placed the output in list comprehension and just returned the output from output_list

app.py

@@ -75,13 +75,17 @@ def llama_generation(input_text: str,
     thread = Thread(target=llama_model.generate, kwargs=generate_kwargs)
     thread.start()
 
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
+    outputs = [text for text in streamer]
+    output_text = output_list(outputs)
+    return output_text
 
-    # Convert output into string
-    print(output_list(outputs))
+    # outputs = []
+    # for text in streamer:
+    #     outputs.append(text)
+    #     yield "".join(outputs)
+
+    # # Convert output into string
+    # print(output_list(outputs))
 
 
 # Let's just make sure the llama is returning as it should and than place that return output into a function making it fit into a base