how standalone question is exactly formulated?-> I'm using different than English language, does it work for non-english languages?

We just send the conversation history with the following prompt structure:

Rewrite the follow-up question on top of a human-assistant conversation history as a standalone question that encompasses all pertinent context.
<Conversation history in format of role-message>

So even though prompt before the conversation history is English, I think the LLM should be able to extract standalone question for non-English conversation histories.