This project demonstrates AI-driven workflow for summarizing lecture content, generating questions, and providing a basic grading mechanism. It uses NLP models (summarization, question generation) integrated into a Flask web application.

1. AI-Powered Summarization
   Upload a lecture file (PDF, DOCX, PPTX), and the application extracts the text, preprocesses it, and summarizes it using a transformer-based summarization model (facebook/bart-large-cnn).

2. Question Generation from AI Models

   • 6 Questions: Questions from chunked segments of the processed text, ensuring coverage of various topics in the lecture.

3. Interactive UI Flow

   • Upload Page: The user uploads a file. A large image (logo) is displayed at the top, with the upload button below, and a footer credit line at the bottom.

   • 

   • Processed Page (Summary & Original Text): Displays the original text, summary, and extracted links. User can choose to upload another file or proceed to questions.

   • 

   • 

   • Questions Page: Lists the generated questions with a text area for each answer and a "Grade Answer" button.

   • 

4. Placeholder Grading Logic
   Currently, grading is simplistic:

   • If the student's answer shares any word with the context, it returns "Good job!"
   • Otherwise, "Try again!"
   • Future enhancements can include semantic similarity-based scoring.

• Better Question Quality: Experiment with other question generation models or fine-tune existing ones.
• Advanced Grading: Implement semantic similarity for more accurate feedback.
• Enhanced UI/UX: Improve styling, add loading indicators, and refine the user experience.

1. Install Dependencies:

   pip install flask PyPDF2 python-docx python-pptx nltk spacy transformers keybert rake-nltk yake