import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';

# Installation

## Create a virtual environment (optional)

When installing AutoGen locally, we recommend using a virtual environment for the installation. This will ensure that the dependencies for AutoGen are isolated from the rest of your system.

<Tabs>
  <TabItem value="venv" label="venv" default>

    Create and activate:

    ```bash
    python3 -m venv pyautogen
    source pyautogen/bin/activate
    ```

    To deactivate later, run:

    ```bash
    deactivate
    ```

  </TabItem>
  <TabItem value="conda" label="Conda">

    [Install Conda](https://docs.conda.io/projects/conda/en/stable/user-guide/install/index.html) if you have not already.


    Create and activate:

    ```bash
    conda create -n pyautogen python=3.10
    conda activate pyautogen
    ```

    To deactivate later, run:

    ```bash
    conda deactivate
    ```

  </TabItem>
  <TabItem value="poetry" label="Poetry">

    [Install Poetry](https://python-poetry.org/docs/#installation) if you have not already.

    Create and activate:
    ```bash
    poetry init
    poetry shell

    poetry add pyautogen
    ```

    To deactivate later, run:

    ```bash
    exit
    ```

  </TabItem>
</Tabs>

## Install AutoGen

AutoGen requires **Python version >= 3.8, < 3.13**. It can be installed from pip:

```bash
pip install pyautogen
```

:::info

`pyautogen<0.2` required `openai<1`. Starting from pyautogen v0.2, `openai>=1` is required.

:::

## Install Docker for Code Execution

We recommend using Docker for code execution.
To install Docker, follow the instructions for your operating system on the [Docker website](https://docs.docker.com/get-docker/).

A simple example of how to use Docker for code execution is shown below:

```python
from pathlib import Path
from autogen import UserProxyAgent
from autogen.coding import DockerCommandLineCodeExecutor

work_dir = Path("coding")
work_dir.mkdir(exist_ok=True)

with DockerCommandLineCodeExecutor(work_dir=work_dir) as code_executor:
    user_proxy = UserProxyAgent(
        name="user_proxy",
        code_execution_config={"executor": code_executor},
    )
```

To learn more about code executors, see the [code executors tutorial](/docs/tutorial/code-executors).

You might have seen a different way of defining the executors without creating the
executor object, please refer to FAQ for this [legacy code executor](/docs/FAQ#legacy-code-executor).