[WIP] Support video inputs

[CUHKSZzxy]

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video_url",
                "video_url": {
                    "url": "https://huggingface.co/datasets/TencentARC/ShortVid-Bench/blob/main/videos/-H5Yu7-Zb90.mp4"
                }
            },
            {"type": "text", "text": "Describe this video."},
        ],
    }
]