News

Microsoft Open Sources Tool for GPT-4-Infused Apps

Microsoft has open sourced an internal incubation project that can help developers integrate cutting-edge AI models quickly and easily into their apps.

Called Semantic Kernel (SK), the project's GitHub repo describes it as "a lightweight SDK enabling integration of AI large language models (LLMs) with conventional programming languages."

And, if you haven't heard the news, that means developers can take advantage of the hot new GPT-4 LLM, from Microsoft partner OpenAI. That's the company behind the groundbreaking ChatGPT chatbox powered by advanced natural language processing (NLP) technology that has captured the public's attention perhaps more than any other app, ever. ChatGPT is based on a the previous GPT-3.5 LLM, whose capabilities are dwarfed by GPT-4.

OpenAI, of course, also supplies the tech behind the GitHub Copilot "AI pair programmer", which has transformed software development and is heavily used by coders using Visual Studio and Visual Studio Code. Microsoft borrowed the "Copilot" moniker as a way to describe the advanced AI tech it's infusing into software of all kinds, ranging from business products like Microsoft 365 to the "new Bing" search engine to development-oriented offerings like the low-code/no-code Power Platform, including the software development component, Power Apps.

Championed by CEO Satya Nadella, Microsoft seems to be quickly transforming into a an AI-centric company across the board, clearly gaining an edge on competitors on the strength of its $10 billion-plus investments into OpenAI, of which it is on track to own a 49 percent share.

"Semantic Kernel (SK) is a lightweight SDK that lets you mix conventional programming languages, like C# and Python, with the latest in Large Language Model (LLM) AI 'prompts' with prompt templating, chaining, and planning capabilities," Microsoft announced in a March 17 blog post titled "Hello, Semantic Kernel! "This enables you to build new experiences into your apps to bring unparalleled productivity for your users: like summarizing a lengthy chat exchange, flagging an important 'next step' that's added to your to-do list via Microsoft Graph, or planning a full vacation instead of just reserving a seat on a plane."

The open sourcing of SK, Microsoft said, not only quickens the pace of building AI-centric apps, but also gives developers insights into how the SDK is being built. Such insights are hidden in GPT-4, with OpenAI withholding the release of fundamental technical details, unlike its practice with previous releases.

"We designed SK to take advantage of emerging capabilities of next generation models like GPT-4," Microsoft said. "For example, both the Planner and Skills architectures were built for achieving outcomes instead of just outputs -- in a more goal-oriented approach to programming that's embodied by SK's underlying architecture."

[Click on image for larger view.] Semantic Kernel (source: Microsoft).

Microsoft listed key benefits of SK as:

  • Fast integration: SK is designed to be embedded in any kind of application, making it easy for you to test and get running with LLM AI.
  • Extensibility: With SK, you can connect with external data sources and services -- giving their apps the ability to use natural language processing in conjunction with live information.
  • Better prompting: SK's templated prompts let you quickly design semantic functions with useful abstractions and machinery to unlock LLM AI's potential.
  • Novel-But-Familiar: Native code is always available to you as a first-class partner on your prompt engineering quest. You get the best of both worlds.

SK is initially targeting C# developers, but preview support is also being provided for Python, a darling among data scientists, while Microsoft is also eying support for other languages including its own TypeScript, based upon what it learns from community feedback.

To help developers get started, Microsoft is offering a free LinkedIn learning course. Its description reads: "The future of AI is finally here, and it's a gamechanger for software developers. Explore the possibilities of Semantic Kernel (SK), the new face of AI-powered development, packaged in a lightweight, easy-to-use, multilayered software development kit. Get up and running quickly with SK, the latest addition to the Microsoft AI ecosystem that enables developers to integrate LLM AI capabilities easily into their apps."

In addition to the LinkedIn learning course, Microsoft explained how developers can clone the repo and try out examples like:

  • Simple chat summary: Use ready-to-use skills and get those skills into your app easily.
  • Book creator: Use planner to deconstruct a complex goal and envision using the planner in your app.
  • Authentication and APIs: Use a basic connector pattern to authenticate and connect to an API and imagine integrating external data into your app's LLM AI.

An Open AI API Key or Azure Open AI service key is required to get started.

That's because, along with the ability to utilize GPT-4, SK hooks into the Azure OpenAI service, with support for other services and products and projects expected.

"SK has been released as open source so that more pioneering developers can join us in crafting the future of this landmark moment in the history of computing," Microsoft said.

About the Author

David Ramel is an editor and writer for Converge360.

comments powered by Disqus

Featured

  • AI for GitHub Collaboration? Maybe Not So Much

    No doubt GitHub Copilot has been a boon for developers, but AI might not be the best tool for collaboration, according to developers weighing in on a recent social media post from the GitHub team.

  • Visual Studio 2022 Getting VS Code 'Command Palette' Equivalent

    As any Visual Studio Code user knows, the editor's command palette is a powerful tool for getting things done quickly, without having to navigate through menus and dialogs. Now, we learn how an equivalent is coming for Microsoft's flagship Visual Studio IDE, invoked by the same familiar Ctrl+Shift+P keyboard shortcut.

  • .NET 9 Preview 3: 'I've Been Waiting 9 Years for This API!'

    Microsoft's third preview of .NET 9 sees a lot of minor tweaks and fixes with no earth-shaking new functionality, but little things can be important to individual developers.

  • Data Anomaly Detection Using a Neural Autoencoder with C#

    Dr. James McCaffrey of Microsoft Research tackles the process of examining a set of source data to find data items that are different in some way from the majority of the source items.

  • What's New for Python, Java in Visual Studio Code

    Microsoft announced March 2024 updates to its Python and Java extensions for Visual Studio Code, the open source-based, cross-platform code editor that has repeatedly been named the No. 1 tool in major development surveys.

Subscribe on YouTube