mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Fix README's and update getting started (#352)
This commit is contained in:
Mark Wallace
committed by
GitHub
Unverified
GitHub
parent
ef16774878
commit
5a1de491d4
@@ -1,4 +1,4 @@
|
||||
# Get Started with Microsoft Agent Framework
|
||||
# Microsoft Agent Framework
|
||||
|
||||
Highlights
|
||||
- Flexible Agent Framework: build, orchestrate, and deploy AI agents and multi-agent systems
|
||||
@@ -11,150 +11,21 @@ Highlights
|
||||
|
||||
Below are the basics for each language implementation. For more details on python see [here](./python/README.md) and for .NET see [here](./dotnet/README.md).
|
||||
|
||||
## Python - Quick Install
|
||||
|
||||
```bash
|
||||
pip install agent-framework
|
||||
# Optional: Add Azure integration
|
||||
pip install agent-framework[azure]
|
||||
# Optional: Add Foundry integration
|
||||
pip install agent-framework[foundry]
|
||||
# Optional: Both
|
||||
pip install agent-framework[azure,foundry]
|
||||
```
|
||||
|
||||
Supported Platforms:
|
||||
- Python: 3.10+
|
||||
- OS: Windows, macOS, Linux
|
||||
|
||||
## Python - 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=...
|
||||
OPENAI_RESPONSES_MODEL_ID=...
|
||||
...
|
||||
AZURE_OPENAI_API_KEY=...
|
||||
AZURE_OPENAI_ENDPOINT=...
|
||||
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=...
|
||||
...
|
||||
FOUNDRY_PROJECT_ENDPOINT=...
|
||||
FOUNDRY_MODEL_DEPLOYMENT_NAME=...
|
||||
```
|
||||
|
||||
You can also override environment variables by explicitly passing configuration parameters to the chat client constructor:
|
||||
|
||||
```python
|
||||
from agent_framework.azure import AzureChatClient
|
||||
|
||||
chat_client = AzureChatClient(
|
||||
api_key=...,
|
||||
endpoint=...,
|
||||
deployment_name=...,
|
||||
api_version=...,
|
||||
)
|
||||
```
|
||||
|
||||
See the following [setup guide](https://github.com/microsoft/agent-framework/tree/main/python/samples/getting_started) for more information.
|
||||
|
||||
## Python - 2. Create a Simple Agent
|
||||
|
||||
Create agents and invoke them directly:
|
||||
|
||||
```python
|
||||
import asyncio
|
||||
from agent_framework import ChatClientAgent
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
|
||||
async def main():
|
||||
async with ChatClientAgent(
|
||||
chat_client=FoundryChatClient(),
|
||||
instructions="""These are the Three Laws of Robotics:
|
||||
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...
|
||||
|
||||
Respond concisely to the user's request.
|
||||
"""
|
||||
):
|
||||
result = await agent.run("Summarize the Three Laws of Robotics")
|
||||
print(result.text)
|
||||
"""
|
||||
Output:
|
||||
Protect humans, obey, self-preserve, prioritized.
|
||||
"""
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
## Python - 3. Build an Agent with Tools
|
||||
|
||||
Enhance your agent with custom tools and function calling:
|
||||
|
||||
```python
|
||||
import asyncio
|
||||
from typing import Annotated
|
||||
from random import randint
|
||||
from pydantic import Field
|
||||
from agent_framework import ChatClientAgent
|
||||
from agent_framework.openai import OpenAIResponsesClient
|
||||
|
||||
|
||||
def get_weather(
|
||||
location: Annotated[str, Field(description="The location to get the weather for.")],
|
||||
) -> str:
|
||||
"""Get the weather for a given location."""
|
||||
conditions = ["sunny", "cloudy", "rainy", "stormy"]
|
||||
return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."
|
||||
|
||||
|
||||
def get_menu_specials() -> str:
|
||||
"""Get today's menu specials."""
|
||||
return """
|
||||
Special Soup: Clam Chowder
|
||||
Special Salad: Cobb Salad
|
||||
Special Drink: Chai Tea
|
||||
"""
|
||||
|
||||
|
||||
async def main():
|
||||
agent = ChatClientAgent(
|
||||
chat_client=OpenAIResponsesClient(),
|
||||
instructions="You are a helpful assistant that can provide weather and restaurant information.",
|
||||
tools=[get_weather, get_menu_specials]
|
||||
)
|
||||
|
||||
response = await agent.run("What's the weather in Amsterdam and what are today's specials?")
|
||||
print(response.text)
|
||||
|
||||
"""
|
||||
Output:
|
||||
The weather in Amsterdam is sunny with a high of 22°C. Today's specials include
|
||||
Clam Chowder soup, Cobb Salad, and Chai Tea as the special drink.
|
||||
"""
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
You can explore additional agent samples [here](https://github.com/microsoft/agent-framework/tree/main/python/samples/getting_started/agents).
