A set of examples showing how to use the OpenAI vision API to run inference on images, video files and webcam streams.

# create and activate virtual environment
python3 -m venv venv
source venv/bin/activate

# install dependencies
pip install -r requirements.txt

Experimenting with the OpenAI API requires an API key. You can get one here.

Experiment	Description	Code	HF Space
WebcamGPT	chat with video stream
Grounding DINO + GPT-4V	label images with Grounding DINO and GPT-4V
GPT-4V Classification	classify images with GPT-4V
GPT-4V vs. CLIP	label images with Grounding DINO and Autodistill
Hot Dog or not Hot Dog	simple image classification

I would love your help in making this repository even better! Whether you want to correct a typo, add some new experiment, or if you have any suggestions for improvement, feel free to open an issue or pull request.