Skip to main content

Debugging Semantic Kernel in C#

I'm working on a (small) project where I'm using Microsoft Semantic Kernel. Although it makes it really easy to build your own copilots and AI agents, it is not that easy to understand what is going on (or what is going wrong).

Just in case you have no clue what Semantic Kernel is:

Semantic Kernel is an open-source SDK that lets you easily build agents that can call your existing code. It is highly extensible and  you can use Semantic Kernel with models from OpenAI, Azure OpenAI, Hugging Face, and more. It can be used in C#, Python and Java code.

After adding the Microsoft.Semantic.Kernel.Core and Microsoft.Semantic.Kernel.Connectors.OpenAI nuget packages, the simplest implementation to write is the following:

That’s easy and there is not much magic going on as you are directly controlling the prompt that is shared with the LLM.

However when you start to use the more complex features like the planner, you don't know what exactly is shared with the LLM. In that case it can be useful to enable debugging. Therefore update the kernel configuration code to add logging:

If we now run our Semantic Kernel enabled application, we can see the prompt that is send to the LLM in the output window:


Happy AI coding!

Popular posts from this blog

.NET 8–Keyed/Named Services

A feature that a lot of IoC container libraries support but that was missing in the default DI container provided by Microsoft is the support for Keyed or Named Services. This feature allows you to register the same type multiple times using different names, allowing you to resolve a specific instance based on the circumstances. Although there is some controversy if supporting this feature is a good idea or not, it certainly can be handy. To support this feature a new interface IKeyedServiceProvider got introduced in .NET 8 providing 2 new methods on our ServiceProvider instance: object? GetKeyedService(Type serviceType, object? serviceKey); object GetRequiredKeyedService(Type serviceType, object? serviceKey); To use it, we need to register our service using one of the new extension methods: Resolving the service can be done either through the FromKeyedServices attribute: or by injecting the IKeyedServiceProvider interface and calling the GetRequiredKeyedServic...

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.

Kubernetes–Limit your environmental impact

Reducing the carbon footprint and CO2 emission of our (cloud) workloads, is a responsibility of all of us. If you are running a Kubernetes cluster, have a look at Kube-Green . kube-green is a simple Kubernetes operator that automatically shuts down (some of) your pods when you don't need them. A single pod produces about 11 Kg CO2eq per year( here the calculation). Reason enough to give it a try! Installing kube-green in your cluster The easiest way to install the operator in your cluster is through kubectl. We first need to install a cert-manager: kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.14.5/cert-manager.yaml Remark: Wait a minute before you continue as it can take some time before the cert-manager is up & running inside your cluster. Now we can install the kube-green operator: kubectl apply -f https://github.com/kube-green/kube-green/releases/latest/download/kube-green.yaml Now in the namespace where we want t...