AI Building Blocks – A new, unified AI layer

Most .NET apps can be made more powerful and productive through AI features, such as semantic search, auto-classification, summarization, translation, data extraction, and even chat-based assistants. But until now there’s been no single standard representation for AI concepts within .NET itself, so developers needed to combine many unrelated APIs.

Microsoft.Extensions.AI addresses this by providing a new set of standard APIs for AI services, including large language models (LLMs) running locally on your workstation or as hosted services, integrating with text embeddings, vector stores, and more.

In this talk we’ll demonstrate how these new standard abstractions let you combine multiple services that can easily be swapped and changed over time, and how you can plug into the internals for more advanced scenarios. By the end you’ll be ready to start experimenting with new AI features in your own apps.

Connect with .NET:
Blog: https://aka.ms/dotnet/blog
Twitter: https://aka.ms/dotnet/twitter
TikTok: https://aka.ms/dotnet/tiktok
Mastodon: https://aka.ms/dotnet/mastodon
LinkedIn: https://aka.ms/dotnet/linkedin
Facebook: https://aka.ms/dotnet/facebook
Docs: https://learn.microsoft.com/dotnet
Forums: https://aka.ms/dotnet/forums
🙋‍♀️Q&A: https://aka.ms/dotnet-qa
👨‍🎓Microsoft Learn: https://aka.ms/learndotnet

#dotnet