Update app.py

app.py

@@ -13,8 +13,9 @@ import os
 from concurrent.futures import ThreadPoolExecutor
 import requests
 from bs4 import BeautifulSoup
-from docx import Document
-from fpdf import FPDF
+import re
+import json
+import pandas as pd
 
 # Load environment variables
 load_dotenv()
@@ -30,10 +31,14 @@ pytesseract.pytesseract.tesseract_cmd = r"/usr/bin/tesseract"  # Adjust based on
 
 # Function to enhance image for OCR processing
 def enhance_image_for_ocr(image):
-    gray_image = image.convert("L")
-    enhancer = ImageEnhance.Contrast(gray_image)
-    enhanced_image = enhancer.enhance(2.0)
-    return enhanced_image
+    try:
+        gray_image = image.convert("L")
+        enhancer = ImageEnhance.Contrast(gray_image)
+        enhanced_image = enhancer.enhance(2.0)  # Increase contrast
+        return enhanced_image
+    except Exception as e:
+        logging.error(f"Error enhancing image for OCR: {e}")
+        return image
 
 # Function to extract text from images using OCR
 def extract_text_from_images(images, lang="eng"):
@@ -112,20 +117,26 @@ def process_files(uploaded_files, lang="eng"):
     ocr_text = extract_text_from_images(images, lang)
     return combined_text + "\n" + ocr_text
 
-# Function to generate questions (without the question number or difficulty)
-def generate_questions(syllabus_text, num_questions):
-    prompt = f"Generate {num_questions} relevant questions based on the following syllabus content. Ensure that the questions are diverse and realistic, as would be generated by a human educator. Syllabus Content: {syllabus_text}"
+# Function to generate questions with enhanced realism
+def generate_questions(question_type, syllabus_text, num_questions, difficulty, prompt_template):
+    prompt = prompt_template.format(
+        num_questions=num_questions,
+        question_type=question_type,
+        syllabus_text=syllabus_text,
+        **difficulty
+    )
 
     chain = (ChatPromptTemplate.from_template(prompt) | llm | StrOutputParser())
     try:
         questions = chain.invoke({})
-        questions = "\n".join([q.strip() for q in questions.split("\n") if q.strip()])  # Clean up the questions
-        return questions
+        # Extract only the question text, remove numbering, difficulty, etc.
+        questions_clean = re.sub(r"(\d+\.)|(.*?)", "", questions)  # Remove question numbers and extra parts
+        return questions_clean.strip()
     except Exception as e:
         logging.error(f"Error generating questions: {e}")
         return ""
 
-# Function to generate answers based on the questions
+# Refined function to generate answers (excluding question numbers and difficulty)
 def generate_answers(questions, syllabus_text):
     answers = {}
     
@@ -134,6 +145,8 @@ def generate_answers(questions, syllabus_text):
             prompt = f"""
             Below is a syllabus excerpt. Please answer the following question based on the content provided. 
             Ensure the answer is directly related to the question and specific to the syllabus. 
+            If necessary, explain key concepts clearly. Answer the question in a concise and detailed manner.
+
             Syllabus Content: {syllabus_text}
 
             Question: {question}
@@ -145,44 +158,40 @@ def generate_answers(questions, syllabus_text):
                 answer = chain.invoke({})
                 answers[f"Answer {i+1}"] = answer.strip()
             except Exception as e:
-                answers[f"Answer {i+1}"] = "No answer found."
+                answers[f"Answer {i+1}"] = search_answers_online(question)
     
     return "\n".join([f"{k}: {v}" for k, v in answers.items()])
 
-# Function to generate docx download
-def generate_docx(questions, answers):
-    doc = Document()
-    doc.add_heading("Questions and Answers", 0)
-
-    questions_list = questions.split("\n")
-    answers_list = answers.split("\n")
+# Function to search answers online
+def search_answers_online(question):
+    search_url = f"https://www.google.com/search?q={question}"
+    headers = {"User-Agent": "Mozilla/5.0"}
+    try:
+        response = requests.get(search_url, headers=headers)
+        soup = BeautifulSoup(response.text, "html.parser")
+        snippets = soup.find_all("div", class_="BNeawe")
+        return "\n".join([snippet.get_text() for snippet in snippets[:3]])
+    except Exception as e:
+        logging.error(f"Error fetching online answers: {e}")
+        return "No online answer found."
 
