Build A Dream Team with Autogen

This repository leverages Microsoft Autogen 0.4, Azure OpenAI and integration with Streamlit, to build an end-to-end multi-agent application, this repository makes it easy to build test and deploy an advanced multi-agent framework, based on Magentic One.

Table of Contents

• Key Features
• Prerequisites
• Getting Started
  • Clone the Repository
  • Login to Azure
  • Deploy Azure Resources
• Running Locally
  • Create a Virtual Environment
  • Install Dependencies
  • Update Configuration
  • Start the Application

Key Features

The following are the key features:

• Advanced Multi-agent Framework: This solution is based on the popular framework Autogen and Magentic One.
• Friendly UI: Easy way to build and share data apps powered by Streamlit.
• Easy Deployment: Developer-friendly deployment that accelerates your path from a local development environment to Azure with Azure Developer CLI.
• Secure Code Execution: Fast access to secure sandboxed with strong isolation environments that are ideal for running code or applications with Azure Container Apps dynamic sessions.
• Managed Identities: Built-in Azure managed identities to eliminate the need for developers to manage these credentials.
• Observability and Debugging: Built-in features and tools for tracking, tracing, and debugging agent interactions and workflows, including PromptFlow tracing.

Prerequisites

• Azure Subscription.
• Azure Developer CLI: Download azd for Windows, Other OS's.
• Docker
  • Once installed, run docker login.
• Python >= 3.10, < 3.13: Download Python.
• (Optional) uv: Python package and project manager.

Getting Started

Clone the Repository

git clone https://github.com/0Upjh80d/autogen-dream-team

Login to Azure

azd auth login

Note

You need to choose your preferred region (you can start with east us or sweden central or any other available region)

Deploy Azure Resources

azd up

Running Locally

Change directory:

cd src

Create a Virtual Environment

uv (Recommended)

uv venv

Once you have created a virtual environment, you may activate it.

On Unix or MacOS, run:

source .venv/bin/activate

On Windows, run:

.venv\Scripts\activate

To deactivate the virtual environment, run:

deactivate

Tip

More information about virtual environments can be found here.

Install Dependencies

uv sync
playwright install --with-deps chromium

---

Note

Alternatively, here are some of the most popular Python package and project managers, if you have opted to not use uv.

Poetry

# Create a virtual environment
poetry shell

# Install dependencies
poetry install

Anaconda

# Create a virtual environment
conda create -n venv python=3.12 -y
conda activate venv

# Install dependencies
pip install -r requirements.txt

Update Configuration

If you used AZD to deploy the resources, simply run the code below:

azd env get-values > .env

Alternatively, copy .env.sample into .env.

Important

Magentic-One code uses code execution, you need to have Docker installed to run the examples if you use local execution.

Start the Application

streamlit run app.py

If your app is ready, you can (typically) browse http://localhost:8501 to see the app in action.

Resources

• Build your dream team with Autogen
• GenAI for SW developers: More Agents Is All You Need?