PyPI page
Author:
Hansen
License:
MIT
Summary:
Go beyond simple parsing. Our SDK and CLI empower you to build intelligent applications by converting diverse document formats (PDF, DOCX, HTML, and others) into a unified structure. Critically, we leverage multimodal LLMs to enrich the parsed content, adding layers of meaning and context essential for maximizing the performance of your generative AI pipelines.
Latest version:
0.1.0
Required dependencies:
auto-mix-prep
|
docx2pdf
|
httpx
|
huggingface-hub
|
numpy
|
opencv-python
|
pdf2image
|
pydantic
|
pytesseract
|
requests
|
tqdm
|
ultralytics
Downloads last day:
0
Downloads last week:
1
Downloads last month:
1
7-day smoothing