The HELMET Benchmark

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Quickly make and deploy full-stack apps with database, auth, styling, storage etc. figured out for you. Add all primitives you want.

Custom Selenium Chromedriver | Zero-Config | Passes ALL bot mitigation systems (like Distil / Imperva/ Datadadome / CloudFlare IUAM)

MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios

Tool to create a dataset of semantic segmentation on website screenshots from their DOM

Generate python documentation using LLMs

🏀 Visualization of NBA games from raw SportVU data logs

Visualization and analysis of NBA player tracking data

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024]

VideoX: a collection of video cross-modal models

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

Detectron2 Webserver (Faster-RCNN) implementation for Ubuntu 20.04. Real time object detection served over the internet.

The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data 🔥

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

A create-react-app template, written in TypeScript, configured for Gitpod (www.gitpod.io) to give you pre-built, ephemeral development environments in the cloud.

Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.

The LLM Evaluation Framework

CHAPI (Common Hierarchical Abstract Parser and Information Converter) streamlines code analysis by converting diverse language source code into a unified abstract model, simplifying cross-language …

Automated bot that identifies live sports arbitrage opportunities across FanDuel, DraftKings, and William Hill (Caesars).

Chat Markup Language conversation library

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Automate your browser with GPT-4

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…