Create app.py

app.py

@@ -0,0 +1,126 @@
+import io
+import os
+import streamlit as st
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain_community.embeddings import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.llms import OpenAI
+import openai
+import random
+
+# Load environment variables
+load_dotenv()
+openai_api_key = os.getenv('OPENAI_API_KEY')
+openai.api_key = openai_api_key
+
+# Initialize Streamlit session states
+if 'vectorDB' not in st.session_state:
+    st.session_state.vectorDB = None
+
+# Function to extract text from a PDF file
+def get_pdf_text(pdf):
+    text = ""
+    pdf_reader = PdfReader(pdf)
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+def get_text_chunks(text: str):
+    """ This function will split the text into smaller chunks"""
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=100,
+        length_function=len,
+        is_separator_regex=False,
+    )
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def get_vectorstore(text_chunks):
+    """ This function will create a vector database as well as create and store the embedding of the text chunks into the VectorDB """
+    embeddings = OpenAIEmbeddings()
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+def search_vectorstore(vectorDB, query):
+    """ This function searches for specific data or content in the vector database"""
+    # Specify the search type
+    search_type = 'similarity'
+    search_results = vectorDB.search(query, search_type=search_type)
+    return search_results
+
+def generate_quiz_questions(search_results, num_questions):
+    """ Generate quiz questions with options using GPT-3.5-turbo-16k based on the search results """
+    st.header(f"Quiz Generator: {quiz_name}")
+    st.subheader(f"Topic: {quiz_topic}")
+
+    # Placeholder for quiz questions
+    quiz_questions = []
+
+    # Generate questions using GPT-3.5-turbo-16k with the correct endpoint
+    for i in range(num_questions):
+        prompt = f"Generate a multiple-choice question  and correct answer for the same related to:\n- {random.choice(search_results)}"
+
+        # Prepare messages
+        messages = [
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt},
+        ]
+
+        # Generate questions using GPT-3.5-turbo-16k with the correct endpoint
+        response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo-16k",
+        messages=messages,
+        max_tokens=200,
+        n=num_questions,
+        stop=None,
+        temperature=0.7,
+        )
+
+        # Extract the generated question from the response
+        question = response['choices'][0]['message']['content'].strip()
+        correct_answer = f"Correct Answer: {random.choice(search_results)}"
+
+        
+        # Generate options (3 incorrect + 1 correct)
+        correct_option = f"Correct: {random.choice(search_results)}"
+        incorrect_options = [f"Incorrect: {random.choice(search_results)}" for _ in range(3)]
+        options = incorrect_options + [correct_option]
+
+        # Shuffle the options to randomize the order
+        random.shuffle(options)
+
+        # Append question and options to the quiz_questions list
+        quiz_questions.append((question, options, correct_answer))
+
+    # Display quiz questions with options
+    st.write('Quiz Questions:')
+    for i, (question, options, correct_answer) in enumerate(quiz_questions, 1):
+        st.write(f"{i}. {question}")
+        correct_option = [opt for opt in options if opt.startswith('Correct')][0]
+
+if __name__ == '__main__':
+    st.set_page_config(page_title="CB Quiz Generator", page_icon="📝")
+    st.title('🤖CB Quiz Generator🧠')
+
+    # User inputs
+    quiz_name = st.text_input('Enter Quiz Name:')
+    quiz_topic = st.text_input('Enter Quiz Topic:')
+    num_questions = st.number_input('Enter Number of Questions:', min_value=1, value=1, step=1)
+    pdf_content = st.file_uploader("Upload PDF Content for Questions:", type='pdf')
+
+    # Generate quiz if all inputs are provided
+    if quiz_name and quiz_topic and num_questions and pdf_content:
+        # Process PDF and create vector database
+        vectorDB = get_vectorstore(get_text_chunks(get_pdf_text(pdf_content)))
+
+        # Searching for a specific query in the vector database
+        if quiz_topic:
+            search_results = search_vectorstore(vectorDB, quiz_topic)
+
+            # Generate quiz questions with options using GPT-3.5-turbo-16k based on the search results
+            generate_quiz_questions(search_results, num_questions)
+        else:
+            st.error('Please provide a topic to search for!')