Update app.py

app.py

@@ -42,7 +42,7 @@ def process_text(uploaded_file):
 
     try:
         abstract_text = extract_abstract(pdf_bytes)
-        logging.info(f"Extracted abstract: {abstract_text[:100]}...")  # Log first 100 chars of abstract
+        logging.info(f"Extracted abstract: {abstract_text[:200]}...")  # Log first 200 chars of abstract
     except Exception as e:
         logging.error(f"Error in abstract extraction: {e}")
         return "Error in processing PDF", None
@@ -66,18 +66,18 @@ def process_text(uploaded_file):
         summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
         # Post-process the summary
-        words = summary.split()
-        cleaned_summary = []
-        for i, word in enumerate(words):
-            if '-' in word and i < len(words) - 1:
-                word = word.replace('-', '') + words[i + 1]
-                words[i + 1] = ""
-
-            if '.' in word and i != len(words) - 1:
-                word = word.replace('.', '')
-                cleaned_summary.append(word + ' and')
-            else:
-                cleaned_summary.append(word)
+        #words = summary.split()
+        #cleaned_summary = []
+        #for i, word in enumerate(words):
+        #    if '-' in word and i < len(words) - 1:
+        #        word = word.replace('-', '') + words[i + 1]
+        #        words[i + 1] = ""
+
+        #    if '.' in word and i != len(words) - 1:
+        #        word = word.replace('.', '')
+        #        cleaned_summary.append(word + ' and')
+        #    else:
+        #        cleaned_summary.append(word) 
 
         final_summary = ' '.join(cleaned_summary)
         final_summary = final_summary[0].upper() + final_summary[1:]