Update app.py

app.py

@@ -36,15 +36,24 @@ def respond(
     )
     
     for chunk in stream:
-        if chunk.choices[0].delta.content is not None:
-            response += chunk.choices[0].delta.content
-            yield response
+        # Extract content from the chunk
+        if 'choices' in chunk and len(chunk['choices']) > 0:
+            if 'text' in chunk['choices'][0]:
+                content = chunk['choices'][0]['text']
+            elif 'delta' in chunk['choices'][0] and 'content' in chunk['choices'][0]['delta']:
+                content = chunk['choices'][0]['delta']['content']
+            else:
+                continue
+                
+            if content is not None:
+                response += content
+                yield response
 
 # Create the Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a helpful AI assistant.", label="System prompt"),
+        gr.Textbox(value="(Answer on the language of the user)", label="System prompt"),
         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(