|
||||
|
||||
**Note**: Advanced orchestration patterns like GroupChat, Sequential, and Concurrent orchestrations are coming soon.
|
||||
|
||||
## More Examples & Samples
|
||||
|
||||
- [Getting Started with Agents](https://github.com/microsoft/agent-framework/tree/main/python/samples/getting_started/agents): Basic agent creation and tool usage
|
||||
- [Chat Client Examples](https://github.com/microsoft/agent-framework/tree/main/python/samples/getting_started/chat_client): Direct chat client usage patterns
|
||||
- [Azure Integration](https://github.com/microsoft/agent-framework/tree/main/python/packages/azure): Azure OpenAI and AI Foundry integration
|
||||
- [.NET Orchestration Samples](https://github.com/microsoft/agent-framework/tree/main/dotnet/samples/GettingStarted/Orchestration): Advanced multi-agent patterns (.NET)
|
||||
### Python
|
||||
- [Getting Started with Agents](./python/samples/getting_started/agents): Basic agent creation and tool usage
|
||||
- [Chat Client Examples](./python/samples/getting_started/chat_client): Direct chat client usage patterns
|
||||
- [Azure Integration](./python/packages/azure): Azure OpenAI and AI Foundry integration
|
||||
|
||||
### .Net
|
||||
- [Getting Started with Agents](./dotnet/samples/GettingStarted/Steps): Basic agent creation and tool usage
|
||||
- [Agent Provider Samples](./dotnet/samples/GettingStarted/Providers): Samples showing different agent providers
|
||||
- [Orchestration Samples](./dotnet/samples/GettingStarted/Orchestration): Advanced multi-agent patterns
|
||||
|
||||
## Agent Framework Documentation
|
||||
|
||||
- [Agent Framework Repository](https://github.com/microsoft/agent-framework)
|
||||
- [Python Package Documentation](https://github.com/microsoft/agent-framework/tree/main/python)
|
||||
- [.NET Package Documentation](https://github.com/microsoft/agent-framework/tree/main/dotnet)
|
||||
- [Design Documents](https://github.com/microsoft/agent-framework/tree/main/docs/design)
|
||||
- [Design Documents](./docs/design)
|
||||
- [Architectural Decision Records](./docs/decisions)
|
||||
- Learn docs are coming soon.
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
# Get Started with Microsoft Agent Framework for C# Developers
|
||||
|
||||
## Run the Minimal Console demo
|
||||
|
||||
The Minimal Console demo is a simple console application which shows how to create and run an agent.
|
||||
|
||||
Supported Platforms:
|
||||
- .Net: net9.0, net8.0, netstandard2.0, net472
|
||||
- OS: Windows, macOS, Linux
|
||||
|
||||
If you want to use the latest published packages following the instructions [here](../docs/FAQS.md).
|
||||
|
||||
### 1. Configure required environment variables
|
||||
|
||||
This samples uses Azure OpenAI by default so you need to set the following environment variable
|
||||
|
||||
``` powershell
|
||||
$env:AZURE_OPENAI_ENDPOINT = "https://<your deployment>.openai.azure.com/"
|
||||
```
|
||||
|
||||
If you want to use OpenAI
|
||||
|
||||
1. Edit [Program.cs](./demos/MinimalConsole/Program.cs) and change the following lines:
|
||||
```csharp
|
||||
AIAgent agent = new AzureOpenAIClient(
|
||||
new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!),
|
||||
new AzureCliCredential())
|
||||
.GetChatClient("gpt-4o-mini")
|
||||
.CreateAIAgent(
|
||||
instructions: "You are a helpful assistant, you can help the user with weather information.",
|
||||
tools: [AIFunctionFactory.Create(GetWeather)]);
|
||||
```
|
||||
To this:
|
||||
```csharp
|
||||
AIAgent agent = new OpenAIClient(Environment.GetEnvironmentVariable("OPENAI_API_KEY")!)
|
||||
.GetChatClient("gpt-4o-mini")
|
||||
.CreateAIAgent(
|
||||
instructions: "You are a helpful assistant, you can help the user with weather information.",
|
||||
tools: [AIFunctionFactory.Create(GetWeather)]);
|
||||
```
|
||||
2. Create an environment variable with your OpenAI key
|
||||
``` powershell
|
||||
$env:OPENAI_API_KEY = "sk-..."
|
||||
```
|
||||
|
||||
### 2. Build the project
|
||||
|
||||
```powershell
|
||||
cd demos\MinimalConsole
|
||||
dotnet build
|
||||
```
|
||||
|
||||
### 3. Run the demonstration
|
||||
|
||||
``` powershell
|
||||
dotnet run --framework net9.0 --no-build
|
||||
```
|
||||
|
||||
Sample output:
|
||||
|
||||
```
|
||||
The weather in Amsterdam is currently cloudy, with a high temperature of 15°C.
|
||||
```
|
||||
|
||||
+1
-10
@@ -1,13 +1,4 @@
|
||||
# Get Started with Microsoft Agent Framework
|
||||
|
||||
Highlights
|
||||
- Flexible Agent Framework: build, orchestrate, and deploy AI agents and multi-agent systems
|
||||
- Multi-Agent Orchestration: Group chat, sequential, concurrent, and handoff patterns
|
||||
- Plugin Ecosystem: Extend with native functions, OpenAPI, Model Context Protocol (MCP), and more
|
||||
- LLM Support: OpenAI, Azure OpenAI, Azure AI Foundry, and more
|
||||
- Runtime Support: In-process and distributed agent execution
|
||||
- Multimodal: Text, vision, and function calling
|
||||
- Cross-Platform: .NET and Python implementations
|
||||
# Get Started with Microsoft Agent Framework for Python Developers
|
||||
|
||||
## Quick Install
|
||||
|
||||
|
||||
Reference in New Issue
Block a user