A few weeks ago I got contacted by someone(Hi Chris!) who was trying to get my Semantic Kernel demo's up and running on his machine. Chris tried to get the application up and running but got some error messages. I used his input to improve the readme file and updated the main branch to simplify the getting started experience.
However there was one specific error he shared that I want to talk about a little more. Here is the screenshot he shared with me:
The reason that he got this error is because ‘auto function calling’ was enabled in the code and the model he was using didn’t support this feature.
Remark: I updated the code to disable auto function calling after I got his email.
A good excuse to talk a little more about this feature…
What is (auto) function calling in Semantic Kernel?
With function calling, you give the LLM the option to interact with your existing code. You can do this quite explicit as I explained in my OllamaSharp post but with Semantic Kernel the process is greatly simplified by automatically describing the registered functions and their parameters to the model and then handling the back-and-forth communication between the model and your code. The model itself will decide based on the provided prompt if a specific function should be called or not.
To make this work you need to create a plugin containing one or more KernelFunction methods:
This plugin should be registered in Semantic Kernel:
Auto function calling is enabled by default in Semantic Kernel:
But you can disable it using the following code:
What models can I use that support function calling?
If you are using Ollama, you can use the filter on the Models page to list only models that support tooling:
More information
Function calling with chat completion | Microsoft Learn