QuizBot

QuizBot acts as an AI Assistant to the teacher. Just upload your teaching material and it creates customizable 'MCQ' question sets based on teacher-selected difficulty, number of questions, and options.

Knowledge

• Chains : Combination of propmt templates to run queries against an LLM where output of one component acts as an input to another.
• Prompt templates : help to translate user input and parameters into instructions for a language model. This can be used to guide a model's response, helping it understand the context and generate relevant and coherent language-based output.​
• Prompt Templates take as input a dictionary, where each key represents a variable in the prompt template to fill in.​

Workflow

• File Upload

  Teacher uploads study material. Set parameters for number of questions, options and difficulty level.

• 

  Tells the LLM to summarize the entire content to make reasoning easier and avoid Context Length crashes.

• 

  Tells the LLM to generate MCQ's based on the summary and keeping in mind the parameters set by the teachers.

• Chain Visualization

  

Features

• Upload multiple files (.txt, .pdf, .docx)
• Automatically summarizes uploaded content
• Generates MCQs based on:
  • Number of questions
  • Number of options per question
  • Difficulty level (Easy, Medium, Hard)
• Uses LangChain prompt chaining with LLM
• Clean frontend interface:
  • Markdown-rendered output
  • Separate output sections for Questions and Answers
  • Copy-to-clipboard functionality for both sections

Video Demo

QuizBot-Demo.webm

Requirements

Install the required Python packages:

pip install flask python-docx PyPDF2 langchain langchain_community

You must also have Ollama installed and running a compatible local model (such as llama3.1:8b)

Technologies Used

• LangChain
• Ollama LLM (llama3)
• Flask
• marked.js for Markdown rendering in the frontend

Author

Developed by Harsh, AI/ML Enthusiast.