使用视频推理报错

[ZHUHF123]

当前已更新vllm，Version: 0.6.6.post1
调用方式
curl -X POST http://10.19.196.71:10002/v1/chat/completions
-H 'Content-Type: application/json'
-d '{
"model": "Qwen2-VL-72B-Instruct",
"messages": [{"role": "user",
"content": [{"type": "video",
"video": ["https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/xzsgiz/football1.jpg",
"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/tdescd/football2.jpg",
"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/zefdja/football3.jpg",
"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/aedbqh/football4.jpg"]},
{"type": "text",
"text": "描述这个视频的具体过程"}]}]
}'

报错：
{"object":"error","message":"6 validation errors for ValidatorIterator\n0.typed-dict.text\n Field required [type=missing, input_value={'type': 'video', 'video'.../aedbqh/football4.jpg']}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.9/v/missing\n0.typed-dict.type\n Input should be 'text' [type=literal_error, input_value='video', input_type=str]\n For further information visit https://errors.pydantic.dev/2.9/v/literal_error\n0.typed-dict.image_url\n Field required [type=missing, input_value={'type': 'video', 'video'.../aedbqh/football4.jpg']}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.9/v/missing\n0.typed-dict.type\n Input should be 'image_url' [type=literal_error, input_value='video', input_type=str]\n For further information visit https://errors.pydantic.dev/2.9/v/literal_error\n0.typed-dict.input_audio\n Field required [type=missing, input_value={'type': 'video', 'video'.../aedbqh/football4.jpg']}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.9/v/missing\n0.typed-dict.type\n Input should be 'input_audio' [type=literal_error, input_value='video', input_type=str]\n For further information visit https://errors.pydantic.dev/2.9/v/literal_error","type":"BadRequestError"

[BearCooike]

Hello, I also encountered a similar problem. Have you found the reason for the error?

[ZHUHF123]

Hello, I also encountered a similar problem. Have you found the reason for the error?

我尝试了使用这个格式可以调用，当时官方示例的多图片检测还是不可以
{
"model": "Qwen2-VL-72B-Instruct",
"messages": [
   {
        "role": "user",
        "content": [
            {
                "type": "video_url",
                "video_url":{ 
                    "url": "https://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/baby.mp4"
                }
            },
            {
                "type": "text", 
                "text": "Describe this video."
            }
        ]
    }
  ]
}