG for context-aware responses, and leveraging vector databases. This detailed insight into the .NET + AI ecosystem, including Microsoft-Extensions-AI and .NET Aspire, enables consultants to confidently guide clients through technology choices, architecture design, and solution development, ensuring they can translate complex technical capabilities into practical business value for diverse use cases.

See salaries and explore the career path for Technical Consultant Artificial Intelligence

Machine Learning Operations Engineer

A Machine Learning Operations Engineer focuses on deploying, monitoring, and maintaining machine learning models and pipelines in production environments. This course may be useful for a Machine Learning Operations Engineer by providing practical insights into the development lifecycle of GenAI applications. While not a dedicated MLOps course, it covers setting up various LLM providers (including local Ollama and cloud-based options), integrating them into .NET applications, and using .NET Aspire for service orchestration, which are foundational for managing distributed AI systems. Understanding how GenAI applications are architected and built, including vector databases and RAG flows, helps in designing robust deployment strategies and monitoring pipelines for these intelligent applications.

See salaries and explore the career path for Machine Learning Operations Engineer

Data Engineer: Machine Learning

A Data Engineer Machine Learning builds and optimizes data pipelines and infrastructure specifically for machine learning workloads. This course may be useful for a Data Engineer Machine Learning by introducing key concepts around data preparation for Generative AI. While not a traditional data engineering course, it covers generating embeddings using models like OpenAI’s text-embedding-3-small or Ollama’s all-MiniLM, and storing these in vector databases such as Qdrant. Understanding these processes for semantic search and Retrieval-Augmented Generation (RAG) is crucial, as it informs how data needs to be structured, processed, and managed to power intelligent applications, offering a specialized perspective on data infrastructure for AI.

See salaries and explore the career path for Data Engineer: Machine Learning

Technical Project Manager Artificial Intelligence

A Technical Project Manager Artificial Intelligence is responsible for planning, executing, and closing AI-driven projects, ensuring they meet technical objectives and business goals. This course may be useful for a Technical Project Manager Artificial Intelligence as it provides a solid foundation in the core technologies and development practices for building GenAI applications. Understanding concepts like LLMs, RAG, vector search, and the .NET + AI ecosystem, including Microsoft-Extensions-AI and .NET Aspire, allows for more accurate project scoping, risk assessment, and resource allocation. This practical knowledge empowers managers to communicate effectively with development teams, track progress, and make informed decisions throughout the lifecycle of complex AI projects.

See salaries and explore the career path for Technical Project Manager Artificial Intelligence

Prompt Engineer

A Prompt Engineer specializes in designing, testing, and refining prompts for large language models to achieve desired outputs for specific tasks and applications. This course may be useful for a Prompt Engineer, as it explicitly covers "Prompt Engineering" as a core GenAI concept. Learners gain hands-on experience using .NET to integrate LLM models for various use cases such as classification, summarization, data extraction, and sentiment analysis. By building AI Chat Apps and implementing function calling, individuals will deepen their understanding of how prompts interact with models and external tools to achieve structured outputs and fulfill complex user requests, providing a robust technical context for this emerging role.

See salaries and explore the career path for Prompt Engineer

Data Scientist Applied Artificial Intelligence

A Data Scientist Applied Artificial Intelligence focuses on developing and deploying AI-driven solutions to solve real-world problems, often bridging statistical analysis with software development. This course may be helpful for a Data Scientist Applied Artificial Intelligence by providing practical skills in implementing GenAI solutions. While typically requiring an advanced degree, this course's emphasis on classification, summarization, data extraction, anomaly detection, and sentiment analysis using LLMs with .NET directly aligns with tasks a data scientist might undertake. The ability to build applications that leverage vector search and Retrieval-Augmented Generation (RAG) against custom data sources empowers data scientists to move beyond descriptive analysis to create intelligent, interactive AI systems.

See salaries and explore the career path for Data Scientist Applied Artificial Intelligence

AI Product Manager

An AI Product Manager defines the strategy, roadmap, and features for products that incorporate artificial intelligence. This course may be useful for an AI Product Manager as it offers a deep, practical understanding of GenAI application development. Knowing how to integrate LLM providers, implement vector search, RAG, and image analysis using .NET, Microsoft-Extensions-AI, and .NET Aspire provides critical insight into the technical possibilities and limitations of AI. This hands-on knowledge enables product managers to define realistic and innovative product requirements, evaluate technical feasibility, and communicate effectively with engineering teams, leading to more successful AI-powered product launches and strategic decisions.

See salaries and explore the career path for AI Product Manager