app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import time
-import pymupdf  # Proper import for PyMuPDF
+import PyPDF2  # Import PyPDF2 for PDF text extraction
 from openai import OpenAI
 from docx import Document
 from docx.shared import Pt
@@ -44,14 +44,14 @@ for message in st.session_state.messages:
 uploaded_file = st.file_uploader("Upload PDF file", type=["pdf"])
 
 if uploaded_file:
-    # Read the PDF file using PyMuPDF
-    pdf_document = PyMuPDF.open(uploaded_file)
+    # Read the PDF file using PyPDF2
+    pdf_reader = PyPDF2.PdfReader(uploaded_file)
     full_text = ""
     
     # Extract text from each page
-    for page_num in range(pdf_document.page_count):
-        page = pdf_document.load_page(page_num)
-        full_text += page.get_text()
+    for page_num in range(len(pdf_reader.pages)):
+        page = pdf_reader.pages[page_num]
+        full_text += page.extract_text()
 
     st.write("Text extracted from PDF:")
     st.text_area("Extracted Text", full_text, height=300)