Skip to content

johngthecreator/books-books-books

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 

Repository files navigation

Books Books Books

How it came to be

This is a little NLP project I cooked up to help me find books to read based off of a query. I used the mixedbread-ai/mxbai-embed-xsmall-v1 to vectorize descriptions of some book from the must read list on Goodreads.

Then I put them into a sqlite file using sqlite-vec to turn the sqlite file into a vector db. Then I set up Hono.js as lightweight backend server that runs a similarity search based on the query and the entries in the vector db.

I also attempted to structure the project based off of the local-first architecture by using Transformers.js to run the mixedbread model and generate embeddings on the client then passing it through.

The project isn't complete and I've dockerized the backend but there is still more work needing to be done to improve security and resilience.

Tech Used

Common Tech

  • Docker
  • React
  • TypeScript
  • TailwindCSS
  • Vite

To-Do

  • Set up proper cors restrictions
  • Deploy the project (backend in a Container Registry and frontend on cloudflare pages.)
  • Figure out more features

About

Search for your next read with word embeddings

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published