Update app.py

app.py

@@ -3,7 +3,7 @@ import pandas as pd
 import json
 import os
 import re
-from PyPDF2 import PdfReader, PdfReadError
+from PyPDF2 import PdfReader
 from collections import defaultdict
 from typing import Dict, List, Optional, Tuple, Union
 import html
@@ -16,10 +16,6 @@ MAX_FILE_SIZE_MB = 5
 MIN_AGE = 5
 MAX_AGE = 120
 
-# ========== NER MODEL HANDLING (DISABLED FOR HF SPACES) ==========
-# Disabled for Hugging Face Spaces compatibility
-ner_pipeline = None
-
 # ========== UTILITY FUNCTIONS ==========
 def sanitize_input(text: str) -> str:
     """Sanitize user input to prevent XSS and injection attacks."""
@@ -129,8 +125,6 @@ def parse_transcript(file_obj) -> Tuple[str, Optional[Dict]]:
                 page_text = page.extract_text()
                 if page_text:
                     text += page_text + '\n'
-        except PdfReadError:
-            raise gr.Error("Failed to read PDF file - may be corrupted")
         except Exception as e:
             raise gr.Error(f"Error processing PDF: {str(e)}")
         
@@ -980,10 +974,10 @@ def create_interface():
     
     return app
 
-# Create and launch the interface
+# Create the interface
 app = create_interface()
 
-# For Hugging Face Spaces, we need to call launch() in the script
+# For Hugging Face Spaces deployment
 if __name__ == "__main__":
     app.launch()