AI Building Blocks for .NET: Add intelligence to your C# Apps
summary
Shows working C# code using Microsoft.Extensions.AI to call cloud and local models (Foundry, Olama) with CLI/integrated credentials, builds a RAG pipeline that stores movie embeddings and returns cosine scores (example: 98 and 40), and ingests Markdown→chunks→embeddings into a SQLite vector store. Demonstrates tool calls via MCP with the C# SDK to query Microsoft Learn and return doc links, and composes multiagent workflows and image generation using Microsoft Agent Framework plus a Nvidia Nemo agent; demos run end‑to‑end and return concrete results.
AI-written summary · about
chapters (12)
- 0:00Welcome and Intro
- 0:28What we're talking about today
- 2:58Today's building blocks
- 3:40Foundations: Microsoft.Extensions.AI
- 5:19Demo
- 10:50Intelligence: VectorData + DataIngestion
- 13:49Demo
- 22:55Tools: MCP with the C# SDK
- 24:39Demo
- 31:15The whole package: Microsoft Agent Framework
- 32:15Demo
- 43:30In Summary
related talks
46mInfusing your .NET Apps with AI: Practical Tools and Techniques
57mEasier AI allows everyone to build smart apps
01h 08mFrom Model Integration to Agents: Building Intelligent .NET Applications
41mAI + Machine Learning for .NET Developers
58mEasily Add GenAI to .NET Apps using Microsoft.Extensions.AI
01h 00mBuilding next-level conversational AI apps with .NET and Aspire
36mBuilding AI Agents in .NET with Azure AI Foundry
20mBuild Intelligent Apps with .NET and Azure