AI Agent Skills

ReadingBank: A Benchmark Dataset for Reading Order Detection

Create, polish, and quality-check editable undergraduate or graduate thesis defense PowerPoint decks from a local thesis PDF/LaTeX project and an existing PPTX template.…

Using LlamaIndex, Redis, and OpenAI to chat with PDF documents. Supplementary material for blog post on Microsoft Developer Blog

Download the actual PDF binary from bot-gated sites (taxpolicycenter.org, urban.org, SSRN-hosted mirrors, think-tank/publisher sites) via the Wayback Machine id_ URL for…

Bank credit card deep layout analysis, fields extraction and recognition/OCR (ScanToPay) using deep learning

Official Implementation of Web-based Visual Corpus Builder (Webvicob), ICDAR 2023

A Webapp that uses Retrieval Augmented Generation (RAG) and Large Language Models to interact with a PDF directly in the browser.

mehmetba/pdf-analyze-streamlit is a high-star GitHub project relevant to AI agent workflows.

A Genshin Impact artifact rater sticking upon artifacts inside the game window. 刻晴办公桌 | 原神 | 圣遗物评分。集成在游戏窗口之上的原神圣遗物导出、评分工具，无需游戏内外来回切换对比，游戏中快速计算与查阅结果。

keras复现场景文本检测网络CPTN: 《Detecting Text in Natural Image with Connectionist Text Proposal Network》；欢迎试用，关注，并反馈问题...

PoseOSC + FaceOSC + HandOSC + OcrOSC + CatOSC + DogOSC

Javascript demo of docTR, powered by TensorFlowJS

SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)

This is a highly separated deployment project based on Deepstream , including the full range of Yolo and continuously expanding deployment projects such as Ocr.

Chat with PDF lets you ask questions to PDF documents. Built and deployed with NuxtHub, and powered by Cloudflare Workers AI and Vectorize.

Simple app to extract text from pictures using Tesseract