requirements.txt

tqdm >= 4.23.4
hyperopt >= 0.1.1
h5py >= 2.8.0
coverage >= 4.3.4
codecov >= 2.0.15
pytest >= 3.7.4
pytest-cov >= 2.4.0
flake8 == 7.0.0
flake8_docstrings == 1.7.0
pydocstyle == 2.1
openai == 1.33.0
datasets == 2.16.1
langchain==0.2.0
langchain-core==0.2.5
langchain-text-splitters==0.2.1
langchain-huggingface==0.0.3
langchain-openai==0.1.8
langsmith>=0.1.61
transformers
pandas
nltk == 3.8.1
sentencepiece==0.2.0
PyPDF2==3.0.1
html2text==2024.2.26
beautifulsoup4==4.12.3
faiss-cpu==1.8.0
umap-learn==0.5.5
sentence_transformers==3.0.0
threadpoolctl==3.5.0
PyMuPDF==1.24.5
hanziconv==0.3.2
datrie==0.8.2
xpinyin==0.7.6
python-pptx==0.6.23
pdfplumber==0.11.0
readability==0.3.1
html_text==0.6.2
python-docx==1.1.2
tortoise==0.1.1
python-magic==0.4.27
html_text==0.6.2
readability==0.3.1
PyMuPDF
hanziconv==0.3.2
PyPDF2
gradio
loguru
xgboost
bm25s
jieba
accelerate