A document processing system from the ground up to make a PDF document searchable character by character and perform editing in real-time. Implemented a system capable of processing millions of pages that had already processed several billion words.

This project has mainly 3 sections: Front-end, Back-end, and M. Once tags are predicted for a document, users can review the document and perform the editing and other operations on the text of the document.

Users can finish the redaction of the document and download the redacted document, along with reports of documents.