- Notifications
You must be signed in to change notification settings - Fork4.1k
Integrate cutting-edge LLM technology quickly and easily into your apps
License
microsoft/semantic-kernel
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
Build intelligent AI agents and multi-agent systems with this enterprise-ready orchestration framework
Semantic Kernel is a model-agnostic SDK that empowers developers to build, orchestrate, and deploy AI agents and multi-agent systems. Whether you're building a simple chatbot or a complex multi-agent workflow, Semantic Kernel provides the tools you need with enterprise-grade reliability and flexibility.
- Python: 3.10+
- .NET: .NET 8.0+
- Java: JDK 17+
- OS Support: Windows, macOS, Linux
- Model Flexibility: Connect to any LLM with built-in support forOpenAI,Azure OpenAI,Hugging Face,NVidia and more
- Agent Framework: Build modular AI agents with access to tools/plugins, memory, and planning capabilities
- Multi-Agent Systems: Orchestrate complex workflows with collaborating specialist agents
- Plugin Ecosystem: Extend with native code functions, prompt templates, OpenAPI specs, or Model Context Protocol (MCP)
- Vector DB Support: Seamless integration withAzure AI Search,Elasticsearch,Chroma, and more
- Multimodal Support: Process text, vision, and audio inputs
- Local Deployment: Run withOllama,LMStudio, orONNX
- Process Framework: Model complex business processes with a structured workflow approach
- Enterprise Ready: Built for observability, security, and stable APIs
First, set the environment variable for your AI Services:
Azure OpenAI:
export AZURE_OPENAI_API_KEY=AAA....
or OpenAI directly:
export OPENAI_API_KEY=sk-...
pip install semantic-kernel
dotnet add package Microsoft.SemanticKerneldotnet add package Microsoft.SemanticKernel.Agents.core
Seesemantic-kernel-java build for instructions.
Create a simple assistant that responds to user prompts:
importasynciofromsemantic_kernel.agentsimportChatCompletionAgentfromsemantic_kernel.connectors.ai.open_aiimportAzureChatCompletionasyncdefmain():# Initialize a chat agent with basic instructionsagent=ChatCompletionAgent(service=AzureChatCompletion(),name="SK-Assistant",instructions="You are a helpful assistant.", )# Get a response to a user messageresponse=awaitagent.get_response(messages="Write a haiku about Semantic Kernel.")print(response.content)asyncio.run(main())# Output:# Language's essence,# Semantic threads intertwine,# Meaning's core revealed.
usingMicrosoft.SemanticKernel;usingMicrosoft.SemanticKernel.Agents;varbuilder=Kernel.CreateBuilder();builder.AddAzureOpenAIChatCompletion(Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT"),Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT"),Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY"));varkernel=builder.Build();ChatCompletionAgentagent=new(){Name="SK-Agent",Instructions="You are a helpful assistant.",Kernel=kernel,};awaitforeach(AgentResponseItem<ChatMessageContent>responseinagent.InvokeAsync("Write a haiku about Semantic Kernel.")){Console.WriteLine(response.Message);}// Output:// Language's essence,// Semantic threads intertwine,// Meaning's core revealed.
Enhance your agent with custom tools (plugins) and structured output:
importasynciofromtypingimportAnnotatedfrompydanticimportBaseModelfromsemantic_kernel.agentsimportChatCompletionAgentfromsemantic_kernel.connectors.ai.open_aiimportAzureChatCompletion,OpenAIChatPromptExecutionSettingsfromsemantic_kernel.functionsimportkernel_function,KernelArgumentsclassMenuPlugin:@kernel_function(description="Provides a list of specials from the menu.")defget_specials(self)->Annotated[str,"Returns the specials from the menu."]:return""" Special Soup: Clam Chowder Special Salad: Cobb Salad Special Drink: Chai Tea """@kernel_function(description="Provides the price of the requested menu item.")defget_item_price(self,menu_item:Annotated[str,"The name of the menu item."] )->Annotated[str,"Returns the price of the menu item."]:return"$9.99"classMenuItem(BaseModel):price:floatname:strasyncdefmain():# Configure structured output formatsettings=OpenAIChatPromptExecutionSettings()settings.response_format=MenuItem# Create agent with plugin and settingsagent=ChatCompletionAgent(service=AzureChatCompletion(),name="SK-Assistant",instructions="You are a helpful assistant.",plugins=[MenuPlugin()],arguments=KernelArguments(settings) )response=awaitagent.get_response(messages="What is the price of the soup special?")print(response.content)# Output:# The price of the Clam Chowder, which is the soup special, is $9.99.asyncio.run(main())
