Update app.py

app.py

@@ -19,20 +19,24 @@ def extract_text(pdf_file):
 
     
 # Function to summarize text
-# Defines a function to summarize the extracted text using facebook/bart-large-cnn    
+# Defines a function to summarize the extracted text using pszemraj/led-base-book-summary    
 def summarize_text(text):
-    sentences = text.split(". ")
-    for i, sentence in enumerate(sentences):
-        if "Abstract" in sentence:
-            start = i + 1
-            end = start + 6
-            break
-            
-    if start is not None and end is not None:  
-        abstract = ". ".join(sentences[start:end+1])
-        #print(abstract)
-    else:                                            #if the Abstract is not found
-        return("Abstract section not found")
+      sentences = text.split(". ")
+
+      # Find the start index of the Abstract section
+      for i, sentence in enumerate(sentences):
+          if "Abstract" in sentence:
+              start = i + 1
+
+      # Find the end index (6 sentences after start)        
+      end = start + 6  
+
+      if start is not None and end is not None:  
+          # Join the sentences from start to end into the abstract 
+          abstract = ". ".join(sentences[start:end+1])  
+
+      else:                                           
+          return("Abstract section not found")
 
   # Load BART model & tokenizer
     tokenizer = AutoTokenizer.from_pretrained("pszemraj/led-base-book-summary")