fix: use the right way to extract the generated text from the stream

app.py

@@ -137,16 +137,17 @@ def generate(
     
     if len(ENDPOINT)>0:
         stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-        print(f"STREAM: {stream}\n")
-        stream = stream.generated_text
     else:
         stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=False, details=True, return_full_text=False)
 
-    
-    
     output = ""
     for response in stream:
-        output += response
+        print('stream',response)
+
+        if len(ENDPOINT)>0:
+            output += response.generated_text
+        else:        
+            output += response
 
         for stop_str in stop_sequences:
             if output.endswith(stop_str):