beautifulsoup4 bs4 docx2txt fake-useragent==0.1.11 Faker==12.0.0 pandas==1.2.3 PyPDF2 regex==2021.8.28 requests requests-file==1.5.1 requests-oauthlib torch transformers validators nltk==3.7 sentence-transformers spacy spacy_streamlit en_core_web_lg @ https://huggingface.co/spacy/en_core_web_lg/resolve/main/en_core_web_lg-any-py3-none-any.whl