Update app.py

app.py

@@ -30,13 +30,13 @@ def save_to_csv(sentence, output, filename="synthetic_data.csv"):
 def generate(file, temperature, max_new_tokens, top_p, repetition_penalty):
     text = extract_text_from_pdf(file)
     sentences = text.split('.')
-    random.shuffle(sentences)  # Shuffle sentences
+    random.shuffle(sentences)  
 
-    # Geçici dosya oluştur ve CSV yazıcısını başlat
+    
     with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
         fieldnames = ['Original Sentence', 'Generated Sentence']
         writer = csv.DictWriter(tmp, fieldnames=fieldnames)
-        writer.writeheader()  # CSV dosyasına kolon isimleri yazılır
+        writer.writeheader()  
 
         for sentence in sentences:
             sentence = sentence.strip()
@@ -58,11 +58,10 @@ def generate(file, temperature, max_new_tokens, top_p, repetition_penalty):
                 for response in stream:
                     output += response.token.text
 
-                # Modelden gelen yanıtı cümlelere ayır
-                generated_sentences = re.split(r'[\.\?!]', output)
+                
+                generated_sentences = re.split(r'(?<=[\.\!\?:])[\s\n]+', output)
                 generated_sentences = [s.strip() for s in generated_sentences if s.strip()]
 
-                # Her cümleyi ayrı bir satır olarak CSV'ye yaz
                 for generated_sentence in generated_sentences:
                     writer.writerow({'Original Sentence': sentence, 'Generated Sentence': generated_sentence})