spacy==3.7.2
jsonschema==4.20.0
scikit-learn==1.3.2
tqdm==4.66.1
nltk==3.8.1
pandas==2.1.4
docx2txt==0.8
python-dateutil==2.8.2
pdfminer.six==20221105
plac==1.4.2
datasets==2.16.0
