sentence-transformers recently added support for the OpenAI CLIP model. This model embeds text and images into the same space, enabling image similarity search. txtai can directly utilize these models.
txtai and all dependencies.
pip install git+https://github.com/neuml/txtai streamlit torchvision # Get test data wget -N https://github.com/neuml/txtai/releases/download/v3.5.0/tests.tar.gz tar -xvzf tests.tar.gz # Get application script wget https://raw.githubusercontent.com/neuml/txtai/master/examples/images.py
Start the application and search. The application takes a single command line argument to a directory of images. Run it against your own images and explore the results!
streamlit run images.py txtai/