data-prep-toolkit==0.2.1.dev2
argparse
boto3>=1.34.69
bs4==0.0.2
clamd==1.0.2
docling[ocr]==1.1.2
duckdb==0.10.1
fasttext==0.9.2
filetype >=1.2.0, <2.0.0
huggingface-hub >= 0.21.4, <1.0.0
langcodes==3.3.0
mmh3==4.1.0
numpy==1.26.4
pandas
parameterized
pyarrow==16.1.0
python-dateutil>=2.8.2
pytz>=2020.1
quackling==0.1.0
scancode-toolkit==32.1.0 ; platform_system != 'Darwin'
sentence-transformers==3.0.1
transformers==4.38.2
tzdata>=2022.7
xxhash==3.4.1
