Metadata-Version: 2.1
Name: chunkit
Version: 0.1.5
Summary: Convert URLs and files into LLM-friendly markdown chunks
Home-page: https://github.com/hypergrok/chunkit
Author: hypergrok
Author-email: 173556723+hypergrok@users.noreply.github.com
Project-URL: Source Code, https://github.com/hypergrok/chunkit
Description-Content-Type: text/markdown
License-File: LICENSE

<p align="center">
  <img src="https://raw.githubusercontent.com/hypergrok/chunkit/main/chn.png" alt="chunkit" width="200"/>
</p>

<div align="center">
  <a href="https://badge.fury.io/py/chunkit"><img src="https://badge.fury.io/py/chunkit.svg" alt="PyPI version" /></a>
  <a href="https://pepy.tech/project/chunkit"><img src="https://pepy.tech/badge/chunkit" alt="Downloads" /></a>
  <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT" /></a>
</div>

### Turn URLs into LLM-friendly markdown chunks

chunkit transforms URLs into markdown chunks which can be used for RAG/LLM applications.

### Installation

Install chunkit using pip:

```bash
pip install chunkit
```

Start chunking:

```python
from chunkit import Chunker

# Initialize the Chunker with your API key
chunker = Chunker(api_key='your_api_key_here')

# Define URLs to process
urls = ["https://en.wikipedia.org/wiki/Chunking",
        "https://calibre-ebook.com/downloads/demos/demo.docx"]

# Process the URLs into markdown chunks
chunkified_urls = chunker.process(urls)

# Output the resulting chunks
for url in chunkified_urls:
    for chunk in url['chunks']:
        print(chunk)
```

### Get API Key

1. Go to [app.chunkit.dev](https://app.chunkit.dev) and log in.
2. Navigate to Deploy API section.
3. Generate a new API key.

You can also test chunking directly on the website.

### Supported files

Handles HTML, PDF, CSV, JSON, YAML, MD, DOCX.

### License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

### Contact

For questions or support, please open an issue.
