pytest
yapf==0.31.0
typing_extensions
pyyaml
jsonlines
json5
ijson
orjson
munch
zstandard
joblib
msgpack
python-ulid
pandas
numpy<2,>=1.19
scipy
boto3
minio
tiktoken
pyarrow
pypandoc
tqdm
alive_progress
pyahocorasick
openai>=1.47.1
aiohttp
tldextract
langdetect
nltk
spacy==3.8.0
