/squery

Lightning fast search implementation using Word2Vec and Smooth Inverse Frequency

Primary LanguageJupyter Notebook

Developing Contextual Search for an FMCG Catalogue

Using Word2Vec

  • The main.ipynb describes the implementation.
  • For production purposes, use main.py for training and saving weights.
  • The code for the web dashboard can be found in web.py.

Word2vec is a group of related models that are used to produce word embeddings. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic contexts of words. Read more about it here.

Team DataMinds

dataminds-01 dataminds-02 dataminds-03 dataminds-04 dataminds-05 dataminds-06 dataminds-07 dataminds-08 dataminds-09 dataminds-10 dataminds-11 dataminds-12