Update app.py

app.py

@@ -17,24 +17,32 @@ def pdf_to_text(pdf_file):
                     text += page_text + "\n"
     except Exception as e:
         return f"Error reading PDF: {str(e)}"
-    return text
+    return text.strip()
 
 def summarize_pdf(pdf_file):
     """Summarize the content of a PDF file."""
     text = pdf_to_text(pdf_file)
-    if len(text.strip()) == 0:
+    if len(text) == 0:
         return "No text found in the PDF."
-    
+
     # Check if the text is too short for summarization
-    if len(text) < 50:  # You can adjust this threshold
+    if len(text) < 50:  # Adjust this threshold if necessary
         return "The text extracted is too short for summarization."
 
+    # Split text if it's too long
+    max_input_length = 1024  # BART's maximum token length
+    text_chunks = [text[i:i + max_input_length] for i in range(0, len(text), max_input_length)]
+
     # Attempt to summarize the text
-    try:
-        summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
-        return summary[0]['summary_text']
-    except Exception as e:
-        return f"Error summarizing text: {str(e)}"
+    summaries = []
+    for chunk in text_chunks:
+        try:
+            summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
+            summaries.append(summary[0]['summary_text'])
+        except Exception as e:
+            return f"Error summarizing text: {str(e)}"
+
+    return "\n\n".join(summaries)  # Join summaries from chunks
 
 # Create a Gradio interface
 interface = gr.Interface(