For more info, check out our blog post announcing ref2vec! - https://weaviate.io/blog/ref2vec-centroid
Download base64_images for upload - https://drive.google.com/file/d/1TDohvh6vyC6Ugd2NlrfhkAvwPfpjnBg3/view?usp=sharing
Put this folder in weaviate-init
Download images for showing the images locally - https://drive.google.com/file/d/1Vp0tg_6_qb1sezf-c-S1lHbmxy5EZ-de/view?usp=sharing
Put this folder in static
Use the requirements.txt
file to install all packages as follows:
python -m pip install -r requirements.txt
Optionally, you can accomplish this by creating a seperate conda environment:
conda create -n ref2vec python=3.9
conda activate ref2vec
python -m pip install -r requirements.txt
cd weaviate-init
docker-compose up -d
python3 create-schema.py
python3 upload-data.py
Now you are all set!
Navigate out of the weaviate-init
folder like this and start the FastAPI app!
cd ..
uvicorn main:app --reload
The app is now running on localhost:8000