Method convert_inputs_to_api_kwargs

api/openai_client.py:270–382

r""" Specify the API input type and output api_kwargs that will be used in _call and _acall methods. Convert the Component's standard input, and system_input(chat model) and model_kwargs into API-specific format. For multimodal inputs, images can be provided in model_kwargs["

(
        self,
        input: Optional[Any] = None,
        model_kwargs: Dict = {},
        model_type: ModelType = ModelType.UNDEFINED,
    )

            return EmbedderOutput(data=[], error=str(e), raw_response=response)

    def convert_inputs_to_api_kwargs(
        self,
        input: Optional[Any] = None,
        model_kwargs: Dict = {},
        model_type: ModelType = ModelType.UNDEFINED,
    ) -> Dict:
        r"""
        Specify the API input type and output api_kwargs that will be used in _call and _acall methods.
        Convert the Component's standard input, and system_input(chat model) and model_kwargs into API-specific format.
        For multimodal inputs, images can be provided in model_kwargs["images"] as a string path, URL, or list of them.
        The model specified in model_kwargs["model"] must support multimodal capabilities when using images.

        Args:
            input: The input text or messages to process
            model_kwargs: Additional parameters including:
                - images: Optional image source(s) as path, URL, or list of them
                - detail: Image detail level ('auto', 'low', or 'high'), defaults to 'auto'
                - model: The model to use (must support multimodal inputs if images are provided)
            model_type: The type of model (EMBEDDER or LLM)

        Returns:
            Dict: API-specific kwargs for the model call
        """

        final_model_kwargs = model_kwargs.copy()
        if model_type == ModelType.EMBEDDER:
            if isinstance(input, str):
                input = [input]
            # convert input to input
            if not isinstance(input, Sequence):
                raise TypeError("input must be a sequence of text")
            final_model_kwargs["input"] = input
        elif model_type == ModelType.LLM:
            # convert input to messages
            messages: List[Dict[str, str]] = []
            images = final_model_kwargs.pop("images", None)
            detail = final_model_kwargs.pop("detail", "auto")

            if self._input_type == "messages":
                system_start_tag = "<START_OF_SYSTEM_PROMPT>"
                system_end_tag = "<END_OF_SYSTEM_PROMPT>"
                user_start_tag = "<START_OF_USER_PROMPT>"
                user_end_tag = "<END_OF_USER_PROMPT>"

                # new regex pattern to ignore special characters such as \n
                pattern = (
                    rf"{system_start_tag}\s*(.*?)\s*{system_end_tag}\s*"
                    rf"{user_start_tag}\s*(.*?)\s*{user_end_tag}"
                )

                # Compile the regular expression

                # re.DOTALL is to allow . to match newline so that (.*?) does not match in a single line
                regex = re.compile(pattern, re.DOTALL)
                # Match the pattern
                match = regex.match(input)
                system_prompt, input_str = None, None