INNER CODE UNIT · Python

embedding

triton-inference-server/server · python/openai/openai_frontend/engine/engine.py:98

    async def embedding(
        self, request: CreateEmbeddingRequest
    ) -> CreateEmbeddingResponse:
        """
        Returns a CreateEmbeddingResponse.
        """
        pass

    async def load_model(self, model_name: str) -> Model:
        """
        Loads a model by name. Only available in EXPLICIT model control mode.
        Blocks until the model is fully loaded and ready, matching standard
        Triton server load behavior.
        """
        pass

    async def unload_model(self, model_name: str) -> None:
        """

View source record →