Skip to content

darshanshivakumar27/ai-learning-system

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI Tutor Learning System

Overview

This project implements a simple AI-powered learning system that can explain educational topics, ask questions, evaluate student answers, and provide feedback.

The goal of this system is to simulate a basic AI tutor that helps students understand concepts interactively.

This project was developed as part of an AI Engineer Internship Assignment.


Features

  • Generate a simple explanation for a topic
  • Ask questions to test student understanding
  • Accept student answers
  • Evaluate responses
  • Provide score and feedback

Tech Stack

  • Python
  • Groq LLM API
  • Prompt Engineering
  • CLI (Command Line Interface)

System Workflow

User Input → AI Explanation → Questions → Student Answers → Evaluation → Feedback


Project Structure

ai-learning-system
│
├── main.py
├── prompts.py
├── evaluator.py
├── requirements.txt
├── README.md
└── sample_io.md

Installation

Clone the repository

git clone https://github.com/yourusername/ai-learning-system.git
cd ai-learning-system

Create virtual environment

python3 -m venv venv
source venv/bin/activate

Install dependencies

python3 -m pip install groq

Set API Key

export GROQ_API_KEY="your_api_key_here"

Run the program

python3 main.py

How It Works

  1. User enters class level, subject, and topic.
  2. The system sends a prompt to the LLM.
  3. The AI generates a simplified explanation.
  4. The system asks questions related to the topic.
  5. The student answers the questions.
  6. The program evaluates responses and provides feedback.

Possible Improvements

  • Adaptive difficulty based on student performance
  • Memory system to track student learning progress
  • Reduce hallucinations with structured prompts
  • Cost optimization using smaller models

Scaling Considerations

If 10,000 students use this system daily, possible issues include:

  • API rate limits
  • High inference cost
  • Increased latency

Possible solutions:

  • Cache explanations for common topics
  • Use request queues for processing
  • Deploy scalable backend infrastructure
  • Use smaller models for frequent queries

Author

Darshan S BE Computer Science & Data Science PES College of Engineering

About

AI-powered tutoring system that explains concepts, asks questions, evaluates answers, and provides feedback using LLMs.

Topics

Resources

Stars

Watchers

Forks

Contributors

Languages