PyPI page
Home page
Author:
Scienceverse
Summary:
Scientific paper extraction to structured JSON: metadata, text, references, tables, figures, and equations from PDF, DOCX, JATS XML, HTML, and ePub.
Latest version:
0.7.3
Required dependencies:
anthropic
|
beautifulsoup4
|
google-genai
|
html5lib
|
httpx
|
huggingface-hub
|
instructor
|
joblib
|
jsonref
|
litserve
|
onnxruntime
|
pandas
|
pillow
|
pyarrow
|
pydantic
|
pydantic-settings
|
pypdfium2
|
python-docx
|
python-dotenv
|
python-magic
|
python-magic-bin
|
python-multipart
|
questionary
|
rapidfuzz
|
rich
|
scikit-learn
|
tenacity
|
tokenizers
|
uvicorn
|
wordfreq
|
wtpsplit-lite
Optional dependencies:
anthropic
|
gradio
|
mcp
|
numind
|
onnxruntime-gpu
|
openai
|
opencv-python-headless
|
pytorch-crf
|
redis
|
sentencepiece
|
torch
|
torchvision
|
transformers
|
vllm
|
vllm-mlx
Downloads last day:
113
Downloads last week:
1,220
Downloads last month:
1,116
7-day smoothing