yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-12-30 00:30:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md (#4205)

Browse Source 
* Update README.md

Should it be "Azure openAI service" ?

* Update README.md with links

---------

Co-authored-by: Hussein Mozannar <hssein.mzannar@gmail.com>
Co-authored-by: Hussein Mozannar <hmozannar@microsoft.com>
This commit is contained in:
Thomas Lin 2024-11-15 13:37:20 +08:00 committed by GitHub
parent 8a4c928efa
commit 88229513e5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 36 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
python/packages/autogen-magentic-one/README.md
View File

@ -17,6 +17,8 @@
We are introducing Magentic-One, our new generalist multi-agent system for solving open-ended web and file-based tasks across a variety of domains. Magentic-One represents a significant step towards developing agents that can complete tasks that people encounter in their work and personal lives.
Find additional information about Magentic-one in our [blog post](https://aka.ms/magentic-one-blog) and [technical report](https://arxiv.org/abs/2411.04468).
![](./imgs/autogen-magentic-one-example.png)
> _Example_: The figure above illustrates Magentic-One mutli-agent team completing a complex task from the GAIA benchmark. Magentic-One's Orchestrator agent creates a plan, delegates tasks to other agents, and tracks progress towards the goal, dynamically revising the plan as needed. The Orchestrator can delegate tasks to a FileSurfer agent to read and handle files, a WebSurfer agent to operate a web browser, or a Coder or Computer Terminal agent to write or execute code, respectively.
@ -56,11 +58,20 @@ You can install the Magentic-One package and then run the example code to see ho
1. Clone the code and install the package:
```bash
git clone https://github.com/microsoft/autogen.git
cd autogen/python/packages/autogen-magentic-one
pip install -e .
```
The easiest way to install is with the [uv package installer](https://docs.astral.sh/uv/getting-started/installation/) which you need to install separately, however, this is not necessary.
Clone repo, use uv to setup and activate virtual environment:
```bash
git clone https://github.com/microsoft/autogen.git
cd autogen/python
uv sync --all-extras
source .venv/bin/activate
```
Install magentic-one from source:
```bash
cd packages/autogen-magentic-one
pip install -e .
```
The following instructions are for running the example code:
@ -82,13 +93,13 @@ playwright install --with-deps chromium
```bash
# Specify logs directory
python examples/example.py --logs_dir ./my_logs
python examples/example.py --logs_dir ./logs
# Enable human-in-the-loop mode
python examples/example.py --logs_dir ./my_logs --hil_mode
python examples/example.py --logs_dir ./logs --hil_mode
# Save screenshots of browser
python examples/example.py --logs_dir ./my_logs --save_screenshots
python examples/example.py --logs_dir ./logs --save_screenshots
```
Arguments:
@ -98,7 +109,7 @@ playwright install --with-deps chromium
- save_screenshots: (Optional) Save screenshots of browser (default: disabled)
6. [Preview] We have a preview API for Magentic-One.
You can use the `MagenticOneHelper` class to interact with the system. See the [interface README](interface/README.md) for more details.
You can use the `MagenticOneHelper` class to interact with the system and stream logs. See the [interface README](interface/README.md) for more details.
## Environment Configuration for Chat Completion Client
@ -107,9 +118,9 @@ This guide outlines how to configure your environment to use the `create_complet
Currently, Magentic-One only supports OpenAI's GPT-4o as the underlying LLM.
### Azure with Active Directory
### Azure OpenAI service
To configure for Azure with Active Directory, set the following environment variables:
To configure for Azure OpenAI service, set the following environment variables:
- `CHAT_COMPLETION_PROVIDER='azure'`
- `CHAT_COMPLETION_KWARGS_JSON` with the following JSON structure:
@ -151,3 +162,17 @@ You can set it using:
```bash
export BING_API_KEY=xxxxxxx
```
## Citation
```
@misc{fourney2024magenticonegeneralistmultiagentsolving,
title={Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks},
author={Adam Fourney and Gagan Bansal and Hussein Mozannar and Cheng Tan and Eduardo Salinas and Erkang and Zhu and Friederike Niedtner and Grace Proebsting and Griffin Bassman and Jack Gerrits and Jacob Alber and Peter Chang and Ricky Loynd and Robert West and Victor Dibia and Ahmed Awadallah and Ece Kamar and Rafah Hosn and Saleema Amershi},
year={2024},
eprint={2411.04468},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2411.04468},
}
```