Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from deep_translator import GoogleTranslator
+from deep_translator import GoogleTranslate
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -9,7 +9,6 @@ client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 translator_vi2en = GoogleTranslator(source='vi', target='en')
 translator_en2vi = GoogleTranslator(source='en', target='vi')
 
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -18,11 +17,10 @@ def respond(
     temperature,
     top_p,
 ):
+    messages = [{"role": "system", "content": system_message}]
 
     message_en = translator_vi2en.translate(message)
     
-    messages = [{"role": "system", "content": system_message}]
-
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
@@ -31,14 +29,20 @@ def respond(
 
     messages.append({"role": "user", "content": message_en})
 
-    respnse =  client.predict(
+    response = ""
+
+    for message in client.chat_completion(
         messages,
+        max_tokens=max_tokens,
+        stream=True,
         temperature=temperature,
         top_p=top_p,
-    )
+    ):
+        token = message.choices[0].delta.content
 
+        response += token
     response_vi = translator_en2vi.translate(response)
-        
+    
     return response_vi
 
 
@@ -49,6 +53,5 @@ demo = gr.ChatInterface(
     respond
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()