Update app.py

app.py

@@ -10,23 +10,18 @@ MAX_TURNS = 20
 MAX_BOXES = MAX_TURNS * 2
 
 
-def predict(input, max_length, top_p, temperature, history=None, state=None):
-    if state is None:
-        state = []
-    if history is None or history == "":
-        history = state
-    else:
-        history = json.loads(history)
-
-    for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
-                                               temperature=temperature):
-        updates = []
-        for query, response in history:
-            updates.append(gr.update(visible=True, value=query))
-            updates.append(gr.update(visible=True, value=response))
-        if len(updates) < MAX_BOXES:
-            updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
-        yield [history] + updates
+def predict(input, max_length, top_p, temperature, history=None):
+    if history is None:
+        history = []
+    response, history = model.chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
+                                   temperature=temperature)
+    updates = []
+    for query, response in history:
+        updates.append(gr.update(visible=True, value="用户：" + query))
+        updates.append(gr.update(visible=True, value="ChatGLM-6B：" + response))
+    if len(updates) < MAX_BOXES:
+        updates = updates + [gr.Textbox.update(visible=False)] * (MAX_BOXES - len(updates))
+    return [history] + updates
 
 
 with gr.Blocks() as demo: