Update app.py

app.py

@@ -36,19 +36,37 @@ def segment_text(text):
     logger.info(f"Segmented text into {len(chunks)} chunks.")
     return chunks
 
+# Function to read file content with fallback encoding
+def read_file_content(file):
+    try:
+        # Try reading with UTF-8 encoding first
+        if hasattr(file, "read"):
+            content = file.read().decode('utf-8')
+        else:
+            content = file.decode('utf-8')
+        logger.info("File read successfully with UTF-8 encoding.")
+        return content
+    except UnicodeDecodeError:
+        # Fallback to latin-1 encoding if UTF-8 fails
+        logger.warning("UTF-8 encoding failed. Trying latin-1 encoding.")
+        if hasattr(file, "read"):
+            file.seek(0)  # Reset file pointer to the beginning
+            content = file.read().decode('latin-1')
+        else:
+            content = file.decode('latin-1')
+        logger.info("File read successfully with latin-1 encoding.")
+        return content
+    except Exception as e:
+        logger.error(f"Failed to read file: {e}")
+        raise gr.Error(f"Failed to read file: {str(e)}")
+
 # Function to process the text and make API calls with rate limiting
 def process_text(file, prompt):
     try:
         logger.info("Starting text processing...")
         
-        # Read the file content properly
-        if hasattr(file, "read"):
-            # If the file is a file-like object, read its content
-            text = file.read().decode('utf-8')  # Decode bytes to string
-        else:
-            # If the file is already a string, use it directly
-            text = file
-        
+        # Read the file content with fallback encoding
+        text = read_file_content(file)
         logger.info(f"Text length: {len(text)} characters.")
         
         # Segment the text into chunks