| Name | semantic-kernel JSON |
| Version |
1.35.0
JSON |
| download |
| home_page | None |
| Summary | Semantic Kernel Python SDK |
| upload_time | 2025-07-16 00:33:47 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Get Started with Semantic Kernel Python
Highlights
- Flexible Agent Framework: build, orchestrate, and deploy AI agents and multi-agent systems
- Multi-Agent Systems: Model workflows and collaboration between AI specialists
- Plugin Ecosystem: Extend with Python, OpenAPI, Model Context Protocol (MCP), and more
- LLM Support: OpenAI, Azure OpenAI, Hugging Face, Mistral, Vertex AI, ONNX, Ollama, NVIDIA NIM, and others
- Vector DB Support: Azure AI Search, Elasticsearch, Chroma, and more
- Process Framework: Build structured business processes with workflow modeling
- Multimodal: Text, vision, audio
## Quick Install
```bash
pip install --upgrade semantic-kernel
# Optional: Add integrations
pip install --upgrade semantic-kernel[hugging_face]
pip install --upgrade semantic-kernel[all]
```
Supported Platforms:
- Python: 3.10+
- OS: Windows, macOS, Linux
## 1. Setup API Keys
Set as environment variables, or create a .env file at your project root:
```bash
OPENAI_API_KEY=sk-...
OPENAI_CHAT_MODEL_ID=...
...
AZURE_OPENAI_API_KEY=...
AZURE_OPENAI_ENDPOINT=...
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=...
...
```
You can also override environment variables by explicitly passing configuration parameters to the AI service constructor:
```python
chat_service = AzureChatCompletion(
api_key=...,
endpoint=...,
deployment_name=...,
api_version=...,
)
```
See the following [setup guide](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/concepts/setup) for more information.
## 2. Use the Kernel for Prompt Engineering
Create prompt functions and invoke them via the `Kernel`:
```python
import asyncio
from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
from semantic_kernel.functions import KernelArguments
kernel = Kernel()
kernel.add_service(OpenAIChatCompletion())
prompt = """
1) A robot may not injure a human being...
2) A robot must obey orders given it by human beings...
3) A robot must protect its own existence...
Give me the TLDR in exactly {{$num_words}} words."""
async def main():
result = await kernel.invoke_prompt(prompt, arguments=KernelArguments(num_words=5))
print(result)
asyncio.run(main())
# Output: Protect humans, obey, self-preserve, prioritized.
```
## 3. Directly Use AI Services (No Kernel Required)
You can use the AI service classes directly for advanced workflows:
```python
import asyncio
import asyncio
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion, OpenAIChatPromptExecutionSettings
from semantic_kernel.contents import ChatHistory
async def main():
service = OpenAIChatCompletion()
settings = OpenAIChatPromptExecutionSettings()
chat_history = ChatHistory(system_message="You are a helpful assistant.")
chat_history.add_user_message("Write a haiku about Semantic Kernel.")
response = await service.get_chat_message_content(chat_history=chat_history, settings=settings)
print(response.content)
"""
Output:
Thoughts weave through context,
Semantic threads interlace—
Kernel sparks meaning.
"""
asyncio.run(main())
```
## 4. Build an Agent with Plugins and Tools
Add Python functions as plugins or Pydantic models as structured outputs;
Enhance your agent with custom tools (plugins) and structured output:
```python
import asyncio
from typing import Annotated
from pydantic import BaseModel
from semantic_kernel.agents import ChatCompletionAgent
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion, OpenAIChatPromptExecutionSettings
from semantic_kernel.functions import kernel_function, KernelArguments
class MenuPlugin:
@kernel_function(description="Provides a list of specials from the menu.")
def get_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.")
def get_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"
class MenuItem(BaseModel):
# Used for structured outputs
price: float
name: str
async def main():
# Configure structured outputs format
settings = OpenAIChatPromptExecutionSettings()
settings.response_format = MenuItem
# Create agent with plugin and settings
agent = ChatCompletionAgent(
service=AzureChatCompletion(),
name="SK-Assistant",
instructions="You are a helpful assistant.",
plugins=[MenuPlugin()],
arguments=KernelArguments(settings)
)
response = await agent.get_response("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())
```
You can explore additional getting started agent samples [here](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_agents).
