Semantic Kernel
The latest news from the Semantic Kernel team for developers
Latest posts
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...
Microsoft Semantic Kernel Office Hours Update
Microsoft Semantic Kernel Office Hours Update Over the upcoming Holidays period there are several office hours sessions that we'll be cancelling. Below is an updated view of our upcoming office hours availability. We will resume with regularly scheduled Office Hours on January 8th for our weekly and monthly sessions. During this time, feel free to catch up on recordings from our Semantic Kernel Office Hours. Our Office Hours are posted here one week after the session: Semantic Kernel Office Hours - YouTube Community office hours During the Semantic Kernel community office hours, you can bring all of your ...
Unlocking the Power of Memory: Announcing General Availability of Semantic Kernel’s Memory Packages
We are thrilled to announce the General Availability (GA) of our Memory packages for .NET, Java, and Python! The Semantic Kernel team and our partners have been working hard to allow you to quickly connect to vector stores and make it easy for you to do embeddings and data retrieval between stores. Transforming Data Management with Vector Stores With the Memory package, you can take advantage of: Vector Store Connectors include (with more coming): For the most up to date list of available connectors see our out-of-the-box connectors page. Seamless integration with Semantic Kernel Chat C...
Announcing the GA Release of Filters for .NET and Python in Semantic Kernel
We are excited to announce the General Availability (GA) release of Filters for our .NET and Python Semantic Kernel! This vital enhancement strengthens the control and visibility developers have when running functions, ensuring responsible AI practices are instilled from the ground up. Filters not only improve security but also contribute to building enterprise-ready solutions that you can feel confident deploying. What Are Filters? Filters in Semantic Kernel provide a mechanism for developers to manage how and when functions operate within their applications. For example, validation filters can be employed...
Customer Case Study: Announcing the Microsoft Semantic Kernel Elasticsearch Connector
Today we're excited to feature the Elastic team to share more about their Semantic Kernel Elasticsearch connector. Read the entire announcement here. I'll turn it over to Srikanth Manvi 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 agents, including the capability to enhance large language models (LLMs) with more relevant, data-driven responses from a vector store. Semantic Kern...
Announcing the GA Release of the OpenAPI Plugin for .NET and Python in Semantic Kernel
We are thrilled to announce the General Availability (GA) release of the OpenAPI package for Semantic Kernel, available for both .NET and Python! With this significant milestone, developers can easily integrate existing APIs as plugins, enhancing the capabilities of their AI agents while making them more versatile in real-world applications. Why OpenAPI Plugins Matter In many enterprises, a robust set of APIs already exists, facilitating critical functions for automation services and front-end applications. Semantic Kernel now allows you to harness these APIs—transforming them into plugins that your agents can ...