usersimcrs.llm_interfaces.openai_interface
==========================================

.. py:module:: usersimcrs.llm_interfaces.openai_interface

.. autoapi-nested-parse::

   Interface to use a LLM served by OpenAI.



Classes
-------

.. autoapisummary::

   usersimcrs.llm_interfaces.openai_interface.OpenAILLMInterface


Module Contents
---------------

.. py:class:: OpenAILLMInterface(configuration_path: str, use_chat_api: bool = False, default_response: str = None)

   Bases: :py:obj:`usersimcrs.llm_interfaces.llm_interface.LLMInterface`


   Initializes interface for OpenAI served LLM.

   :param configuration_path: Path to the configuration file.
   :param use_chat_api: Whether to use the chat or completion API. Defaults to
                        False (i.e., completion API).
   :param default_response: Default response to be used if the LLM fails to
                            generate a response.

   :raises FileNotFoundError: If the configuration file is not found.


   .. py:attribute:: model


   .. py:attribute:: client


   .. py:attribute:: use_chat_api
      :value: False



   .. py:method:: generate_utterance(prompt: usersimcrs.simulator.llm.prompt.utterance_generation_prompt.UtteranceGenerationPrompt) -> dialoguekit.core.Utterance

      Generates a user utterance given a prompt.

      :param prompt: Prompt for generating the utterance.

      :returns: Utterance in natural language.



   .. py:method:: get_llm_api_response(prompt: str, initial_prompt: str = None) -> str

      Gets the raw response from the LLM API.

      This method should be used to interact directly with the LLM API, i.e.,
      for everything that is not related to the generation of an utterance.

      :param prompt: Prompt for the LLM.
      :param initial_prompt: Initial prompt for the chat API. Defaults to None.

      :returns: Response from the LLM API without any post-processing.