Microsoft Semantic Kernel is an open-source framework for building AI apps. It allows developers to use state-of-the-art AI models to add intelligence to their apps. You can consider Semantic Kernel (SK) as a lightweight SDK that allows integration of AI Large Language Models (LLMs) with conventional programming languages. The Semantic Kernel SDK now supports both C# and Python versions and is generally available.
The SK extensible programming model combines natural language semantic functions, traditional code native functions, and embeddings-based memory unlocking new potential and adding value to applications with AI. It also supports prompt templating, function chaining, vectorized memory, and intelligent planning capabilities out of the box.
To show the power and versatility of the Semantic Kernel SDK, Microsoft released an open-source Copilot Chat starter app that allows developers add conversational interfaces to their line-of-business apps that leverages Memories (for injecting business-specific context into AI prompts) and the Planner (enabling the AI to “goal seek”).
Semantic Kernel is available to easily deploy to Azure with supplied deployment template scripts. Semantic Kernel also has a preview version of its VS Code extension that offers tooling for creating and editing and debugging AI plugins.