Update app.py

app.py

@@ -26,6 +26,8 @@ model = f"./Models/{repo_id}/{filename}"
 max_length = 8192
 pipeline = chatglm_cpp.Pipeline(model, max_length=max_length)
 
+messages = []
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -34,6 +36,8 @@ def respond(
     temperature,
     top_p,
 ):
+    global messages
+    
     generation_kwargs = dict(
         max_length=max_length,
         max_context_length=max_tokens,
@@ -44,14 +48,15 @@ def respond(
         repetition_penalty=1.0,
         stream=True,
     )
-    
-    messages = [chatglm_cpp.ChatMessage(role="system", content=system_message)]
 
-    for val in history:
-        if val[0]:
-            messages.append(chatglm_cpp.ChatMessage(role="user", content=val[0]))
-        if val[1]:
-            messages.append(chatglm_cpp.ChatMessage(role="assistant", content=val[0]))
+    if messages == []:
+        messages = [chatglm_cpp.ChatMessage(role="system", content=system_message)]
+
+    # for val in history:
+    #     if val[0]:
+    #         messages.append(chatglm_cpp.ChatMessage(role="user", content=val[0]))
+    #     if val[1]:
+    #         messages.append(chatglm_cpp.ChatMessage(role="assistant", content=val[0]))
 
     messages.append(chatglm_cpp.ChatMessage(role="user", content=message))