search

SVJLucas / Scanipy

Scanipy stands for "scan it with Python"—it's your smart Python library for scanning and parsing complex PDF files like books, reports, articles, and academic papers. Utilizing cutting-edge Deep Learning algorithms, Scanipy transforms your PDFs into a treasure trove of extractable information: tables, images, equations, and text.
MIT License
19 stars 1 forks source link

What's he like after he runs？ #2

Open Kakichoco1 opened 1 year ago

Kakichoco1 commented 1 year ago

Can this present transformed data like mathpix or nougat, or is it just a tool to extract structured information? I have not yet deployed because there are many requestment, if you see the trouble answer, thank you!

SVJLucas commented 1 year ago

Hello, Kakichoco1,

The primary objective of our project is to extract data from non-structured PDFs and offer it in a usable format. The unique aspect of our approach is its flexibility: users can choose how they want the data to be extracted. Whether you're interested in transformed data, similar to what Nougat provides, or you prefer structured data broken down into individual blocks of information within the PDF, our model is designed to accommodate both.

Moreover, we're working on options to output this data in various formats, including Markdown, depending on user preferences. Importantly, we aim to achieve all of this without the need for running resource-intensive transformers.

Please be advised that the code is still in the development phase and is not yet fully functional. However, we are committed to making it operational by next week.

Thank you for your interest in our project!