| Name | Version | Summary | date |
| aspose-total-net |
25.1.0 |
Aspose.Total for Python via .NET is a Document Processing python class library that allows developers to work with Microsoft Word®, Microsoft PowerPoint®, Microsoft Outlook®, OpenOffice®, & 3D file formats without needing Office Automation. |
2025-02-03 18:11:00 |
| kreuzberg |
1.2.0 |
A text extraction library supporting PDFs, images, office documents and more |
2025-02-02 14:24:02 |
| vision-parse |
0.1.13 |
Parse PDF documents into markdown formatted content using Vision LLMs |
2025-02-02 13:19:59 |
| filemac |
1.1.3 |
Open source Python CLI toolkit for conversion, manipulation, Analysis of files (All major file operations) |
2025-02-01 22:51:11 |
| fastmrz |
2.0.2 |
Extracts the Machine Readable Zone (MRZ) data from document images |
2025-02-01 20:02:03 |
| tikara |
0.1.5 |
The metadata and text content extractor for almost every file type. |
2025-01-26 23:33:40 |
| par-ocr |
0.2.0 |
Use AI vision to OCR PDF and image files to markdown. |
2025-01-26 23:17:10 |
| peslac |
0.1.4 |
A Python package for the Peslac API |
2025-01-25 06:54:20 |
| marker-pdf |
1.3.1 |
Convert PDF to markdown with high speed and accuracy. |
2025-01-24 18:13:43 |
| huaweicloudsdkocr |
3.1.133 |
OCR |
2025-01-23 08:12:35 |
| htrflow |
0.2.1 |
htrflow is developed at Riksarkivet's AI-lab as an open-source package to simplify HTR |
2025-01-22 12:10:00 |
| aimq |
0.1.0 |
A robust message queue processor for Supabase pgmq with AI-powered document processing capabilities |
2025-01-18 22:17:05 |
| sparrow-parse |
0.5.0 |
Sparrow Parse is a Python package (part of Sparrow) for parsing and extracting information from documents. |
2025-01-09 12:28:45 |
| autopc |
1.0.1 |
An image recognition framework running on a computer |
2025-01-08 07:42:22 |
| leadtools |
23.0.0.4 |
Powered by patented artificial intelligence and machine learning algorithms, LEADTOOLS is a collection of comprehensive toolkits to integrate recognition, document, medical, imaging, and multimedia technologies into desktop, server, tablet, web and mobile solutions. |
2025-01-02 19:30:22 |
| dedoc |
2.3.2 |
Extract content and logical tree structure from textual documents |
2024-12-25 10:05:04 |
| yomitoku |
0.6.0 |
Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language. |
2024-12-15 15:46:51 |
| rapid-undistorted |
1.0.1 |
table detection with onnx model |
2024-12-15 08:50:56 |
| atr-dan |
0.2.0rc12 |
Teklia DAN |
2024-12-12 11:25:30 |
| wired-table-rec |
1.1.9 |
Wired Table Recognition |
2024-12-12 07:14:59 |