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

<div>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.</div><div><br></div><div>Throughout the course, you’ll learn:</div><div><ul><li><span style="font-size: 1rem;">.NET + AI Ecosystem</span></li></ul></div><div><br></div><div><span style="font-size: 1rem;">You'll learn about Microsoft's new abstraction libraries like Microsoft-Extensions-AI, which makes it super easy to integrate &amp; switch different LLM providers like OpenAI, Azure AI, Ollama and even self-hosted models.</span><br><ul><li><span style="font-size: 1rem;">Setting Up LLM Providers</span></li><li><span style="font-size: 1rem;">Configure the LLM providers—such as GitHub Models, Ollama, and Azure AI Foundry—so you can choose the best fit for your use case.</span></li><li><span style="font-size: 1rem;">Text Completion LLM w/ GitHub Models OpenAI gpt-5-mini and Ollama llama3.2 Model model</span></li></ul></div><div><br></div><div>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.</div><div><br></div><div><ul><li>Build AI Chat App with .NET and gpt-5-mini model</li></ul></div><div><span style="font-size: 1rem;"><br></span></div><div><span style="font-size: 1rem;">You'll develop back-and-forth conversation based messaging with LLM and user where the AI maintains context across multiple user turns.&nbsp; We will use Chat Streaming features when developing AI Chat Application.</span></div><div><ul><li>Function Calling with .NET and gpt-5-mini model</li><li><span style="font-size: 1rem;">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.</span></li><li><span style="font-size: 1rem;">.NET AI Vector Search using Vector Embeddings and Vector Store</span></li></ul></div><div><br></div><div>We’ll also cover Vector Search, a powerful feature that allows semantic search based on meaning—not keywords.</div><div><br></div><div>You’ll learn how to:</div><div><ul><li><span style="font-size: 1rem;">Generate embeddings using OpenAI’s text-embedding-3-small or Ollama’s all-MiniLM&nbsp; embeddings model,</span></li><li><span style="font-size: 1rem;">Store these in a vector database like Qdrant</span></li><li><span style="font-size: 1rem;">Query the vector store with user embedding to find top matches by similarity</span></li><li><span style="font-size: 1rem;">Retrieve relevant data based on similarity searches—all in our .NET applications.</span></li><li><span style="font-size: 1rem;">RAG – Retrieval-Augmented Generation with .NET</span></li></ul></div><div><br></div><div>You’ll learn how to combine vector search results with LLM responses to:</div><div><ul><li><span style="font-size: 1rem;">Retrieve relevant data from your own sources</span></li><li><span style="font-size: 1rem;">Break documents into chunks → embed them → store in vector DB</span></li><li><span style="font-size: 1rem;">At query time, embed the question → retrieve relevant chunks → pass them along with the user’s query to the LLM</span></li><li><span style="font-size: 1rem;">Get accurate, context-specific answers using your internal data from LLM</span></li><li><span style="font-size: 1rem;">We’ll implement the full RAG flow with real examples using .NET and Qdrant.</span></li><li><span style="font-size: 1rem;">Image Analysis with .NET AI</span></li></ul></div><div><br></div><div>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</div><div><ul><li>Vision models for object recognition, classification, or captioning</li><li><span style="font-size: 1rem;">Combining text and image processing to build more powerful, multi-modal applications for traffic cam analysis operations</span></li><li><span style="font-size: 1rem;">Final Project: E-Shop Semantic Search with .NET Aspire</span></li><li><span style="font-size: 1rem;">You’ll build a complete full-stack AI-powered EShop Vector Search app step by step.</span></li></ul></div><div><br></div><div>We’ll use:</div><div><ul><li><span style="font-size: 1rem;">.NET Aspire for service orchestration</span></li><li><span style="font-size: 1rem;">Qdrant as our Vector Database</span></li><li><span style="font-size: 1rem;">and GPT-5 Mini or Ollama’s local models to generate embeddings and respond intelligently to user queries</span></li></ul></div><div><br></div><div>In this project, you’ll:</div><div><ul><li><span style="font-size: 1rem;">Generate product embeddings with OpenAI text-embeddings or Ollama all-minilm</span></li><li><span style="font-size: 1rem;">Store them in Qdrant Vector DB&nbsp; for fast similarity search</span></li><li><span style="font-size: 1rem;">Implement a RAG flow that provides semantic search over our EShop product catalog</span></li><li><span style="font-size: 1rem;">Enable users to search products by meaning—not just keywords</span></li></ul></div><div><span style="font-size: 1rem;"><br></span></div><div><span style="font-size: 1rem;">This project brings everything you learn in this course into a single, full-stack, real-world app.</span></div><div><br></div><div>By the end of this course, you'll have the tools and confidence to build intelligent, GenAI-powered apps in .NET.</div>

What you'll learn:

• 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)