NanoNets/docstrange

Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.

Owner: NanoNets (organization)
Stars: Stars: 1,585
Forks: Forks: 138
Language: Python
License: MIT
Created: 2025
Topics: image-to-markdownllmmarkdownocrpdf-to-markdownstructured-dataaidocument-parserdocument-parsingpdf-parser
Tier: Beta (700 to 1,999 ★) What this tier means

View on GitHub

More repos by NanoNets

All 6 repos by NanoNets

NanoNets/docextStars: 2,087PythonRC
NanoNets/nanonets-ocr-sample-pythonStars: 209PythonPrototype
NanoNets/RaspberryPi-ObjectDetection-TensorFlowStars: 174PythonPrototype
NanoNets/ocr-with-tesseractStars: 136Jupyter NotebookPrototype
NanoNets/ocr-pythonStars: 129Jupyter NotebookPrototype

Nearby in Python

All Python repos

OsciiArt/DeepAAStars: 1,585PythonBeta
evo-design/evoStars: 1,585PythonBeta
WeiboAI/VibeThinkerStars: 1,585PythonBeta