Semantic Kernel
The latest news from the Semantic Kernel team for developers
Latest posts
Semantic Kernel and Microsoft.Extensions.AI: Better Together, Part 2
This is Part 2 of our series on integrating Microsoft.Extensions.AI with Semantic Kernel. In Part 1, we explored the relationship between these technologies and how they complement each other. Now, let's dive into practical examples showing how to use Microsoft.Extensions.AI abstractions with Semantic Kernel in non-agent scenarios. Getting Started with Microsoft.Extensions.AI and Semantic Kernel Before we dive into examples, let's understand what we'll be working with. Microsoft.Extensions.AI provides foundational abstractions like  and , while Semantic Kernel builds upon these to provide higher-level functio...
Semantic Kernel: Multi-agent Orchestration
The field of AI is rapidly evolving, and the need for more sophisticated, collaborative, and flexible agent-based systems is growing. With this in mind, Semantic Kernel introduces a new multi-agent orchestration framework that enables developers to build, manage, and scale complex agent workflows with ease. This post explores the new orchestration patterns, their capabilities, and how you can leverage them in your own projects. Why Multi-agent Orchestration? Traditional single-agent systems are limited in their ability to handle complex, multi-faceted tasks. By orchestrating multiple agents, each with special...
Semantic Kernel and Microsoft.Extensions.AI: Better Together, Part 1
This is the start of a series highlighting the integration between Microsoft Semantic Kernel and Microsoft.Extensions.AI. Future parts will provide detailed examples of using Semantic Kernel with Microsoft.Extensions.AI abstractions. The most common questions are: This blog post will address these questions and offer guidance on when and how to use them. First, we will explore what Microsoft Extensions AI is and its relationship with Semantic Kernel. The Evolution of AI Integration in .NET with Microsoft Extensions AI Artificial Intelligence, or AI, is evolving at a rapid pace that many d...
Transitioning to new Extensions AI IEmbeddingGenerator interface
As Semantic Kernel shifts its foundational abstractions to Microsoft.Extensions.AI, we are obsoleting and moving away from our experimental embeddings interfaces to the new standardized abstractions that provide a more consistent and powerful way to work with AI services across the .NET ecosystem. The Evolution of Embedding Generation in Semantic Kernel Semantic Kernel has always aimed to provide a unified way to interact with AI services, including embedding generation. Our initial approach used the  interface, which served us well during the experimental phase. However, as the AI landscape has matured, so...
Vector Data Extensions are now Generally Available (GA)
We’re excited to announce the release of Microsoft.Extensions.VectorData.Abstractions, a foundational library providing exchange types and abstractions for vector stores when working with vector data in AI-powered applications. This release is the result of a close collaboration between the Semantic Kernel and .NET teams, combining expertise in AI and developer tooling to deliver a robust, extensible solution for developers. What is Microsoft.Extensions.VectorData.Abstractions? Microsoft.Extensions.VectorData.Abstractions provides shared abstractions and utilities for working with vector data, enabling develope...
Semantic Kernel: Package previews, Graduations & Deprecations
Semantic Kernel: Package Previews, Graduations & Deprecations We are excited to share a summary of recent updates and continuous clean-up efforts across the Semantic Kernel .NET codebase. These changes focus on improving maintainability, aligning with the latest APIs, and ensuring a consistent experience for users. Below you’ll find details on package graduations, deprecations, and a few other improvements. Graduations Spring Cleaning – Deprecations Improvements & Updates These updates are part of our ongoing effort to keep the S...
RC1: Semantic Kernel for Java Agents API
We’re excited to announce the release candidate of the Semantic Kernel for Java Agents API! This marks a major step forward in bringing the power of intelligent agents to Java developers, enabling them to build rich, contextual, and interactive AI experiences using the Semantic Kernel framework. What Are Agents in Semantic Kernel? Agents are intelligent, autonomous components that can reason, plan, and act using natural language. They leverage large language models (LLMs) to interact with users, invoke tools, and maintain context over time. With this API, Java developers can now create agents that: ...
Guest Blog: Orchestrating AI Agents with Semantic Kernel Plugins: A Technical Deep Dive
Today we're excited to welcome Jarre Nejatyab as a guest blog to highlight a technical deep dive on orchestrating AI Agents with Semantic Kernel Plugins. In the rapidly evolving world of Large Language Models (LLMs), orchestrating specialized AI agents has become crucial for building sophisticated cognitive architectures capable of complex reasoning and task execution. While powerful, coordinating multiple agents—each with unique capabilities and data access—presents significant engineering challenges. Microsoft's Semantic Kernel (SK) offers a robust framework for managing this complexity through its intuitive p...
Guest Blog: Letting AI Help Make the World More Accessible – Analyzing Website Accessibility with Semantic Kernel and OmniParser
Today we're excited to welcome Jonathan David, as a guest author on the Semantic Kernel blog. We'll turn it over to Jonathan to dive into Letting AI Help Make the World More Accessible - Analyzing Website Accessibility with Semantic Kernel and OmniParser. With the European Accessibility Act and Germany's Barrierefreiheitsstärkungsgesetz (which translates to Barrier Freedom Strengthening Act) coming into force in July 2025, ensuring digital accessibility is no longer optional. This article explores the importance of accessibility and how AI-driven solutions using Semantic Kernel and OmniParser could strea...