app.py

# -*- coding: utf-8 -*-
"""
Created on Mon Dec 25 18:18:27 2023

@author: alish
"""

import gradio as gr
import fitz  # PyMuPDF
import questiongenerator as qs
import random

from sentence_transformers import SentenceTransformer, util
from questiongenerator import QuestionGenerator
qg = QuestionGenerator()



def highlight_similar_sentence(text1, text2, color='yellow'):
    # Load the pre-trained sentence-transformers model
    model = SentenceTransformer("paraphrase-MiniLM-L6-v2")

    # Split text into sentences
    sentences_text1 = [sentence.strip() for sentence in text1.split('.') if sentence.strip()]
    sentences_text2 = [sentence.strip() for sentence in text2.split('.') if sentence.strip()]

    # Compute embeddings for text1
    #embeddings_text1 = model.encode(sentences_text1, convert_to_tensor=True)

    highlighted_text2 = text2
    max_similarity = 0.0

    # Find the most similar sentence in text2 for each sentence in text1
    for sentence_text1 in sentences_text1:
        # Compute embeddings for the current sentence in text1
        embedding_text1 = model.encode(sentence_text1, convert_to_tensor=True)

        for sentence_text2 in sentences_text2:
            # Compute cosine similarity between sentence in text1 and text2
            embedding_text2 = model.encode(sentence_text2, convert_to_tensor=True)
            similarity = util.pytorch_cos_sim(embedding_text1, embedding_text2).item()

            # Highlight the most similar sentence in text2
            if similarity > max_similarity:
                max_similarity = similarity
                highlighted_text2= highlight_text(text2, sentence_text2, color=color)
                #highlighted_text2 = text2.replace(sentence_text2, f"<span style='background-color: {color};'>{sentence_text2}</span>")

    return highlighted_text2


def Extract_QA(qlist,selected_extracted_text):
        Q_All=''
        A_All=''
        xs=['A','B','C','D']
        h_colors=['yellow', 'red', 'DodgerBlue', 'Orange', 'Violet']
        for i in range(len(qlist)):
            question_i= qlist[i]['question']
            Choices_ans= []
            Choice_is_correct=[]
            for j in range(4):
               Choices_ans= Choices_ans+ [qlist[i]['answer'][j]['answer']]
               Choice_is_correct= Choice_is_correct+ [qlist[i]['answer'][j]['correct']]
               
            Q=f"""
                 Q_{i+1}: {question_i}
                 A. {Choices_ans[0]}
                 B. {Choices_ans[1]}
                 C. {Choices_ans[2]}
                 D. {Choices_ans[3]} 
                                  
                """
            
            result = [x for x, y in zip(xs, Choice_is_correct) if y ]
            correct_answer= [x for x, y in zip(Choices_ans, Choice_is_correct) if y ]
            A= f"""
                <p>Answer_{i+1}: {result[0]} - {correct_answer[0]}<p>
                
                
                """
            color= h_colors[i]
            
            A_sen= f""" The correct answer is {correct_answer[0]}."""
            
            A= highlight_text(input_text=A, selcted_text=correct_answer[0], color=color)
            selected_extracted_text= highlight_similar_sentence(A_sen, selected_extracted_text, color=color)
            
            
            Q_All= Q_All+Q
            A_All=A_All+ A
            
            
        return (Q_All,A_All,selected_extracted_text)






def extract_text_from_pdf(pdf_file_path):
    # Read the PDF file
    global extracted_text
    text = []
    with fitz.open(pdf_file_path) as doc:
        for page in doc:
            text.append(page.get_text())
    extracted_text= '\n'.join(text)
    extracted_text= get_sub_text(extracted_text)
    
    return ("The pdf is uploaded Successfully from:"+ str(pdf_file_path))

qg = qs.QuestionGenerator()

def get_sub_text(TXT):
   sub_texts= qg._split_into_segments(TXT)
   if isinstance(sub_texts, list):
       return sub_texts
   else:
       return [sub_texts]

def highlight_text(input_text, selcted_text, color='yellow'):
    # Replace 'highlight' with <span> tags for highlighting
    highlighted_text = input_text.replace(selcted_text, f'<span style="background-color: {color}">{selcted_text}</span>')
    return highlighted_text


def pick_One_txt(sub_texts):
    global selected_extracted_text
    N= len(sub_texts)
    if N==1:
       selected_extracted_text= sub_texts[0] 
       return(selected_extracted_text)
    # Generate a random number between low and high
    random_number = random.uniform(0, N)    
    # Pick the integer part of the random number
    random_number = int(random_number)
    selected_extracted_text= sub_texts[random_number]
        
    return(selected_extracted_text)
 

def pipeline(NoQs):
    global Q,A
    text= selected_extracted_text
    qlist= qg.generate(text, num_questions=NoQs, answer_style="multiple_choice")
    Q,A,highligthed_text= Extract_QA(qlist,text)
    A= A + '\n'+highligthed_text
    return (Q,A)

def ReurnAnswer():
    return A

def GetQuestion(NoQs):
    NoQs=int(NoQs)
    pick_One_txt(extracted_text)
    Q,A=pipeline(NoQs)
    return Q

with gr.Blocks() as demo:
    

    with gr.Row():
        with gr.Column(scale=1):
            with gr.Row():
                gr.Image("PupQuizAI.png")            
                gr.Markdown(""" 🐶 **PupQuizAI** is an Artificial-Intelligence tool that streamlines the studying process. Simply input a text pdf that you need to study from. Then, PupQuiz will create 1-5 custom questions for you to study from each time you push 'Show Questions'. 
                             """ )
            
            input_file=gr.UploadButton(label='Select a file!', file_types=[".pdf"])
            input_file.upload(extract_text_from_pdf, input_file)
            #upload_btn = gr.Button(value="Upload the pdf File.")
            Gen_Question = gr.Button(value="Show Questions")
            Gen_Answer = gr.Button(value="Show Answers")
            No_Qs= gr.Slider(minimum=1, maximum=5,value=3, step=1, label='Max # of Questions')
    
            gr.Markdown(""" 🐶 
                        **Instructions:**                     
                        * Start by selecting a 'pdf' text file you want to upload by clicking the "Select file" button. (PupQuiz currently only supports files that can have highlightable text)
                        * Select the number of questions you want generated from the "# of Questions" selector. 
                        * Click "Show Questions" 
                        * Then, if you want answers to the questions, select "Show Answers" """  )
         
            #gr.Image("PupQuizAI.png")
            
            
            
        with gr.Column(scale=2.0):
            #file_stat= gr.Textbox(label="File Status")
            question = gr.Textbox(label="Question(s)")
            #Answer = gr.Textbox(label="Answer(s)")
            Answer = gr.HTML(label="Answer(s)")

    Gen_Question.click(GetQuestion, inputs=No_Qs, outputs=question, api_name="QuestioGenerator")
    Gen_Answer.click(ReurnAnswer, inputs=None, outputs=Answer, api_name="QuestioGenerator")
   

demo.launch()