Metadata-Version: 2.4
Name: paperflux
Version: 3.4.20260528
Summary: AI-powered PDF annotation for research papers
Author: PaperFlux contributors
License-Expression: MIT
Project-URL: Documentation, https://ehabets.github.io/PaperFlux/
Project-URL: Homepage, https://github.com/ehabets/PaperFlux
Project-URL: Issues, https://github.com/ehabets/PaperFlux/issues
Project-URL: Source, https://github.com/ehabets/PaperFlux
Keywords: annotation,openai,papers,pdf,research
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: openai>=2.38.0
Requires-Dist: typer>=0.15.4
Requires-Dist: PyMuPDF>=1.24
Requires-Dist: pyyaml>=6.0
Requires-Dist: pydantic>=2.7
Requires-Dist: rich>=13.7
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: jinja2>=3.1
Provides-Extra: dev
Requires-Dist: pytest>=8.2; extra == "dev"
Dynamic: license-file

# PaperFlux

AI-powered PDF annotation for research papers. PaperFlux extracts exact quotations, organizes them by category (contributions, limitations, claims, evidence), and annotates your PDFs with precise highlights.

## Quick Start

### 1. Installation

Install the latest release from PyPI:

```bash
python -m pip install paperflux
```

For local development from a cloned repository:

```bash
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
```

### 2. Set API Key

```bash
export PAPERFLUX_OPENAI_API_KEY="sk-your-key"
```

### 3. Run

```bash
paperflux init
paperflux --config config.yaml path/to/paper.pdf
```

## Features

- Batch processing: `*.pdf`
- Three detail levels (low/medium/high)
- RAG-based extraction with exact quotes
- Color-coded highlights by category
- Markdown summary with sticky note
- Quote-match report with matched/skipped counts and scores
- Layout-aware quote matching across column, table, figure, and caption interruptions
- Stage-level CLI progress during extraction and annotation
- Configurable prompts and colors

## Documentation

For detailed setup, configuration options, and advanced usage, see the [full documentation](https://ehabets.github.io/PaperFlux/).

## Contributing

Contributions welcome! Fork the repo, create a feature branch, and open a PR.

## License

See [LICENSE](LICENSE) for details.
