| datasets<=3.2 | |
| numpy<2.0.0 | |
| scipy | |
| torch | |
| torchvision | |
| torchaudio | |
| tqdm | |
| transformers<=4.51.3 | |
| aisuite | |
| math_verify | |
| word2number | |
| accelerate | |
| rapidfuzz | |
| colorlog | |
| appdirs | |
| datasketch | |
| modelscope | |
| addict | |
| pytest | |
| rich | |
| docstring_parser | |
| pydantic | |
| nltk | |
| colorama | |
| # text2sql | |
| func_timeout | |
| sqlglot | |
| # general text | |
| fasttext-wheel | |
| kenlm | |
| langkit | |
| openai | |
| sentencepiece | |
| datasketch | |
| presidio_analyzer[transformers] | |
| presidio_anonymizer | |
| vendi-score==0.0.3 | |
| google-api-core | |
| google-api-python-client | |
| evaluate | |
| contractions | |
| symspellpy | |
| simhash | |
| # knowledge base cleaning | |
| chonkie | |
| trafilatura | |
| lxml_html_clean | |
| # dataflow agent | |
| cloudpickle | |
| fastapi | |
| httpx | |
| pandas | |
| psutil | |
| pyfiglet | |
| pyyaml | |
| requests | |
| termcolor | |
| uvicorn |