Method run

camel/models/sglang_model.py:181–215

r"""Runs inference of OpenAI chat completion. Args: messages (List[OpenAIMessage]): Message list with the chat history in OpenAI API format. Returns: Union[ChatCompletion, Stream[ChatCompletionChunk]]: `ChatCompletion` in the

(
        self,
        messages: List[OpenAIMessage],
    )

                )

    def run(
        self,
        messages: List[OpenAIMessage],
    ) -> Union[ChatCompletion, Stream[ChatCompletionChunk]]:
        r"""Runs inference of OpenAI chat completion.

        Args:
            messages (List[OpenAIMessage]): Message list with the chat history
                in OpenAI API format.

        Returns:
            Union[ChatCompletion, Stream[ChatCompletionChunk]]:
                `ChatCompletion` in the non-stream mode, or
                `Stream[ChatCompletionChunk]` in the stream mode.
        """

        # Ensure server is running
        self._ensure_server_running()

        with self._lock:
            # Update last run time
            self.last_run_time = time.time()

        if self._client is None:
            raise RuntimeError(
                "Client is not initialized. Ensure the server is running."
            )

        response = self._client.chat.completions.create(
            messages=messages,
            model=self.model_type,
            **self.model_config_dict,
        )

        return response

    @property
    def stream(self) -> bool: