# Installation

[LiteLLM Proxy Server](https://docs.litellm.ai/docs/simple_proxy) is an open-source, self-hosted proxy server that offers an OpenAI-compatible API, enabling seamless interaction with multiple LLM providers like OpenAI, Azure, IBM WatsonX etc. It simplifies model integration, providing a unified interface for diverse AI backends.

This guide will walk you through integrating **LiteLLM Proxy Server** with **AG2**, ensuring efficient AI agent orchestration with minimal setup.

## Prerequisites

Before proceeding, ensure the following:

- **Docker** is installed. Refer to the [Docker installation guide](https://docs.docker.com/get-docker/)
- **(Optional)** Install **Postman** for easier API request testing.

## Installation

### Install AG2

**AG2** is a powerful framework designed to simplify AI agent orchestration.

To install `AG2`, simply run the following command:

```
pip install ag2[openai]
```

Tip

If you have been using `autogen` or `ag2`, all you need to do is upgrade it using:

```
pip install -U autogen[openai]
```

or

```
pip install -U ag2[openai]
```

as `autogen` and `ag2` are aliases for the same PyPI package.

### Install LiteLLM

LiteLLM runs as a lightweight proxy server, making it easier to integrate different LLM providers.

To install LiteLLM, download the latest Docker image:

```
docker pull ghcr.io/berriai/litellm:main-latest
```