Skip to content

Recommends books by comparing the vector embeddings of their descriptions.

Notifications You must be signed in to change notification settings

kikis05/BookRecommender

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Current Functionalities:

  • Embeds book descriptions from Kaggle Dataset
  • Groups books vectors into hash buckets using locality sensitive hashing (with multiple universes)
  • Uses cosine similarity to get closest books descriptions to chosen book
  • Book search function with txt.ai

Future:

  • Comment code and make more legible
  • See if it is possible to iterate through only a few universes and get the same coverage of nearest neighbors

About

Recommends books by comparing the vector embeddings of their descriptions.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published