Skip to content

Demo on using Weaviate's ref2vec vectorizer for building Recommendation Systems!

License

Notifications You must be signed in to change notification settings

weaviate/ref2vec-ecommerce-demo

Repository files navigation

Welcome to the Ref2Vec eCommerce Demo!

For more info, check out our blog post announcing ref2vec! - https://weaviate.io/blog/ref2vec-centroid

Step 1: Download the images!

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

Step 2: Install all the requirements:

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

Step 3: Now Initialize Weaviate by running these commands:

cd weaviate-init
docker-compose up -d
python3 create-schema.py
python3 upload-data.py

Step 4: Run the app

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

About

Demo on using Weaviate's ref2vec vectorizer for building Recommendation Systems!

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published