Update app.py

app.py

@@ -1,9 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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
-"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
@@ -15,6 +12,10 @@ def respond(
     temperature,
     top_p,
 ):
+    # Добавляем инструкцию для поддержки многоязычности
+    system_message = system_message or "You are a multilingual assistant. Respond in the user's language and provide clear, correct answers."
+
+    # Составляем историю сообщений для отправки модели
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -27,6 +28,7 @@ def respond(
 
     response = ""
 
+    # Генерация ответа с потоковой выдачей токенов
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,18 +37,18 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
-
         response += token
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Интерфейс Gradio с дополнительными настройками
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(
+            value="You are a multilingual assistant. Respond in the user's language and provide clear, correct answers.",
+            label="System message",
+        ),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -62,3 +64,4 @@ demo = gr.ChatInterface(
 
 if __name__ == "__main__":
     demo.launch()
+