Monitor the performance of OpenAI's GPT-4V model over time.

This repository offers a Python framework for a retrieval-augmented generation (RAG) pipeline using text and images from MHTML documents, leveraging Azure AI and OpenAI services. It includes ingestion and enrichment flows, a RAG with Vision pipeline, and evaluation tools.

Vision utilities for web interaction agents 👀

Control Any Computer Using LLMs

Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta

Video Voiceover with gpt-4o-mini

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

Mark web pages for use with vision-language models

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

[READ-ONLY] Describe images and generate alt tags for visually impaired users.

GPT-4V in Wonderland: LMMs as Smartphone Agents

[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions

Multi-Modal Multi-Embodied Hivemind-like Iteration of RTX-2

OCR application for converting handwritten equations into LaTeX code using OpenAI's GPT-4V API, with LaTeX renderer for editing and checking (Next.js, Typescript, OpenAI GPT-4V, KaTex, Vercel)

Vision-Assisted Camera Orientation

Discover the GPT-4o multimodal model at Microsoft Build 2024, now with text and image capabilities. My prototype enhances chats with real-time camera snapshots, powered by Flask, OpenCV, and Azure’s OpenAI Services. It’s interactive, visual, and simple to use. Give it a try!

中文医学多模态大模型 Large Chinese Language-and-Vision Assistant for BioMedicine

Draw your projects to life

The ultimate sketch to code app made using GPT4o serving 25k+ users. Choose your desired framework (React, Next, React Native, Flutter) for your app. It will instantly generate code and preview (sandbox) from a simple hand drawn sketch on paper captured from webcam

麻雀GPTs-API市场