Csharp

Chat history and memory allow agents to maintain context across conversations and remember user preferences, which enables agents to provide personalized experiences. Using the Microsoft Agent Framework, we can use in-memory chat message stores, persistent databases, and specialized memory services to cater to a variety of different use cases. In this article, I’ll show you a simple example of how we can use an Azure Cosmos DB Vector store to store conversations we have with an agent, and how we can retrieve conversations so that our agents can maintain context. ...

Almost a year ago, I wrote a blog post on how you could use GitHub Models with Semantic Kernel applications for dev and test purposes. Now that the Microsoft Agent Framework is available, I thought I’d create an updated article on how you can use GitHub Models with the new framework, so that you don’t have to provision Azure Foundry and pay for using LLM usage to build agents. What is the Microsoft Agent Framework? It’s an open-source kit for building AI Agents and agentic workflows in Python and C#. The Agent Framework is an extension of both Semantic Kernel and AutoGen projects, and it provides a unified approach for building agents. Both the Semantic Kernel and AutoGen teams are working together to build the Microsoft Agent Framework. ...

A couple of years back, I built a Fitbit API token refresh service using Azure Functions. The purpose of that function was to refresh an access token that I can use to make calls to the Fitbit API and extract my own data using Azure Functions. This was before Azure Container Apps even existed, so Azure Functions was really the only option. WebJobs was an alternative (after all, Functions are essentially built on top of Azure WebJobs), but that wasn’t attractive since this was just an hobby project, and I didn’t want to break the bank. The problem with Azure Functions is that you’re restricted with the programming model. It’s fine if you just need the plumbing done for you for simple integrations, but if you want the flexibility, it’s not great. ...

In my last post on Semantic Kernel, I talked about how we interact with large language models (LLMs) through plugins that run with NLP prompts. We can also create plugins using native code. We can use our code to integrate with LLMs for calculations, data manipulation or any other functionality that our applications require. In this article, I’ll talk about how we can use native functions in the Semantic Kernel SDK, how we can create native function plugins, and how we can combine native functions with prompts. ...

When we use the Semantic Kernel SDK, we use plugins that act as the building blocks for our AI applications. Plugins essentially define the tasks that the kernel should complete, and the kernel interfaces with large language models and run the plugins we define. Plugins can include native code and natural language prompts, allowing us to use generative AI in our application. Plugins give us the flexibility of defining desired behavior in our application, and we can create custom prompt plugins to fine tune our applications precisely as we need to. ...