Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Features to implement before v.0.1.0 is released #6

Open
gianluccacolangelo opened this issue Jul 28, 2024 · 3 comments
Open

Features to implement before v.0.1.0 is released #6

gianluccacolangelo opened this issue Jul 28, 2024 · 3 comments

Comments

@gianluccacolangelo
Copy link
Owner

  • ID for highlights, so the system can check in Anki if there is already flashcards with that highlight, and then we can handle a situation like "No new highlights had been found".
  • English and spanish modes as variables for the prompt.
  • A module to retrieve wider contexts, to make possible connections. For example someone could give a .pdf with exams, or his .md from obsidian. This should filter first by semantic similarity with a tuned threshold, and then let the LLM evaluate if its pertinent to make the connection in the flashcard.
@gianluccacolangelo
Copy link
Owner Author

Point 2 has been implemented in commit f0913bb

@gianluccacolangelo
Copy link
Owner Author

Point 1 has been implemented in commit 00cfea6

@gianluccacolangelo
Copy link
Owner Author

Now what is left, is a module that is able to track if the files are renamed or changed in directories, to update anki, with ankiconnect api.

The bad news are we can't use inode for this, because each time we add an annotation to a pdf, a new pdf is replaced and consequently a new inode is created.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant