requests beautifulsoup4 transformers torch huggingface_hub>=0.22.2 sentencepiece pymupdf nltk PyPDF2 tiktoken langchain-core langchain langchain-community chromadb openpyxl nltk pypdf spacy https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.0/en_core_web_sm-3.7.0-py3-none-any.whl sentence-transformers faiss-cpu scikit-learn feedparser pdfminer.six camelot-py[cv] pandas numpy opencv-python-headless llama-parse nest-asyncio llama-index llama-cpp-agent duckduckgo_search trafilatura googlesearch-python readability-lxml pydantic