PyPI page
Home page
Author:
PDFStract Team
License:
MIT
Summary:
PDFStract - The Extraction and Chunking Layer in Your RAG Pipeline - Available as CLI - WEBUI - API
Latest version:
1.1.1
Required dependencies:
aiofiles
|
chonkie
|
click
|
fastapi
|
jinja2
|
loguru
|
markitdown
|
paddlepaddle
|
pillow
|
pip
|
pymupdf4llm
|
pypdf2
|
python-magic
|
python-multipart
|
rich
|
tomli
|
uvicorn
Optional dependencies:
addict
|
docling
|
easydict
|
gensim
|
langchain-google-genai
|
langchain-openai
|
langchain_ollama
|
marker-pdf
|
matplotlib
|
paddleocr
|
pdf2image
|
pdfstract
|
pytesseract
|
torch
|
transformers
|
unstructured
Downloads last day:
12
Downloads last week:
63
Downloads last month:
167