Metadata-Version: 2.4
Name: convoviz
Version: 0.3.1
Summary: Get analytics and visualizations on your ChatGPT data!
Keywords: markdown,chatgpt,openai,visualization,analytics,json,export,data-analysis,obsidian
Author: Mohamed Cheikh Sidiya
Author-email: Mohamed Cheikh Sidiya <mohamedcheikhsidiya77@gmail.com>
License-Expression: MIT
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: orjson>=3.11.5
Requires-Dist: pydantic>=2.12.5
Requires-Dist: pydantic-settings>=2.7.0
Requires-Dist: questionary>=2.1.1
Requires-Dist: rich>=14.2.0
Requires-Dist: tqdm>=4.67.1
Requires-Dist: typer>=0.21.0
Requires-Dist: nltk>=3.9.2 ; extra == 'viz'
Requires-Dist: wordcloud>=1.9.5 ; extra == 'viz'
Requires-Python: >=3.12
Project-URL: Repository, https://github.com/mohamed-chs/chatgpt-history-export-to-md
Provides-Extra: viz
Description-Content-Type: text/markdown

# Convoviz 📊: Visualize your entire ChatGPT data

Convert your ChatGPT history into well-formatted Markdown files. Additionally, visualize your data with word clouds 🔡☁️, view your prompt history graphs 📈, and access all your custom instructions 🤖 in a single location.

![GitHub last commit](https://img.shields.io/github/last-commit/mohamed-chs/chatgpt-history-export-to-md)
![GitHub issues](https://img.shields.io/github/issues/mohamed-chs/chatgpt-history-export-to-md)

## Features

- **YAML Headers**: Optional and included by default.
- **Inline Images**: Media attachments rendered directly in Markdown.
- **Data Visualizations**: Word clouds, graphs, and more.

See examples [here](demo).

## How to Use 📖

### 1. Export Your ChatGPT Data 🗂

- Sign in at [chat.openai.com](https://chat.openai.com).
- Navigate: Profile Name (bottom left) -> **Settings** -> **Data controls** -> **Export** -> **Confirm export**.
- Await email from OpenAI and download the `.zip` file.

### 2. Install the tool 🛠

With uv ([astral-sh/uv](https://github.com/astral-sh/uv?tab=readme-ov-file#highlights)):

```bash
uv tool install convoviz[viz]
```

or pipx:
```bash
pipx install convoviz[viz]
```

The `[viz]` extra includes graphs and word clouds. If you only need markdown conversion, you can skip it for a faster install (`uv tool install convoviz`).

### 3. Run the tool 🏃‍♂️

Simply run the command and follow the prompts:

```bash
convoviz
```

#### Command Line Arguments

You can provide arguments directly to skip the prompts:

```bash
convoviz --input path/to/your/export.zip --output path/to/output/folder
```

##### Selective Output Generation

By default, Convoviz generates all outputs (Markdown files, graphs, and word clouds). You can select specific outputs using the `--outputs` flag:

```bash
# Generate only Markdown files (fastest)
convoviz --input export.zip --outputs markdown

# Generate Markdown and graphs (no word clouds)
convoviz --input export.zip --outputs markdown --outputs graphs

# Generate all outputs (default behavior)
convoviz --input export.zip --outputs markdown --outputs graphs --outputs wordclouds
```

In interactive mode, you'll be prompted to select which outputs to generate.

##### Other Notes

- `--zip` / `-z` is kept as an alias for `--input` for convenience.
- You can force non-interactive mode with `--no-interactive`.
- Use `--flat` to put all Markdown files in a single folder instead of organizing by date.

For more options, run:

```bash
convoviz --help
```

### 4. Check the Output 🎉

And that's it! After running the script, head over to the output folder to see your neatly formatted Markdown files and visualizations.

![wordcloud example](demo/wordcloud-example.png)

## Share Your Feedback! 💌

I hope you find this tool useful. I'm continuously looking to improve on this, but I need your help for that.

Whether you're a tech wizard or you're new to all this, I'd love to hear about your journey with the tool. Found a quirk? Have a suggestion? Or just want to send some good vibes? I'm all ears! (see [issues](https://github.com/mohamed-chs/chatgpt-history-export-to-md/issues))

And if you've had a great experience, consider giving the project a star ⭐. It keeps me motivated and helps others discover it!

## Notes

This is just a small thing I coded to help me see my convos in beautiful markdown. It was originally built with [Obsidian](https://obsidian.md/) (my go-to note-taking app) in mind, but the default output is standard Markdown.

I wasn't a fan of the clunky, and sometimes paid, browser extensions.

It was also a great opportunity to learn more about Python and type annotations. I had mypy, pyright, and ruff all on strict mode, 'twas fun.

It should(?) also work as library, so you can import and use the models and functions. I need to add more documentation for that tho. Feel free to reach out if you need help.

### Offline / reproducible runs

Word clouds use NLTK stopwords. If you're offline and NLTK data isn't installed yet, pre-download it:

```bash
python -c "import nltk; nltk.download('stopwords')"
```

### Bookmarklet

There's also a JavaScript bookmarklet flow under `js/` (experimental) for exporting additional conversation data outside the official ZIP export.
