A tool that can mask words that match regular expression, keywords or PII (Personally Identifiable Information) in an image file.
-
Updated
May 23, 2024 - Python
A tool that can mask words that match regular expression, keywords or PII (Personally Identifiable Information) in an image file.
AWS tutorial code.
🔍 Data pipeline for crawling PDFs from the Web and transforming their contents into structured data using AWS textract. Built with AWS CDK + TypeScript
Demo for AWS Textextract and Bedrock
To extract information from an damaged image using AWS textract and Azure form recognizer (OCR) ✨💥
A conversational document bot Windows Forms desktop application that allows users to upload PDF or Word files and ask questions about their content, with the bot keeping track of the conversation history and providing contextual responses based on the whole conversation.
An algorithm developed for counting words from documents in Python using pandas and textract. REGex pattern is tweaked to identify Latin characters all together (such as enzyme, protein names)
List all unique citations in your document
Docu.ai: Document Analysis POC for Fintech Company 📈📊
This is my NLP project on Resume Classification in this i have performed EDA , data cleaning, Model building on various models, model evaluation and model deployment
Generative AI Multi-Cloud application
Extract named entities from data in files of various formats.
Add a description, image, and links to the textract topic page so that developers can more easily learn about it.
To associate your repository with the textract topic, visit your repo's landing page and select "manage topics."