Skip to content

Latest commit

 

History

History

semanticsearch-transformers-wines

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Semantic search of wines with Weaviate

This folder contains code used for the Hackernoon article: "Semantic Search Queries Return More Informed Results".

This folder contains Wine review data, retrieved from Kaggle (from WineEnthusiast). The transformer model sentence-transformers/msmarco-distilroberta-base-v2 is connected to Weaviate as vectorization module (see docker-compose.yaml file).

How to use

  1. Start up Weaviate: docker-compose up -d. Once completed, Weaviate is running on http://localhost:8080.
  2. Install requirements: pip install -r requirements.txt
  3. Run python import.py to import 2500 wines to Weaviate.
  4. Navigate to console.semi.technology, connect to http://localhost:8080, navigate to the query module, and happy querying!