## 5. Multi-Agent Orchestration
Coordinate a group of agents to iteratively solve a problem or refine content together:
```python
import asyncio
from semantic_kernel.agents import ChatCompletionAgent, GroupChatOrchestration, RoundRobinGroupChatManager
from semantic_kernel.agents.runtime import InProcessRuntime
from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion
def get_agents():
return [
ChatCompletionAgent(
name="Writer",
instructions="You are a creative content writer. Generate and refine slogans based on feedback.",
service=AzureChatCompletion(),
),
ChatCompletionAgent(
name="Reviewer",
instructions="You are a critical reviewer. Provide detailed feedback on proposed slogans.",
service=AzureChatCompletion(),
),
]
async def main():
agents = get_agents()
group_chat = GroupChatOrchestration(
members=agents,
manager=RoundRobinGroupChatManager(max_rounds=5),
)
runtime = InProcessRuntime()
runtime.start()
result = await group_chat.invoke(
task="Create a slogan for a new electric SUV that is affordable and fun to drive.",
runtime=runtime,
)
value = await result.get()
print(f"Final Slogan: {value}")
# Example Output:
# Final Slogan: "Feel the Charge: Adventure Meets Affordability in Your New Electric SUV!"
await runtime.stop_when_idle()
if __name__ == "__main__":
asyncio.run(main())
```
For orchestration-focused examples, see [these orchestration samples](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_agents/multi_agent_orchestration).
## More Examples & Notebooks
- [Getting Started with Agents](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_agents): Practical agent orchestration and tool use
- [Getting Started with Processes](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_processes): Modeling structured workflows with the Process framework
- [Concept Samples](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/concepts): Advanced scenarios, integrations, and SK patterns
- [Getting Started Notebooks](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started): Interactive Python notebooks for rapid experimentation
## Semantic Kernel Documentation
- [Getting Started with Semantic Kernel Python](https://learn.microsoft.com/en-us/semantic-kernel/get-started/quick-start-guide?pivots=programming-language-python)
- [Agent Framework Guide](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/?pivots=programming-language-python)
- [Process Framework Guide](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/process/process-framework)
Raw data
{
"_id": null,
"home_page": null,
"name": "semantic-kernel",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Microsoft <SK-Support@microsoft.com>",
"download_url": "https://files.pythonhosted.org/packages/bc/5c/4d761ff412c211260415f0e6683d22139b4ab990d9010c9962d1ec35d1b8/semantic_kernel-1.35.0.tar.gz",
"platform": null,
"description": "# Get Started with Semantic Kernel Python\n\nHighlights\n- Flexible Agent Framework: build, orchestrate, and deploy AI agents and multi-agent systems\n- Multi-Agent Systems: Model workflows and collaboration between AI specialists\n- Plugin Ecosystem: Extend with Python, OpenAPI, Model Context Protocol (MCP), and more\n- LLM Support: OpenAI, Azure OpenAI, Hugging Face, Mistral, Vertex AI, ONNX, Ollama, NVIDIA NIM, and others\n- Vector DB Support: Azure AI Search, Elasticsearch, Chroma, and more\n- Process Framework: Build structured business processes with workflow modeling\n- Multimodal: Text, vision, audio\n\n## Quick Install\n\n```bash\npip install --upgrade semantic-kernel\n# Optional: Add integrations\npip install --upgrade semantic-kernel[hugging_face]\npip install --upgrade semantic-kernel[all]\n```\n\nSupported Platforms:\n- Python: 3.10+\n- OS: Windows, macOS, Linux\n\n## 1. Setup API Keys\n\nSet as environment variables, or create a .env file at your project root:\n\n```bash\nOPENAI_API_KEY=sk-...\nOPENAI_CHAT_MODEL_ID=...\n...\nAZURE_OPENAI_API_KEY=...\nAZURE_OPENAI_ENDPOINT=...\nAZURE_OPENAI_CHAT_DEPLOYMENT_NAME=...\n...\n```\n\nYou can also override environment variables by explicitly passing configuration parameters to the AI service constructor:\n\n```python\nchat_service = AzureChatCompletion(\n api_key=...,\n endpoint=...,\n deployment_name=...,\n api_version=...,\n)\n```\n\nSee the following [setup guide](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/concepts/setup) for more information.