Update app.py

app.py

@@ -3,8 +3,7 @@ from huggingface_hub import hf_hub_download
 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
+from llama_cpp_agent.chat_history.messages import UserMessage, AssistantMessage
 
 # ⬇️ دانلود مدل
 hf_hub_download(
@@ -31,17 +30,35 @@ agent = LlamaCppAgent(
 )
 
 # 💬 تابع پاسخ‌دهنده
-def respond(message, chat_history=[], system_message="You are Arsh...", max_tokens=2048, temperature=0.6, top_p=0.95, top_k=40, repeat_penalty=1.1):
+def respond(message, chat_history, system_message, max_tokens, temperature, top_p, top_k, repeat_penalty):
+    # تنظیمات
+    settings = provider.get_provider_default_settings()
+    settings.temperature = temperature
+    settings.top_k = top_k
+    settings.top_p = top_p
+    settings.max_tokens = max_tokens
+    settings.repeat_penalty = repeat_penalty
+    settings.stream = True
+
+    # رفرش کردن سابقه چت
     if chat_history is None:
         chat_history = []
 
-    messages = BasicChatHistory()
+    # ساخت سابقه چت
+    messages = []
     for msg in chat_history:
-        messages.add_message(msg)
+        role = msg["role"]
+        content = msg["content"]
+        if role == "user":
+            messages.append(UserMessage(content))
+        elif role == "assistant":
+            messages.append(AssistantMessage(content))
 
+    # گرفتن استریم پاسخ
     stream = agent.get_chat_response(
         message,
         chat_history=messages,
+        llm_sampling_settings=settings,
         returns_streaming_generator=True,
         print_output=False
     )
@@ -54,22 +71,33 @@ def respond(message, chat_history=[], system_message="You are Arsh...", max_toke
 # 🎛️ رابط Gradio
 with gr.Blocks() as demo:
     gr.Markdown("# Arsh-LLM Q4_K_M Chat Demo")
-    gr.ChatInterface(
+    
+    with gr.Row():
+        with gr.Column():
+            system_msg = gr.Textbox("You are Arsh, a helpful assistant.", label="System Message", interactive=True)
+            max_tokens = gr.Slider(1, 4096, value=2048, step=1, label="Max Tokens")
+            temperature = gr.Slider(0.1, 4.0, value=0.6, step=0.1, label="Temperature")
+            top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
+            top_k = gr.Slider(0, 100, value=40, step=1, label="Top-k")
+            repeat_penalty = gr.Slider(0.0, 2.0, value=1.1, step=0.1, label="Repetition Penalty")
+
+    chatbot = gr.Chatbot(
+        type="messages",  # ✅ فرمت صحیح
+        bubble_full_width=False,
+        show_copy_button=True
+    )
+
+    chat_interface = gr.ChatInterface(
         respond,
         additional_inputs=[
-            gr.Textbox("You are Arsh, a helpful assistant.", label="System Message", interactive=True),
-            gr.Slider(minimum=1, maximum=4096, value=2048, step=1, label="Max Tokens"),
-            gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
-            gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
-            gr.Slider(minimum=0, maximum=100, value=40, step=1, label="Top-k"),
-            gr.Slider(minimum=0.0, maximum=2.0, value=1.1, step=0.1, label="Repetition Penalty"),
+            system_msg,
+            max_tokens,
+            temperature,
+            top_p,
+            top_k,
+            repeat_penalty
         ],
-        chatbot=gr.Chatbot(
-            type="messages",  # ✅ اینجا نوعشو مشخص کردیم
-            label="Chat with Arsh-LLM",
-            bubble_full_width=False,
-            show_copy_button=True
-        )
+        chatbot=chatbot
     )
 
 # 🚀 اجرای برنامه