usingSystem.ComponentModel;usingMicrosoft.SemanticKernel;usingMicrosoft.SemanticKernel.Agents;usingMicrosoft.SemanticKernel.ChatCompletion;varbuilder=Kernel.CreateBuilder();builder.AddAzureOpenAIChatCompletion(Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT"),Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT"),Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY"));varkernel=builder.Build();kernel.Plugins.Add(KernelPluginFactory.CreateFromType<MenuPlugin>());ChatCompletionAgentagent=new(){Name="SK-Assistant",Instructions="You are a helpful assistant.",Kernel=kernel,Arguments=newKernelArguments(newPromptExecutionSettings(){FunctionChoiceBehavior=FunctionChoiceBehavior.Auto()})};awaitforeach(AgentResponseItem<ChatMessageContent>responseinagent.InvokeAsync("What is the price of the soup special?")){Console.WriteLine(response.Message);}sealedclassMenuPlugin{[KernelFunction,Description("Provides a list of specials from the menu.")]publicstringGetSpecials()=>""" Special Soup: Clam Chowder Special Salad: Cobb Salad Special Drink: Chai Tea """;[KernelFunction,Description("Provides the price of the requested menu item.")]publicstringGetItemPrice([Description("The name of the menu item.")]stringmenuItem)=>"$9.99";}
Build a system of specialized agents that can collaborate:
importasynciofromsemantic_kernel.agentsimportChatCompletionAgent,ChatHistoryAgentThreadfromsemantic_kernel.connectors.ai.open_aiimportAzureChatCompletion,OpenAIChatCompletionbilling_agent=ChatCompletionAgent(service=AzureChatCompletion(),name="BillingAgent",instructions="You handle billing issues like charges, payment methods, cycles, fees, discrepancies, and payment failures.")refund_agent=ChatCompletionAgent(service=AzureChatCompletion(),name="RefundAgent",instructions="Assist users with refund inquiries, including eligibility, policies, processing, and status updates.",)triage_agent=ChatCompletionAgent(service=OpenAIChatCompletion(),name="TriageAgent",instructions="Evaluate user requests and forward them to BillingAgent or RefundAgent for targeted assistance."" Provide the full answer to the user containing any information from the agents",plugins=[billing_agent,refund_agent],)thread:ChatHistoryAgentThread=Noneasyncdefmain()->None:print("Welcome to the chat bot!\n Type 'exit' to exit.\n Try to get some billing or refund help.")whileTrue:user_input=input("User:> ")ifuser_input.lower().strip()=="exit":print("\n\nExiting chat...")returnFalseresponse=awaittriage_agent.get_response(messages=user_input,thread=thread, )ifresponse:print(f"Agent :>{response}")# Agent :> I understand that you were charged twice for your subscription last month, and I'm here to assist you with resolving this issue. Here’s what we need to do next:# 1. **Billing Inquiry**:# - Please provide the email address or account number associated with your subscription, the date(s) of the charges, and the amount charged. This will allow the billing team to investigate the discrepancy in the charges.# 2. **Refund Process**:# - For the refund, please confirm your subscription type and the email address associated with your account.# - Provide the dates and transaction IDs for the charges you believe were duplicated.# Once we have these details, we will be able to:# - Check your billing history for any discrepancies.# - Confirm any duplicate charges.# - Initiate a refund for the duplicate payment if it qualifies. The refund process usually takes 5-10 business days after approval.# Please provide the necessary details so we can proceed with resolving this issue for you.if__name__=="__main__":asyncio.run(main())
- 📖 Try ourGetting Started Guide or learn aboutBuilding Agents
- 🔌 Explore over 100Detailed Samples
- 💡 Learn about core Semantic KernelConcepts
- Authentication Errors: Check that your API key environment variables are correctly set
- Model Availability: Verify your Azure OpenAI deployment or OpenAI model access
- Check ourGitHub issues for known problems
- Search theDiscord community for solutions
- Include your SDK version and full error messages when asking for help
We welcome your contributions and suggestions to the SK community! One of the easiest ways 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 with us before sending a PR. This is to avoid rejection as we might be taking the core in a different direction, but also to consider the impact on the larger ecosystem.
To learn more and get started:
Read thedocumentation
Learn how tocontribute to the project
Ask questions in theGitHub discussions
Ask questions in theDiscord community
Follow the team on ourblog
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.
Copyright (c) Microsoft Corporation. All rights reserved.
Licensed under theMIT license.
About
Integrate cutting-edge LLM technology quickly and easily into your apps
Topics
Resources
License
Code of conduct
Security policy
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Packages0
Uh oh!
There was an error while loading.Please reload this page.