\n\n## 2. Use the Kernel for Prompt Engineering\n\nCreate prompt functions and invoke them via the `Kernel`:\n\n```python\nimport asyncio\nfrom semantic_kernel import Kernel\nfrom semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion\nfrom semantic_kernel.functions import KernelArguments\n\nkernel = Kernel()\nkernel.add_service(OpenAIChatCompletion())\n\nprompt = \"\"\"\n1) A robot may not injure a human being...\n2) A robot must obey orders given it by human beings...\n3) A robot must protect its own existence...\n\nGive me the TLDR in exactly {{$num_words}} words.\"\"\"\n\n\nasync def main():\n result = await kernel.invoke_prompt(prompt, arguments=KernelArguments(num_words=5))\n print(result)\n\n\nasyncio.run(main())\n# Output: Protect humans, obey, self-preserve, prioritized.\n```\n\n## 3. Directly Use AI Services (No Kernel Required)\n\nYou can use the AI service classes directly for advanced workflows:\n\n```python\nimport asyncio\nimport asyncio\n\nfrom semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion, OpenAIChatPromptExecutionSettings\nfrom semantic_kernel.contents import ChatHistory\n\n\nasync def main():\n service = OpenAIChatCompletion()\n settings = OpenAIChatPromptExecutionSettings()\n\n chat_history = ChatHistory(system_message=\"You are a helpful assistant.\")\n chat_history.add_user_message(\"Write a haiku about Semantic Kernel.\")\n response = await service.get_chat_message_content(chat_history=chat_history, settings=settings)\n print(response.content)\n\n \"\"\"\n Output:\n\n Thoughts weave through context, \n Semantic threads interlace\u2014 \n Kernel sparks meaning.\n \"\"\"\n\n\nasyncio.run(main())\n```\n\n## 4. Build an Agent with Plugins and Tools\n\nAdd Python functions as plugins or Pydantic models as structured outputs;\n\nEnhance your agent with custom tools (plugins) and structured output:\n\n```python\nimport asyncio\nfrom typing import Annotated\nfrom pydantic import BaseModel\nfrom semantic_kernel.agents import ChatCompletionAgent\nfrom semantic_kernel.connectors.ai.open_ai import AzureChatCompletion, OpenAIChatPromptExecutionSettings\nfrom semantic_kernel.functions import kernel_function, KernelArguments\n\nclass MenuPlugin:\n @kernel_function(description=\"Provides a list of specials from the menu.\")\n def get_specials(self) -> Annotated[str, \"Returns the specials from the menu.\"]:\n return \"\"\"\n Special Soup: Clam Chowder\n Special Salad: Cobb Salad\n Special Drink: Chai Tea\n \"\"\"\n\n @kernel_function(description=\"Provides the price of the requested menu item.\")\n def get_item_price(\n self, menu_item: Annotated[str, \"The name of the menu item.\"]\n ) -> Annotated[str, \"Returns the price of the menu item.\"]:\n return \"$9.99\"\n\nclass MenuItem(BaseModel):\n # Used for structured outputs\n price: float\n name: str\n\nasync def main():\n # Configure structured outputs format\n settings = OpenAIChatPromptExecutionSettings()\n settings.response_format = MenuItem\n\n # Create agent with plugin and settings\n agent = ChatCompletionAgent(\n service=AzureChatCompletion(),\n name=\"SK-Assistant\",\n instructions=\"You are a helpful assistant.\",\n plugins=[MenuPlugin()],\n arguments=KernelArguments(settings)\n )\n\n response = await agent.get_response(\"What is the price of the soup special?\")\n print(response.content)\n\n # Output:\n # The price of the Clam Chowder, which is the soup special, is $9.99.\n\nasyncio.run(main()) \n```\n\nYou can explore additional getting started agent samples [here](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_agents).\n\n## 5. Multi-Agent Orchestration\n\nCoordinate a group of agents to iteratively solve a problem or refine content together:\n\n```python\nimport asyncio\nfrom semantic_kernel.agents import ChatCompletionAgent, GroupChatOrchestration, RoundRobinGroupChatManager\nfrom semantic_kernel.agents.runtime import InProcessRuntime\nfrom semantic_kernel.connectors.ai.open_ai import AzureChatCompletion\n\ndef get_agents():\n return [\n ChatCompletionAgent(\n name=\"Writer\",\n instructions=\"You are a creative content writer. Generate and refine slogans based on feedback.