Skip to content
This repository has been archived by the owner on Dec 5, 2024. It is now read-only.

Use AI (fastText's multilingual word vectors) to search through your anki notes.

License

Notifications You must be signed in to change notification settings

thiswillbeyourgithub/Anki-Semantic-Search

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This project has been abandonned for a while. but I made a way better tool that allows directly asking questions to your anki database: wdoc

Anki SemSearch: do AI powered semantic search on your anki collection(s)

Use AI (fastText's multilingual word vectors) to search through your anki notes.

This is still a work in progress!

FAQ

  • What is it and how does it work?
  • Why should I use this?
  • This looks awesome! Are you working on other things like that? Yes and thank you! Another project of mine uses AI to reduce your daily workload on anki : I call it AnnA (Anki neuronal Appendix)

Usage

How to

tested on python3.9

  • pip install -r requirements.txt
  • python ./__init__.py --profiles ["Main", "Old"] --query="path taken by Nile river"

TODO

  • investigate using Faiss to speed up the search but orders of magnitude
  • use joblib caching instead of diy solutions
  • prettier results
  • shortcut to open in anki browser
  • remove warnings from ankipandas and pandas
  • replace acronyms
  • add requirements file
  • add argument to load other fastText models
  • add argument to ignore suspended cards or not
  • only vectorize words deemed important according to keyword extraction techniques from TFIDF

About

Use AI (fastText's multilingual word vectors) to search through your anki notes.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages