/dream-team

This repo helps you to build a team of AI agents with Autogen

Primary LanguageJupyter NotebookMIT LicenseMIT

PRs Welcome LinkedIn

Build your dream team with Autogen

This repository leverages Microsoft Autogen 0.4, Azure OpenAI and integrates it with Streamlit, to build an end to end multi agents application, this repo makes it easy to build test and deploy an advanced multi agent framwork, based on Magentic One

Architecture

🎉 December 3, 2024: The repo now support one click deployment with Azure Developer CLI, if you would like to run it with the full process localy you can check v0.21

🎉 November 18, 2024: we are porting this repo to Autogen 0.4, A new event driven, asynchronous architecture for AutoGen and Magentic One

Prerequisites:

  1. Install Azure Developer CLI.
  2. Ensure you have access to an Azure subscription
  3. Docker - Follow the official Docker installation instructions
  4. Python version >= 3.8, < 3.13

Step by Step Deployment

1. Clone the repository

git clone https://github.com/yanivvak/dream-team.git  

2. Login to your Azure account

azd auth login

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

3. Deploy Azure Resources and the app

azd up

Working localy

cd src 

Set up a virtual environment (Preferred)

python -m venv dream

Once you’ve created a virtual environment, you may activate it.

On Windows, run:

dream\Scripts\activate

On Unix or MacOS, run:

source dream/bin/activate

To deactivate :

deactivate

More information about virtual environments can be found here

Install dependencies

pip install -r requirements.txt
git clone --depth 1 --branch v0.4.0.dev8 https://github.com/microsoft/autogen.git
cd autogen/python/packages/autogen-magentic-one
pip install -e .
playwright install --with-deps chromium

Update configuration

  • If you used AZD to deploy the resources just run azd env get-values > .env in the src directory
  • Alternatively, copy .env.sample (under src) into .env

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

cd ../../../..
cd src

Run

streamlit run app.py

Learn

Check these resources:

  1. Bloogpost - Build your dream team with Autogen
  2. Webinar - More agents is all you need