Query Regarding API for Vicuna Model

Nobody has claimed this yet.

Hello LMSYS Team,

I am reaching out to inquire about the functionality of the Vicuna model.

I would like to know if there is an available API for Vicuna that allows me to input a string prompt to a function and get a string response as the return value, which would be the model's response.

In more specific terms, what I am looking for is something similar to:

```python
def vicuna_prompt(prompt):
# some API functionality here
response = vicuna_model.reply(prompt)
return response
```

This way, the given string prompt would be processed and the function would yield the response generated by the Vicuna model.

If supported, is there any example code?

If this functionality is not currently supported, do you have plans to implement it in the future? Or are there any workarounds to achieve this?

Looking forward to your feedback.

Thank you and best regards,
Yilei

The issue names no files, tests, or entry points. Start by checking the project's existing Vicuna serving and API documentation, then determine whether a prompt-to-response interface and example are already documented; done would mean a clear supported usage or documented limitation and workaround.

Written by the indexing model from the issue text.