-    for i in range(len(questions_list)):
-        doc.add_heading(f"Q{i+1}: {questions_list[i]}", level=1)
-        doc.add_paragraph(f"A{i+1}: {answers_list[i]}")
+# Function to limit downloads to DOCX, PDF, and TXT formats
+def save_as_txt(questions, answers):
+    return f"Questions:\n{questions}\n\nAnswers:\n{answers}"
 
-    doc_path = "/tmp/questions_and_answers.docx"
-    doc.save(doc_path)
-    return doc_path
+def save_as_pdf(questions, answers):
+    # For simplicity, returning a text-based PDF. For more complex PDFs, libraries like ReportLab can be used.
+    from fpdf import FPDF
 
-# Function to generate PDF download
-def generate_pdf(questions, answers):
     pdf = FPDF()
-    pdf.set_auto_page_break(auto=True, margin=15)
     pdf.add_page()
-
-    questions_list = questions.split("\n")
-    answers_list = answers.split("\n")
-
+    pdf.set_auto_page_break(auto=True, margin=15)
     pdf.set_font("Arial", size=12)
-
-    for i in range(len(questions_list)):
-        pdf.cell(200, 10, f"Q{i+1}: {questions_list[i]}", ln=True)
-        pdf.multi_cell(200, 10, f"A{i+1}: {answers_list[i]}")
-
-    pdf_path = "/tmp/questions_and_answers.pdf"
-    pdf.output(pdf_path)
-    return pdf_path
+    pdf.multi_cell(0, 10, f"Questions:\n{questions}\n\nAnswers:\n{answers}")
+    pdf_output = BytesIO()
+    pdf.output(pdf_output)
+    pdf_output.seek(0)
+    return pdf_output
 
 # Streamlit UI
 st.title("AI-Powered Exam Generator")
@@ -213,9 +222,30 @@ with tab2:
 # Generate questions and answers
 with tab3:
     st.header("Generate Questions and Answers")
-    num_questions = st.number_input("Total Number of Questions", min_value=1, step=1)
-    if num_questions and st.button("Generate Questions and Answers"):
-        questions = generate_questions(st.session_state.get("syllabus_text", ""), num_questions)
+    question_type = st.selectbox("Select Question Type", ["MCQs", "Short Questions", "Long Questions", "Fill-in-the-Blank", "Case Study"])
+    num_questions = st.text_input("Total Number of Questions")
+    difficulty_levels = ["Remember", "Understand", "Apply", "Analyze", "Evaluate", "Create"]
+    difficulty = {level: st.slider(level, 0, 5, 1) for level in difficulty_levels}
+    prompt_template = st.text_area(
+        "Edit Prompt Template",
+        """
+        Generate {num_questions} {question_type} questions from the syllabus content below.
+        Syllabus Content: {syllabus_text}
+        Difficulty Levels:
+        - Remember: {Remember}
+        - Understand: {Understand}
+        - Apply: {Apply}
+        - Analyze: {Analyze}
+        - Evaluate: {Evaluate}
+        - Create: {Create}
+        """,
+        height=200
+    )
+    if num_questions.isdigit() and st.button("Generate Questions and Answers"):
+        num_questions = int(num_questions)
+        
+        # Generate questions
+        questions = generate_questions(question_type, st.session_state.get("syllabus_text", ""), num_questions, difficulty, prompt_template)
         st.session_state["questions"] = questions
         st.text_area("Generated Questions", questions, height=300)
 
@@ -225,14 +255,12 @@ with tab3:
         st.text_area("Generated Answers", answers, height=300)
 
         # Download questions and answers
-        st.download_button("Download Questions", questions, file_name="questions.txt")
-        st.download_button("Download Answers", answers, file_name="answers.txt")
-        st.download_button("Download as DOCX", generate_docx(questions, answers), file_name="questions_and_answers.docx")
-        st.download_button("Download as PDF", generate_pdf(questions, answers), file_name="questions_and_answers.pdf")
+        st.download_button("Download Questions (TXT)", save_as_txt(questions, answers), file_name="qa.txt")
+        st.download_button("Download Q&A (PDF)", save_as_pdf(questions, answers), file_name="qa.pdf")
 
 # Generate answers
 with tab4:
-    st.header("Generate Answers for Uploaded Content")
+    st.header("Generate Answers (Optional)")
     if "questions" in st.session_state:
         if st.button("Generate Answers"):
             answers = generate_answers(st.session_state["questions"], st.session_state.get("syllabus_text", ""))
@@ -240,6 +268,4 @@ with tab4:
             st.text_area("Generated Answers", answers, height=300)
 
             # Download answers
-            st.download_button("Download Answers", answers, file_name="answers.txt")
-            st.download_button("Download Answers as DOCX", generate_docx(st.session_state["questions"], answers), file_name="answers.docx")
-            st.download_button("Download Answers as PDF", generate_pdf(st.session_state["questions"], answers), file_name="answers.pdf")
+            st.download_button("Download Answers", answers, file_name="answers.txt")