optimum/intel/openvino/modeling_visual_language.py [2882:2912]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @staticmethod
    def preprocess_inputs(
        text: str,
        image: Optional["Image"] = None,
        processor: Optional[AutoImageProcessor] = None,
        tokenizer: Optional[PreTrainedTokenizer] = None,
        config: Optional[PretrainedConfig] = None,
        video: Optional["VideoInput"] = None,
        audio: Optional[np.ndarray] = None,
    ):
        if processor is None:
            raise ValueError("Processor is required.")
        if audio is not None:
            raise ValueError("Audio input is not supported")
        conversation = [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": text},
                ],
            }
        ]
        if image is not None:
            conversation[0]["content"].insert(0, {"type": "image"})
        if video is not None:
            conversation[0]["content"].insert(0, {"type": "video"})

        text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

        inputs = processor(images=image, text=text_prompt, videos=video, return_tensors="pt")
        return inputs
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/intel/openvino/modeling_visual_language.py [3321:3351]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @staticmethod
    def preprocess_inputs(
        text: str,
        image: Optional["Image"] = None,
        processor: Optional[AutoImageProcessor] = None,
        tokenizer: Optional[PreTrainedTokenizer] = None,
        config: Optional[PretrainedConfig] = None,
        video: Optional["VideoInput"] = None,
        audio: Optional[np.ndarray] = None,
    ):
        if processor is None:
            raise ValueError("Processor is required.")
        if audio is not None:
            raise ValueError("Audio input is not supported")
        conversation = [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": text},
                ],
            }
        ]
        if image is not None:
            conversation[0]["content"].insert(0, {"type": "image"})
        if video is not None:
            conversation[0]["content"].insert(0, {"type": "video"})

        text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

        inputs = processor(images=image, text=text_prompt, videos=video, return_tensors="pt")
        return inputs
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -