Flashy

Inspiration

Our inspiration came from our recent midterm exams where we would manually make flashcards to study for our exams.

What it does

The program takes a pdf file and then turns the pdf file into simplified virtual flashcards. That PDF file could be your teachers slideshow, or even your own notes.

How we built it

The program converts the pdf to text using the API PyPDF2. Then the program utilizes an OpenAI API to generate flashcards based off of the notes or slideshow from a lecture. We the use the framework PyQt5 to show the interface of the program, and we connected the buttons and textboxes to the backend.

Challenges we ran into

Time constraints, we initially wanted to also be able to take other types of files but we didn't have enough time to implement that. Another challenge we ran into was an issue with dependencies, we had to dedicate time to install all of the tools we needed for the program.

Accomplishments that we're proud of

The program has a GUI and is not just a CLI. Despite no experience with APIs we were able to quickly learn how to use the OpenAI API and use it in such a short time span.

What we learned

Learned how to use PyQt5, and how to use images in it. We learned how to use the OpenAI API, and we learned how to use a PDF to text converting API called PyPDF2.

What's next for Flashy

Next we'd implement a way to save our flashcards using file IO, and we'd allow for a conversion of videos to flashcards, using a speech to text API and an API for separating the video from the audio.