Inspiration
Flashcards have always been a great way to study for upcoming tests. But they can be a pain to create, manually making each card on paper or on a website like Quizlet. We decided to develop a solution by utilizing generative AI that processes your textbook and creates flashcards for you.
What it does
Our website allows users to upload a pdf of their textbook, and then choose either the entire textbook or certain page numbers for the AI model to create flashcards for. When the user clicks generate, the page navigates to a list of all the flashcards, and the user can click through them, save them, or export them.
How we built it
We built our website using Flask for the backend and React for the frontend.
Challenges we ran into
One challenge we ran into was training the model to output a satisfiable definition given a term. Since many of the datasets we used were more geared toward summarization, we had to finetune the model hyperparameters much more than expected.
Accomplishments that we're proud of
We are proud that we built a functional frontend and backend that can communicate with each other.
What we learned
We learned how to integrate a Flask backend with a React frontend. We also learned how to adjust machine learning hyperparameters and preprocess data to fit our use case.
What's next for Cardify
We plan on adding a user interface for registration so users can save their flashcard sets. We also want to improve the quality of our model to provide more accurate flashcard term and definitions.
Log in or sign up for Devpost to join the conversation.