Project Info

EasyQuizzes

Inspiration

Having used Quizzlet for most of my tests the hardest task for me is first reading through all my notes and then making every Flashcard myself (hoping I grasp the right idea and my answer on the other side is right). I used to waste lot of my time preparing to prepare for the test than actually studying. With all the new development in AI and with Open Source models catching up with the State-of-the-Art models. Its easier than ever to create study notes

What it does

EasyQuizzes automates the creation of study flashcards from your notes. You upload a PDF, choose a topic, and set the number of flashcards you want. The app then creates knowledge chunks from these PDFs stores them to ChromaDB's vector database. When the user asks for N flashcards it pulls the K(preset value) most relevant chunks and the llama3.2 model uses them to generate your flashcards.

How we built it

We used ChromaDB as our vector database for storing chunk embeddings. FastAPI was utilized for API handling and backend testing. Meta’s LLaMA 3.2-3B-preview powers the app, with deployment made easier through Groq. The backend is written in Python, while the frontend uses VanillaJS, HTML, and CSS

Challenges we ran into

As a non CS grad, I had some programming background with LLMs and RAG , but deploying these projects was really hard the entire first day was spent on resolving issues with colliding packages in JS and Python. We almost entirely gave up on the tech stack.

Accomplishments we're proud of

e're proud the app works as intended, especially under a tight 3-day deadline. The successful implementation of OCR was also a big win.

What we learned

We learned the value of teamwork, leveraging each other's strengths and past experiences. Delegating tasks effectively based on expertise helped us push through challenges.

What's next

Post-competition, we aim to integrate VLLMs like LLaMA 3.2-11B-vision or smaller models like LLAVA or Moondream to add features like converting videos and audios into flashcards. We also plan to incorporate a NoSQL database to store flashcards and eventually develop EasyQuizzes into a full-fledged app. The current implementation uses groq hosted models which lack the finetuning needed for such specific tasks. So, we hope to deploy our own LoRA models for better output or understanding OCR content better.

ByteBuilder Flashcard Generator - Cal Hacks 11.0

ByteBuilder presents a Flashcard Generator, developed for Cal Hacks 11.0. This web application allows users to upload PDF documents and generate AI-powered flashcards, creating an excellent tool for study and revision.

Features
Prerequisites
Installation
Running the Application
Usage
Working
Project Structure
Technologies Used
Troubleshooting
Future Improvements

Flashcard Generator

Flashcard Generator is a web application that allows users to upload PDF documents and generate flashcards based on the content. It uses AI to create multiple-choice questions and answers, making it an excellent tool for study and revision.

Features

PDF upload and processing
AI-powered flashcard generation
Multiple-choice question format
Topic-specific flashcard creation
Interactive flashcard interface

Prerequisites

Python 3.8 or higher
Groq API key (sign up at https://www.groq.com)

Installation

Clone the repository:

Create a virtual environment (for PiP):

  python -m venv venv
  source venv/bin/activate  # On Windows: venv\Scripts\activate

Install dependencies using PiP(requirements.txt):
```
 pip install -r requirements.txt
```

Install dependencies using Conda (environment.yml):

 conda env create -f environment.yml
 conda activate flashcard-env

Set up environment variables:

Open .env and replace your_api_key_here with your actual Groq API key

Running the Application

Start the FastAPI server:

  python -m uvicorn backend.app.main:app --reload

Open a web browser and navigate to http://Localhost:8000 or whichever is provided by CLI

Usage

Upload a PDF file using the "Upload PDF" button.
Enter a topic and the number of flashcards you want to generate.
Click "Generate Flashcards" to create your flashcards.
Navigate through the flashcards using the "Previous" and "Next" buttons.
Click on a flashcard to reveal the answer.

Working

Crash course in Python Book Link: https://ehmatthes.github.io/pcc/

[]

Project Structure

This structure represents the main directories and files in the project:

backend/: Contains the backend logic.
- app/: Contains Python scripts for backend functionality.
  - __init__.py: Initializes the Python package.
  - main.py: The entry point of the backend application.
  - models.py: Defines database or data models.
  - ocr.py: Script for Optical Character Recognition (OCR).
  - VectorDB.py: Vector database management.
  - llm.py: Logic for Large Language Model (LLM) interactions.
frontend/: Contains frontend files.
- index.html: The main HTML file.
- styles.css: The CSS file for styling.
- script.js: The JavaScript file for frontend functionality.
.env.example: Example of environment variables.
.gitignore: Files and directories to be ignored by Git.
requirements.txt: List of dependencies for the backend.
README.md: Project documentation.

Technologies Used

Backend: FastAPI, ChromaDB, Groq API
Frontend: HTML, CSS, JavaScript
PDF Processing: PyPDF2
Environment Management: python-dotenv

Troubleshooting

If you encounter any issues:

Ensure you're using Python 3.8 or higher
Verify that all dependencies are correctly installed
Check that your .env file contains the correct Groq API key
Make sure you have an active internet connection for API calls

Future Improvements

Implement user accounts for saving and managing flashcard sets
Add support for more file formats beyond PDF
Enhance the AI model for even more accurate and diverse question generation
Develop a mobile app version for on-the-go studying

Analysis

Compare with all teams

View

Metric

Atharva2099
87

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only

CSSIn code
FastAPIIn code
HTMLIn code
JavaScriptIn code
PythonIn code

5 of 5 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

27 KB

Source files

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.