Update app.py

app.py

@@ -18,6 +18,11 @@ def extract_text_from_pdf(file):
 def generate_synthetic_data(sentences, temperature, max_new_tokens, top_p, repetition_penalty):
     synthetic_data = []
     for sentence in sentences:
+        # Trim whitespace and skip if the sentence is empty
+        sentence = sentence.strip()
+        if not sentence:
+            continue
+        
         generate_kwargs = {
             "temperature": temperature,
             "max_new_tokens": max_new_tokens,
@@ -26,12 +31,17 @@ def generate_synthetic_data(sentences, temperature, max_new_tokens, top_p, repet
             "do_sample": True,
             "seed": 42,
         }
-        formatted_prompt = sentence  # Using the sentence directly as the prompt
-        stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-        output = ""
-        for response in stream:
-            output += response.token.text
-        synthetic_data.append(output)
+
+        try:
+            stream = client.text_generation(sentence, **generate_kwargs, stream=True, details=True, return_full_text=False)
+            output = ""
+            for response in stream:
+                output += response.token.text
+            synthetic_data.append(output)
+        except Exception as e:
+            print(f"Error generating data for sentence '{sentence}': {e}")
+            # Optionally, append a placeholder or error message to `synthetic_data` to maintain alignment with input sentences
+            synthetic_data.append(f"Error: {e}")
     return synthetic_data
 
 def generate(file, temperature, max_new_tokens, top_p, repetition_penalty):