OpenAI-API-dotnet VS semantic-kernel

Can't say I've compared them to one another, but OpenAI by OkGoDoIt has bee pretty easy to use.

I'm keen to tinker around on the ChatGPT space, and I managed to build something pretty good in C# using this plugin. https://github.com/OkGoDoIt/OpenAI-API-dotnet It has an Angular front end on the client and allows the user to query ChatGPT. So far so good.

Are you familiar with https://github.com/OkGoDoIt/OpenAI-API-dotnet?

One such library is available on GitHub: OpenAI-API-dotnet. This package is designed to work seamlessly with .NET applications, making it easy for you to integrate Chat-GPT into your project.

I'm happy to point people in the direction of what was used, this used OpenAI GPT API using: https://github.com/OkGoDoIt/OpenAI-API-dotnet and the backend AI service is built in ASP Core and interacts with actual WoW data stored in a MySQL database to build the prompts using various bits of info about the targeted NPC and current player.

On this topic, when developing with the OpenAI API in .NET like with this library at Github, I was pleasantly surprised just how easy it is to customize a chat bot. As in... Super simple. The ChatGPT API simply takes what they call a "System" message and this sets up the personality of the bot. E.g. "You are a librarian, eager to answer any questions. You refuse to discuss topics not pertaining to literature." One can also populate it with a leading conversation to run off with.

I'm baffled, what am I doing wrong here? Shouldn't this emulate similar results to ChatGPT? I am using the following NuGet for OpenAI access: https://github.com/OkGoDoIt/OpenAI-API-dotnet

In Visual Studio you can install a NuGet package which allows you to connect with OpenAI it is documented here https://github.com/OkGoDoIt/OpenAI-API-dotnet the caveat is that you need to write your app using C#, there are many places you can convert vb.net to C# until you get the hang of C#, you'll get it in no time, I am sure.

There is an amazing sample on how to create your own LLM Service class to be used in Semantic Kernel. You can view the Sample here: https://github.com/microsoft/semantic-kernel/blob/3451a4ebbc9db0d049f48804c12791c681a326cb/dotnet/samples/KernelSyntaxExamples/Example16_CustomLLM.cs

This week, I had the chance to explore the SemanticKernel code base, particularly the core plugins. SemanticKernel comes equipped with these built-in plugins:

In this article we'll look at the high-level capabilities building AI orchestration systems in C# with Semantic Kernel, a rapidly maturing open-source AI orchestration framework.

I'm using Semantic Kernel (https://github.com/microsoft/semantic-kernel) and it's really nice. Makes building more complex workflows really simple without sacrificing control.

A bunch of examples (https://github.com/microsoft/semantic-kernel/blob/main/dotne...) for how to handle just about anything you need to do with OAI with a lot less boilerplate.

I haven't tried it but there's Microsoft semantic-kernel.

https://github.com/microsoft/semantic-kernel

Semantic Kernel github.com/microsoft/semantic-kernel

The need for efficient model routing has been a point of discussion in the community. Addressing this, I've submitted a pull request to Semantic-Kernel that introduces an automated multi-model connector.