Update app.py

app.py

@@ -76,7 +76,13 @@ def chat_llama3_8b(message: str,
     )
     
     response=llm.create_chat_completion(messages=conversation, temperature=temperature)
-    yield response
+    # Access the first (and likely only) choice in the response
+    choice = response['choices'][0]
+
+    # Extract the text content from the message within the choice
+    text_response = choice['message']['content']
+
+    yield text_response
         
 
 # Gradio block