\",\n service=AzureChatCompletion(),\n ),\n ChatCompletionAgent(\n name=\"Reviewer\",\n instructions=\"You are a critical reviewer. Provide detailed feedback on proposed slogans.\",\n service=AzureChatCompletion(),\n ),\n ]\n\nasync def main():\n agents = get_agents()\n group_chat = GroupChatOrchestration(\n members=agents,\n manager=RoundRobinGroupChatManager(max_rounds=5),\n )\n runtime = InProcessRuntime()\n runtime.start()\n result = await group_chat.invoke(\n task=\"Create a slogan for a new electric SUV that is affordable and fun to drive.\",\n runtime=runtime,\n )\n value = await result.get()\n print(f\"Final Slogan: {value}\")\n\n # Example Output:\n # Final Slogan: \"Feel the Charge: Adventure Meets Affordability in Your New Electric SUV!\"\n\n await runtime.stop_when_idle()\n\nif __name__ == \"__main__\":\n asyncio.run(main())\n```\n\nFor orchestration-focused examples, see [these orchestration samples](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_agents/multi_agent_orchestration).\n\n## More Examples & Notebooks\n\n- [Getting Started with Agents](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_agents): Practical agent orchestration and tool use \n- [Getting Started with Processes](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started_with_processes): Modeling structured workflows with the Process framework \n- [Concept Samples](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/concepts): Advanced scenarios, integrations, and SK patterns \n- [Getting Started Notebooks](https://github.com/microsoft/semantic-kernel/tree/main/python/samples/getting_started): Interactive Python notebooks for rapid experimentation \n\n## Semantic Kernel Documentation\n\n- [Getting Started with Semantic Kernel Python](https://learn.microsoft.com/en-us/semantic-kernel/get-started/quick-start-guide?pivots=programming-language-python) \n- [Agent Framework Guide](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/?pivots=programming-language-python) \n- [Process Framework Guide](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/process/process-framework)\n",
"bugtrack_url": null,
"license": null,
"summary": "Semantic Kernel Python SDK",
"version": "1.35.0",
"project_urls": {
"homepage": "https://learn.microsoft.com/en-us/semantic-kernel/overview/",
"issues": "https://github.com/microsoft/semantic-kernel/issues",
"release_notes": "https://github.com/microsoft/semantic-kernel/releases?q=tag%3Apython-1&expanded=true",
"source": "https://github.com/microsoft/semantic-kernel/tree/main/python"
},
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "b014b0ddf679dae28393cf068401e8f953602adf78d1fe17504479ddf9f7afdf",
"md5": "9c026c85715ca80446d13f52b7d0824c",
"sha256": "ce2b9c313d53841448059833e885f082d136c54a113e687359b14c5e358c0e66"
},
"downloads": -1,
"filename": "semantic_kernel-1.35.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9c026c85715ca80446d13f52b7d0824c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 875792,
"upload_time": "2025-07-16T00:33:45",
"upload_time_iso_8601": "2025-07-16T00:33:45.891030Z",
"url": "https://files.pythonhosted.org/packages/b0/14/b0ddf679dae28393cf068401e8f953602adf78d1fe17504479ddf9f7afdf/semantic_kernel-1.35.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "bc5c4d761ff412c211260415f0e6683d22139b4ab990d9010c9962d1ec35d1b8",
"md5": "6a1f832de7301bf32446240f72020720",
"sha256": "7fe49faaf7086263d3ac4cb42ec5d0b2344dcc21f0759bd6b79a92a7b4f8533f"
},
"downloads": -1,
"filename": "semantic_kernel-1.35.0.tar.gz",
"has_sig": false,
"md5_digest": "6a1f832de7301bf32446240f72020720",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 572339,
"upload_time": "2025-07-16T00:33:47",
"upload_time_iso_8601": "2025-07-16T00:33:47.948613Z",
"url": "https://files.pythonhosted.org/packages/bc/5c/4d761ff412c211260415f0e6683d22139b4ab990d9010c9962d1ec35d1b8/semantic_kernel-1.35.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-16 00:33:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "microsoft",
"github_project": "semantic-kernel",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "semantic-kernel"
}
