Metadata-Version: 2.3
Name: gyokusai
Version: 0.1.0
Summary: Add your description here
Requires-Dist: daft[openai,ray]>=0.7.16
Requires-Dist: fastertext>=0.1.1
Requires-Dist: ftfy>=6.3.1
Requires-Dist: gigatoken>=0.10.0
Requires-Dist: google-re2>=1.1.20251105
Requires-Dist: kernels<0.15
Requires-Dist: lxml>=6.1.1
Requires-Dist: magic-html>=0.1.8
Requires-Dist: orjson>=3.10,<4
Requires-Dist: presidio-analyzer>=2.2.364
Requires-Dist: presidio-anonymizer>=2.2.364
Requires-Dist: py7zr>=1.1.3
Requires-Dist: resiliparse>=1.0.8
Requires-Dist: sentence-transformers>=5.6.0
Requires-Dist: text-dedup>=0.4.1
Requires-Dist: trafilatura>=2.1.0
Requires-Dist: usearch>=2.26.0
Requires-Dist: vllm>=0.26.0
Requires-Python: >=3.12
Description-Content-Type: text/markdown

```bash
ruff check --select I --fix . && ruff format .
```
```bibtex
@software{shippole2026llmdata,
  title        = {: A Python Library for },
  author       = {Shippole, Enrico and Hu, Andrew and Li, Owen and Huang, Thomas and Jitsev, Jenia},
  year         = {2026},
  url          = {https://github.com/teraflop-ai/llm-data},
  version      = {1.0.0},
  note         = {Python package available on PyPI at \url{https://pypi.org/project//}}
}
```
```bibtex
@misc{paster2023openwebmath,
    title={OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text},
    author={Keiran Paster and Marco Dos Santos and Zhangir Azerbayev and Jimmy Ba},
    year={2023},
    eprint={2310.06786},
    archivePrefix={arXiv},
    primaryClass={cs.AI}
}
```