Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 import logging
 from dotenv import load_dotenv
 import streamlit as st
-from PyPDF2 import PdfReader, PdfReadError
+from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceInstructEmbeddings
 from langchain.vectorstores import FAISS
@@ -26,13 +26,10 @@ def get_pdf_text(pdf_docs):
         try:
             pdf_reader = PdfReader(pdf)
             for page in pdf_reader.pages:
-                text += page.extract_text()
-        except PdfReadError:
-            st.warning(f"Could not read {pdf.name}. Skipping this file.")
-            logging.warning(f"Could not read {pdf.name}. Skipping.")
+                text += page.extract_text() or ""
         except Exception as e:
-            st.warning(f"Error processing {pdf.name}: {e}")
-            logging.error(f"Error processing {pdf.name}: {e}")
+            st.warning(f"Could not read {pdf.name}. Skipping this file.")
+            logging.warning(f"Error processing {pdf.name}: {e}")
     return text
 
 # Function to split the extracted text into chunks
@@ -113,4 +110,4 @@ def main():
                 st.session_state.conversation = get_conversation_chain(vectorstore)
 
 if __name__ == '__main__':
-    main()
+    main()