Semantic Kernel
The latest news from the Semantic Kernel team for developers
Latest posts
Guest Blog: Building Multi-Agent Systems with Multi-Models in Semantic Kernel – Part 1
Today I want to welcome back Arafat Tehsin, who’s a Microsoft Most Valuable Professional (MVP) for AI. He’s written an article we’re sharing below, focused on Building Multi-Agent Systems with Multi-Models in Semantic Kernel. We’ll turn it over to Arafat to share more! Imagine running a restaurant. Each of your team member, from the chef to server to the cashier has got specialised skills. While the chef prepares delicious meals, the server ensures that the food is delivered promptly and the cashier ensures smooth transactions. Together, they deliver a seamless dining experience. Similarly, in a multi-a...
Understanding Semantic Kernel AI Connectors
AI Connectors in Semantic Kernel are components that facilitate communication between the Kernel's core functionalities and various AI services. They abstract the intricate details of service-specific protocols, allowing developers to seamlessly interact with AI services for tasks like text generation, chat interactions, and more. Using AI Connectors in Semantic Kernel Developers utilize AI connectors to connect their applications to different AI services efficiently. The connectors manage the requests and responses, providing a streamlined way to leverage the power of these AI services with...
Empowering AI Agents with Tools via OpenAPI: A Hands-On Guide with Microsoft Semantic Kernel Agents
Today the Semantic Kernel team is happy to welcome back our guest author, Akshay Kokane. We will turn it over to him to dive into his recent Medium article on Semantic Kernel. As we advance towards an Agentic Approach in the AI world, I would like to share my insights on how Semantic Kernel can assist in building AI agents and leveraging existing APIs to create intelligent agents. In a previous article, I discussed how Semantic Kernel can develop a multi-agent system that fosters a collaborative environment for these agents to interact and deliver results. In this new blog post, I am pleased to share that ...
Unwrap some Semantic Kernel (Power)Toys this holiday season
Windows PowerToys has always been one of my favorite productivity hacks, and its latest release adds Paste with Advanced AI, which takes it to a new level. This feature, powered by Semantic Kernel, transforms how you work with text, images, and data from your clipboard by applying AI-driven enhancements. What Does It Do? Advanced Paste uses the OpenAI API to analyze, reformat, and transform clipboard text based on the user’s input, for example: Advanced Paste also has additional paste actions that work beyond simple text-based inputs: With Semantic Kernel, you can n...
Global Expansion – “G3J Learn Semantic Kernel” Show – A Deep Dive in Korean!
Global Expansion – "G3J Learn Semantic Kernel" Show – A Deep Dive in Korean! Localization Increases Demand Following the success of this multi-language delivery, we quickly noticed a surge in demand for localized content. Developers from different parts of the world have expressed interest in diving deeper into Semantic Kernel, and we couldn’t be more excited to expand on this momentum. To address this growing interest, we are thrilled to announce the recordings of a new initiative, starting with a deep dive into Semantic Kernel in Korean. The pilot session featured above is the first of many localized forma...
ONNX GenAI Connector for Python (Experimental)
ONNX GenAI Connector for Python (Experimental) With the latest update we added support for running models locally with the onnxruntime-genai. The onnxruntime-genai package is powered by the ONNX Runtime in the background, but first let’s clarify what ONNX, ONNX Runtime and ONNX Runtime-GenAI are. ONNX ONNX is an open-source format for AI models, both for Deep Learning and traditional Machine Learning. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. ONNX Runtime The ONNX Runtime executes the saved weighted operations stored using the O...
Customer Case Study: How to use Elasticsearch Vector Store Connector for Microsoft Semantic Kernel for AI Agent development
How to use Elasticsearch Vector Store Connector for Microsoft Semantic Kernel for AI Agent development Today we're excited to feature the Elastic team to share more about their Semantic Kernel Elasticsearch Vector Store connector for Microsoft Semantic Kernel. Read the entire announcement here. I'll turn it over to Srikanth Manvi and Florian Bernd to dive into it. In collaboration with the Microsoft Semantic Kernel team, we are announcing the availability of Semantic Kernel Elasticsearch Vector Store Connector, for Microsoft Semantic Kernel (.NET) users. Semantic Kernel simplifies building enterprise-grade AI a...
Tracing your AI apps with Azure AI Foundry
We previously introduced observability within the Semantic Kernel. For further insights, please refer to our previous blog post, and you can also explore our learn site for additional details. To summarize, observability is an essential aspect of your application stack, particularly in today's landscape where AI plays a significant role in numerous applications. Given that large language models are inherently stochastic, they do not consistently generate the same outputs from identical inputs. As an application developer, it is vital for your team to have the capability to monitor the transactions made by your...
使用Semantic Kernel来开启您的AI旅程
Semantic Kernel (SK) 是由微软开发的一款开源开发工具包，旨在帮助开发者和企业利用最新的人工智能技术构建更智能和复杂的AI驱动解决方案，例如检索增强生成 (RAG) 和智能体 (Agent)。 核心概念 内核（Kernel） 您可以将SK的内核视为一个容器，该容器包含您所需的所有与AI相关的组件，如提示语模板、AI服务和插件。如果将所有的服务和插件提供给内核，则AI会根据需求自动使用它们。SK还提供多项企业级功能，使您可以保证您的AI符合安全要求且在部署后能够持续监控AI的表现。 提示语（Prompt Engineering） 提示语在使用大型语言模型中至关重要。优质的提示语能够显著提升用户体验。SK通过提示语模板（template）的方式来实现自然语言与AI插件的混合使用，让您的提示语变得更加的灵活。 AI服务（AI Services） SK支持多种AI应用场景，包括对话补全，文本生成，嵌入（embedding）生成，图像与文字转换，以及音频与文字转换。此外，SK兼容多个AI服务提供商，如OpenAI，Azure，Google AI， Amazon Bedrock， 以及提供本地推理服务的Ollama等。 插件（Plugins/Functions） SK通过插件支持扩展大型语言模型的功能。插件可以是代码或自然语言，并可集成外部系统，如数据库、API或其他云服务，以便AI解决方...