PyPI page
Home page
Author:
None
Summary:
Vision-language OCR and multimodal document QA for images and PDFs.
Latest version:
0.2.6
Required dependencies:
aiofiles
|
asyncio
|
colpali-engine
|
openai
|
pdf2image
|
pillow
|
pydantic
|
pymupdf
|
rank-bm25
Downloads last day:
8
Downloads last week:
31
Downloads last month:
63