I’ve been trying to wrap my head around function/tool calling for a while now, and I’m excited to share what I’ve learned with you. It’s a powerful way to let developers integrate advanced AI features directly into their applications. We’ll walk through understanding the core concepts, setting up your environment, and implementing a practical example using a C# source generator.

Microsoft recently unveiled Phi-3, the latest iteration of their Small Language Model (SLM). And hot on its heels is Ollama, a powerful tool that enables you to run SLMs and LLMs right on your own machine.

Excited to dive in? In this guide, I’ll show you how to harness the power of Phi-3 and Ollama using C# and Semantic Kernel. I’ll walk you through the process of creating a simple console application to get you started on your SLM journey.

So, let’s get coding and unlock the potential of Phi-3 and Ollama on your machine!

C# 12 is the latest, just released, version of the popular programming language that runs on the .NET 8 platform. It introduces several new features that aim to improve the expressiveness, performance, and safety of the language. In this post, we will explore some of these features and see how they can benefit your code.

With my team, we like to keep our C# code base updated. So, recently we went to .NET 7 and C# 11. At the same time, we were still adopting some of the new capabilities of .NET 6 and C# 10. Our code base is large, so it takes some time. One of the new features that we planned to use was the ArgumentNullException.ThrowIfNull method, which throws an exception if an argument is null. In this post, I will show you how I effortlessly did that refactoring by letting the machine work and not the human 😁 (me). In the past, I used the same approach to migrate lots of code that used Assert.True() to Assert.That(, Is.True) and for some other even more complex cases. We will use ReSharper and Rider for that.

I am using a tool called logseq to manage my notes. It is a fantastic tool, and I would like to be able to extend it. I am not an expert web developer, but I am a .NET developer. I would like to be able to write plugins for logseq using .NET and C#. I have found a way to do it using WebAssembly. In this post, I am going to show you how to do it.

In the past, within my team at Innoveo, we had several discussions about the best way to unit test async WPF ICommand. We value quality, so testing is essential to us. We decided to make the methods called by the command internal so that our tests could call those.

What is the problem with unit testing an Async WPF ICommand? The problem is that the command is an async void method! So, you have no way to await the end of the execution of your command. So, your test might assert on things that are still executing.

Early in my journey in developing software, I used to start a project by setting first a way to build my software automatically each time I did a set of changes. Long, very long ago, I used scripts scheduled to run. When JetBrains shipped TeamCity I started to use it extensively for my projects, here is my first post about “Set Up a Build Computer using VisualSVN, Team City, MsTest, NUnit“ from March 21, 2008, but used it since version 1.0. Later on, I also used Azure Pipelines to build Git Diff Margin and also GitHub Actions, for example, to build and deploy those pages.

In the previous post “gRPC and C# 8 Async stream“, we looked at how gRPC server stream and C# 8 Async stream work great together. In this post, we are looking at the way we can, from the client, stop the server to stream results back.

gRPC and its idea to describe an API in a standardized file, which can generate both client and server code to interact in different languages is a compelling idea.
In this post, I would like to have a quick look at the experience you would have with gRPC streaming capability and the new C# 8 async streams, which sounds like a perfect match.

This post is a transcript of an internal post I did on Innoveo Solutions internal blog. Thanks to Innoveo to let me share this here!

Skye Editor is our metal model editor which is written in C# 4, WPF uses Model-View-ViewModel design pattern and MVVM Light.