Update app.py

app.py

@@ -10,25 +10,34 @@ def summarize_pdf(pdf_file):
         # Extract text from the uploaded PDF
         pdf_reader = PyPDF2.PdfReader(pdf_file)
         text = ""
-        for page in pdf_reader.pages:
-            text += page.extract_text()
+        
+        for page_number, page in enumerate(pdf_reader.pages):
+            try:
+                page_text = page.extract_text()
+                if page_text:
+                    text += page_text + "\n"
+            except Exception as e:
+                return f"❌ Could not read page {page_number + 1}: {str(e)}"
         
         # Check if text was extracted
         if not text.strip():
-            return "❌ Could not extract text from the PDF. Please upload a valid document."
+            return "❌ Could not extract any text from the PDF. Please upload a readable document."
 
         # Summarize the extracted text
-        summary = summarizer(text, max_length=300, min_length=50, do_sample=False)
+        # Limit the text input length for summarization to avoid overflow errors
+        max_length = 1024  # Hugging Face models have input length limits
+        text = text[:max_length]
+        summary = summarizer(text, max_length=200, min_length=50, do_sample=False)
         return summary[0]['summary_text']
 
     except Exception as e:
         return f"❌ An error occurred: {str(e)}"
 
-# Update Gradio interface to use the new syntax
+# Gradio Interface
 interface = gr.Interface(
     fn=summarize_pdf,
-    inputs=gr.File(label="Upload PDF"),  # Updated to gr.File
-    outputs=gr.Textbox(label="Summary"),  # Updated to gr.Textbox
+    inputs=gr.File(label="Upload PDF"),
+    outputs=gr.Textbox(label="Summary"),
     title="PDF Summarizer",
     description="Upload a PDF file to extract and summarize its content using state-of-the-art AI."
 )