langtest.modelhandler.lmstudio_modelhandler.chat_completion_api#

chat_completion_api(text: str, url: str, server_prompt: str, **kwargs)#

Send a user text message to a chat completion API and receive the model’s response.

Parameters:

  • text (str) – The user’s input text.

  • url (str) – The API endpoint URL.

  • **kwargs – Additional keyword arguments.

Keyword Arguments:

  • server_prompt (str, optional) – The server prompt for the chat. Defaults to a space.

  • temperature (float, optional) – The temperature parameter for controlling randomness. Defaults to 0.7.

  • max_tokens (int, optional) – The maximum number of tokens to generate. Defaults to -1 (no limit).

  • stream (bool, optional) – Whether to use streaming for long conversations. Defaults to False.

Returns:

The JSON response from the API if successful, otherwise None.

Return type:

dict or None