bs4 chromadb gradio langchain langchain_community openai pymongo numpy python-dotenv tiktoken yt_dlp text_generation transformers sentence-transformers mdtex2html pypinyin socksio tqdm colorama Pygments llama_index markdown markdown2 scikit-learn nltk pyspellchecker reportlab PyPDF2 python-Levenshtein fuzzywuzzy python-docx python-pptx pypdf PyMuPDF langchain-huggingface