Update main.py

main.py

@@ -105,11 +105,11 @@ def chat_with_llama_stream(messages, model="gpt-3.5-turbo", max_llm_history=4, m
         )
         
         full_response = ""
-        for event in response:
-            if "content" in event["choices"][0].delta:
-                current_response = event["choices"][0].delta.content
-                full_response +=current_response
-                yield current_response
+        for chunk in response:
+            if chunk.choices[0].delta.content is not None:
+                content = chunk.choices[0].delta.content
+                full_response += content
+                yield content
         
         # After streaming, add the full response to the conversation history
         messages.append({"role": "assistant", "content": full_response})