Update app.py

app.py

@@ -10,7 +10,6 @@ import io
 import tempfile
 import re
 
-# Initialize the inference client with your chosen model
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 def extract_text_from_pdf(file):
@@ -30,9 +29,8 @@ 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)  
+    random.shuffle(sentences)  # Shuffle sentences
 
-    
     with tempfile.NamedTemporaryFile(mode='w', newline='', delete=False, suffix='.csv') as tmp:
         fieldnames = ['Original Sentence', 'Generated Sentence']
         writer = csv.DictWriter(tmp, fieldnames=fieldnames)
@@ -58,9 +56,8 @@ def generate(file, temperature, max_new_tokens, top_p, repetition_penalty):
                 for response in stream:
                     output += response.token.text
 
-                
                 generated_sentences = re.split(r'(?<=[\.\!\?:])[\s\n]+', output)
-                generated_sentences = [s.strip() for s in generated_sentences if s.strip()]
+                generated_sentences = [s.strip() for s in generated_sentences if s.strip() and s != '.']
 
                 for generated_sentence in generated_sentences:
                     writer.writerow({'Original Sentence': sentence, 'Generated Sentence': generated_sentence})