Update app.py

app.py

@@ -10,7 +10,6 @@ from llama_cpp import Llama
 from llama_cpp_agent import LlamaCppAgent, MessagesFormatterType
 from llama_cpp_agent.providers import LlamaCppPythonProvider
 from llama_cpp_agent.chat_history import BasicChatHistory
-from llama_cpp_agent.chat_history.messages import Roles, ChatMessage
 import gradio as gr
 from huggingface_hub import hf_hub_download
 
@@ -34,7 +33,7 @@ def chat_fn(message, history, model, system_message, max_tokens, temperature, to
     response_generator = respond(message, history_list, model, system_message, max_tokens, temperature, top_p, top_k, repeat_penalty)
     
     for chat_history in response_generator:
-        yield chat_history.get_messages(), history #  直接yield BasicChatHistory 对象
+        yield chat_history.get_messages(), history
 
 
 def respond(message, history, model, system_message, max_tokens, temperature, top_p, top_k, repeat_penalty):
@@ -74,10 +73,10 @@ def respond(message, history, model, system_message, max_tokens, temperature, to
     messages = BasicChatHistory()
 
     for user_msg, bot_msg in history:
-        messages.add_message(ChatMessage(role="user", content=user_msg))
-        messages.add_message(ChatMessage(role="assistant", content=bot_msg))
+        messages.add_message({"role": "user", "content": user_msg})
+        messages.add_message({"role": "assistant", "content": bot_msg})
     
-    messages.add_message(ChatMessage(role="user", content=message)) # 添加用户当前消息
+    messages.add_message({"role": "user", "content": message})
 
     start_time = time.time()
     token_count = 0
@@ -95,7 +94,7 @@ def respond(message, history, model, system_message, max_tokens, temperature, to
     for output in stream:
         outputs += output
         token_count += len(output.split())
-        messages.add_message(ChatMessage(role="assistant", content=output))
+        messages.add_message({"role": "assistant", "content": output})
         yield messages
 
     end_time = time.time()