Update app.py

app.py

@@ -8,6 +8,8 @@ import csv
 import os
 import io 
 import tempfile
+import re
+
 # Initialize the inference client with your chosen model
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
@@ -24,15 +26,18 @@ def save_to_csv(sentence, output, filename="synthetic_data.csv"):
         writer.writerow([sentence, output])
 
 
+
 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
 
-   
+    # Geçici dosya oluştur ve CSV yazıcısını başlat
     with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
-        writer = csv.writer(tmp)
-        
+        fieldnames = ['Original Sentence', 'Generated Sentence']
+        writer = csv.DictWriter(tmp, fieldnames=fieldnames)
+        writer.writeheader()  # CSV dosyasına kolon isimleri yazılır
+
         for sentence in sentences:
             sentence = sentence.strip()
             if not sentence:
@@ -52,7 +57,15 @@ def generate(file, temperature, max_new_tokens, top_p, repetition_penalty):
                 output = ""
                 for response in stream:
                     output += response.token.text
-                writer.writerow([sentence, output])  
+
+                # Modelden gelen yanıtı cümlelere ayır
+                generated_sentences = re.split(r'[\.\?!]', 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})
+
             except Exception as e:
                 print(f"Error generating data for sentence '{sentence}': {e}")