Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Integrate cutting-edge LLM technology quickly and easily into your apps

License

NotificationsYou must be signed in to change notification settings

j4t-git/semantic-kernel

 
 

Repository files navigation

Python packageNuget packagedotnet Dockerdotnet WindowsLicense: MITDiscord

ℹ️NOTE: This project is just like AI and will evolve quickly.We invite you to join us in developing the Semantic Kernel together!Please contribute byusing GitHubDiscussions,opening GitHubIssues,sending usPRs,joining ourDiscord community.

Semantic Kernel (SK) is a lightweight SDK enabling integration of AI LargeLanguage Models (LLMs) with conventional programming languages. The SK extensibleprogramming model combines natural languagesemantic functions, traditionalcodenative functions, andembeddings-based memory unlocking new potentialand adding value to applications with AI.

SK supportsprompt templating, functionchaining,vectorized memory, andintelligent planningcapabilities out of the box.

Semantic Kernel supports and encapsulates several design patterns from the latestin AI research, such that developers can infuse their applications withplugins likepromptchaining, recursive reasoning, summarization, zero/few-shot learning, contextualmemory, long-term memory,embeddings, semantic indexing,planning, retrieval-augmented generation and accessing externalknowledge stores as well as your own data.

By joining the SK community, you can build AI-first apps faster and have a front-rowpeek at how the SDK is being built. SK has been released as open-source so that morepioneering developers can join us in crafting the future of this landmark momentin the history of computing.

Get Started with Semantic Kernel ⚡

Semantic Kernel is available to explore AI and build apps with C#, Python and Java:

Java logo

See theFeature Matrix to see a breakdown of feature parity between our currently supported languages.

The quickest way to get started with the basics is to get an API key(OpenAI or Azure OpenAI)and to run one of the C#, Python, and Java console applications/scripts:

For C#:

  1. Create a new console app.
  2. Add the semantic kernel nugetMicrosoft.SemanticKernel.
  3. Copy the code fromhere into the appProgram.cs file.
  4. Replace the configuration placeholders for API key and other params with your key and settings.
  5. Run withF5 ordotnet run

For Python:

  1. Install the pip package:python -m pip install semantic-kernel.
  2. Create a new script e.g.hello-world.py.
  3. Store your API key and settings in an.env file as describedhere.
  4. Copy the code fromhere into thehello-world.py script.
  5. Run the python script.

For Java:

  1. Clone the repository:git clone https://github.com/microsoft/semantic-kernel.git
  2. Switch tosemantic-kernel directory and then checkout experimental Java branch:git checkout experimental-java
  3. Follow the instructionshere

Sample apps ⚡

The repository includes some sample applications, with a React frontend anda backend web service using Semantic Kernel.

Follow the links for more information and instructions about running these apps.

Simple chat summaryUse ready-to-use plugins and get plugins into your app easily.
Book creatorUse planner to deconstruct a complex goal and envision using the planner in your app.
Authentication and APIsUse a basic connector pattern to authenticate and connect to an API and imagine integrating external data into your app's LLM AI.
GitHub repository Q&AUse embeddings and memory to store recent data and allow you to query against it.
Copilot Chat Sample AppBuild your own chat experience based on Semantic Kernel.

Requirements:

Deploy Semantic Kernel to Azure in a web app service ☁️

Getting Semantic Kernel deployed to Azure as web app service is easy with one-click deployments. Clickhere to learn more on how to deploy to Azure.

Jupyter Notebooks ⚡

For a more hands-on overview, you can also check out the C# and Python Jupyter notebooks, startingfrom here:

Requirements: C# notebooks require.NET 7and the VS CodePolyglot extension.

Contributing and Community

We welcome your contributions and suggestions to SK community! One of the easiestways to participate is to engage in discussions in the GitHub repository.Bug reports and fixes are welcome!

For new features, components, or extensions, please open an issue and discuss withus before sending a PR. This is to avoid rejection as we might be taking the corein a different direction, but also to consider the impact on the larger ecosystem.

To learn more and get started:

Code of Conduct

This project has adopted theMicrosoft Open Source Code of Conduct.For more information see theCode of Conduct FAQor contactopencode@microsoft.comwith any additional questions or comments.

License

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under theMIT license.

About

Integrate cutting-edge LLM technology quickly and easily into your apps

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C#76.9%
  • Python23.1%

[8]ページ先頭

©2009-2025 Movatter.jp