Semantic Kernel

Guest Blog: Microsoft MVP Developed Course on Understanding Semantic Kernel

August 6, 2024 Aug 6, 2024 08/6/24

Sophia Lagerkrans-Pandey

Today we're featuring an AI Microsoft Most Valuable Professional (MVP) who's been developing content on Semantic Kernel. We wanted to highlight Jamie Maguire's work and detail the multi-part blog below. Here's the link to his course: New Course: Understanding Semantic Kernel – Jamie Maguire https://jamiemaguire.net/index.php/2024/08/03/...

Introducing enterprise multi-agent support in Semantic Kernel

August 1, 2024 Aug 1, 2024 08/1/24

Chris Rickman, Evan Mattson

The term "agent" has become a popular term within the industry. There have many different definitions, but at their core, they consist of a system prompt (i.e., a persona), plugins, and an ability to automatically reason and create plans to address user goals. Up until today, we've demonstrated how you could use components of Semantic ...

What’s coming next? Summer / Fall roadmap for Semantic Kernel

July 30, 2024 Jul 30, 2024 07/30/24

Matthew Bolanos

It feels like yesterday when we went live with v1.0+ of all our SDKs (Python, Java, and C#) at Microsoft Build. Since then, the Semantic Kernel team has been hard at work making Semantic Kernel even better. Now that we've made some progress, we'd like to share what we have planned over the next few months for Microsoft Ignite. To see ...

Support for Azure.AI.OpenAI and OpenAI v2 is coming

July 30, 2024 Jul 30, 2024 07/30/24

Mark Wallace

Microsoft announced the official OpenAI library for .NET at the Build 2024 conference. This new SDK ensures that .NET developers have parity with other programming language libraries when accessing Azure OpenAI models. This means the new SDK will be able to support the latest OpenAI features and models as soon as they come out, such as GPT4o ...

Announcing Semantic Kernel for Java 1.2.0

July 25, 2024 Jul 25, 2024 07/25/24

Derek Keeler, John Oliver

Hello Java AI developers! We are announcing the release of Semantic Kernel for Java v1.2.0! Since our release of v1.0 this past May, we have been working to improve and expand the capabilities we provide. Today, we are thrilled to share the latest updates, new features, and experimental features with you. What’s New in Semantic Kernel ...

Customer Case Study: SimCorp’s AI Journey with Semantic Kernel

July 24, 2024 Jul 24, 2024 07/24/24

Sophia Lagerkrans-Pandey

(image) We're excited to feature the SimCorp team on the Semantic Kernel blog today. The SimCorp team will discuss their AI journey and how they’ve integrated Semantic Kernel to build out their AI solutions. Let’s dive into the details from the SimCorp team! SimCorp Background: SimCorp was founded in 1971 and has continuously ...

Planning with Semantic Kernel using Automatic Function Calling

July 23, 2024 Jul 23, 2024 07/23/24

Dmytro Struk, Sophia Lagerkrans-Pandey

Hello, everyone! AI planning is a powerful tool that allows to generate and execute complex workflows in applications based on specified goal. In Semantic Kernel, it's possible to implement planning logic using FunctionCallingStepwisePlanner class. Today we want to introduce a new way how to achieve the same results by using Automatic ...

The future of Planners in Semantic Kernel

July 23, 2024 Jul 23, 2024 07/23/24

Matthew Bolanos

Since the very earlier days of Semantic Kernel, we have shipped experimental “planners” that use prompts to generate multi-step plans. This was extremely powerful because it allowed developers to use LLMs (which were created to merely generate text) to begin automating business processes. Since then, the Semantic Kernel team has evolved...

Model as a Service (MaaS) Available for Semantic Kernel

July 17, 2024 Jul 17, 2024 07/17/24

Sophia Lagerkrans-Pandey, Tao Chen

Hello! We are delighted to make an announcement regarding the availability of Azure AI Inference within Semantic Kernel (Python). This latest AI connector empowers you to experiment with a broader range of models hosted on Azure within your applications.   The Sample Application: Evaluating LLMs Here is the location of the full ...

Introducing Python Function Choice Behavior: Streamlining AI Model Configuration

July 11, 2024 Jul 11, 2024 07/11/24

Sophia Lagerkrans-Pandey, Evan Mattson

  Introducing Function Choice Behavior Today, we're excited to introduce the Function Choice Behavior, an enhancement over the existing Function Call Behavior. This new feature streamlines configuration and supports specifying multiple required functions, simplifying code and enhancing functionality. One significant advantage of ...