---
title: Style Master
emoji: 😻
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 4.44.1
app_file: app.py
pinned: false
license: unlicense
---

This project uses OpenAI large language models (LLMs) to create the recommendation engine for an e-commerce clothing store.

## Running Locally

1. Install packages

```sh
make install
```

2. Set up your environment variables

```sh
cp .env.example .env
```

- Update the environment variables in `.env`, e.g., `OPENAI_API_KEY`, according to your needs.

3. (optional) Process garment images

This step is needed only when you have changed the garment images and/or manifest info.

```sh
make process
```

- if `GARMENTS_FILE_PATH` doesn't exist, the script will call GPT-4 Vision API to generate metadata for garment images stored in `GARMENT_MANIFEST_FILE_PATH` folder. A new file `GARMENTS_FILE_PATH` will be created.

- if `GARMENTS_FILE_PATH` already exists, the script will NOT call GPT-4 Vision API. The file `GARMENTS_FILE_PATH` will be updated with the latest data from `GARMENT_MANIFEST_FILE_PATH` file.

4. Run automated test cases

```sh
make test
```

5. Run Gradio web app

```sh
make start
```