Develop innovative AI apps with .NET 8.0

The future of artificial intelligence (AI) is now, and .NET 8 provides the perfect tools for building comprehensive applications. Whether you're starting new projects or extending existing ones, the latest developments in .NET make it easier than ever to integrate AI and go from idea to solution.

Why use AI in your applications?
  • Increasing user loyaltyOffer relevant and satisfying interactions that will delight your users.
  • Increased productivity and efficiencyReduce errors and save time through automated processes.
  • New business opportunitiesOffering innovative services that deliver real added value.
  • Competitive advantageStaying ahead of market trends and meeting customer expectations.

These are just some of the many advantages that demonstrate what is possible with AI.
Learn more about the possibilities that .NET 8 offers.

First steps in AI development

If you are new to AI development, the new .NET + AI Documentation an excellent starting point. Here you'll find quickstart guides and practical examples of how to use OpenAI models with the Azure OpenAI SDK or the Semantic Kernel Library. Further examples can be found at Azure developer templates for .NET and AI.

Semantic Kernel: The key to easy integration

Many examples utilize the Semantic Kernel (SK), an open-source library that simplifies the development of AI solutions that can leverage existing code. The SK is a flexible SDK that works with models from OpenAI, Azure OpenAI, Hugging Face, and many others, and enables connections to popular vector repositories such as Qdrant, Milivus, and Azure AI Search. By providing unified abstractions, the Semantic Kernel reduces the effort required to integrate diverse models and vector repositories. Dependency injection in .NET allows you to easily swap components as you develop and optimize your applications.

Monitoring and debugging your AI applications

At Build 2024, it was demonstrated how AI solutions can be monitored and debugged, both locally and in production. Semantic Kernel supports end-to-end traceability and debugging of AI calls, helping you optimize performance, quality, and costs. SK builds on the OpenTelemetry Protocol (OTLP) This makes it easy to monitor your application with any storage or reporting tool that supports this.

Strong foundations for AI developments

The .NET runtime and libraries are continuously evolving to meet the demands of AI. New tools such as tokenization libraries and the introduction of Tensor TensorPrimitives and ML.NET simplify the preparation of text data and mathematical operations for AI applications. These extensions make .NET a robust and reliable platform for AI and machine learning that can be seamlessly integrated with existing libraries such as ML.NET, TorchSharp, and ONNX.

AI at the edge with Small Language Models (SLMs)

Smaller language models are becoming increasingly accessible, enabling AI applications to run locally and at the edge. Libraries such as OnnxRuntime GenAI offer .NET developers the opportunity to use these models and develop customized solutions that are precisely tailored to the needs of their applications.

A growing ecosystem for .NET developers

The ecosystem of AI tools and services for .NET developers is growing steadily. At Build 2024, several new projects were presented and announcements related to technologies were made, including:

Additional information

Here are some helpful resources: