Metadata-Version: 2.4
Name: BigBoss
Version: 0.1.0
Summary: Local folder-to-memory chunking, summary extraction, embedding, and search CLI.
Author: Wenxi Wang
License: MIT
Project-URL: Homepage, https://github.com/your-name/BigBoss
Keywords: embedding,local-memory,chunking,ocr,search
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: scikit-learn
Requires-Dist: sentence-transformers
Requires-Dist: PyMuPDF
Requires-Dist: Pillow
Dynamic: license-file

# BigBoss

BigBoss is a local folder memory builder. It routes code/text/PDF/image files, chunks them, extracts important content, builds embeddings, and searches the closest memory chunk from one sentence.

## Install locally

```bash
pip install -e .
```

## Install build tools

```bash
pip install -U build twine
```

## Run

```bash
bigboss --folder "PATH_TO_YOUR_FOLDER" --chunk-size 500 --embed
```

## Search

```bash
bigboss-check --query "one sentence question" --top-k 5
```

## Build for PyPI

```bash
python -m build
```

## Upload to PyPI

```bash
python -m twine upload dist/*
```

## Notes

- PyPI project name: `BigBoss`
- Import/package folder: `bigboss`
- Output memory folder is created in the current terminal folder as `memory/`.
- OCR for scanned PDFs/images needs Tesseract installed or placed in a local `tesseract/` folder.
