> For the complete documentation index, see [llms.txt](https://ds-organization-11.gitbook.io/maccaw/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ds-organization-11.gitbook.io/maccaw/tutorial/ai-recycle-bin-assistant/step-by-step.md).

# Step by Step

#### Step-by-Step Guide

**1. Setup Environment Variables**

The Maccaw agent needs an API key and base URL to communicate with OpenAI's LLMs. Create a `.env` file in your project directory and add the following keys:

```bash
BASE_URL=https://api.openai.com/v1/engines [Optional]
API_KEY=your_openai_api_key
MODEL_NAME=gpt-3.5-turbo
```

> Replace `your_openai_api_key` with your actual OpenAI API key.

**Install Required Libraries**

Run the following commands to install the necessary libraries:

```bash
pip install maccaw pydantic winshell pywin32 python-dotenv
```

* `maccaw`: Allows integration with LLM-based agents.
* `pydantic`: For data validation.
* `winshell` and `pywin32`: For working with the Windows recycle bin.

#### Step 3: Import Required Libraries

Next, we'll import the required libraries. The `winshell` module allows us to interact with the recycle bin, and we’ll use `pydantic` to define the structure of the tool's inputs.

```python
import os
import winshell
from pydantic import BaseModel, Field
from typing import Optional, Type
from maccaw.maccaw import BaseTool
from win32com.client import Dispatch
```