#计算机科学#A Unified Toolkit for Deep Learning Based Document Image Analysis
#自然语言处理#Novalad offers a unified, centralized platform enabling organizations to extract meaningful data and perform advanced processing at high speed.
pdfDet aims to simplify PDF layout detect tasks for users.
Extracting structured text from GI Bill index cards for JDoc 2023 paper
#大语言模型#A lightweight Python library for metadata-rich document chunking in Retrieval-Augmented Generation (RAG) workflows. It leverages Azure AI Document Intelligence to enhance chunking by retaining hierarc...
Layout Parser notebook Implementation & Re-trained model for Image detection and extraction
Yolo & Layout Parser & Detectron2