from langchain_community.chat_models import ChatTongyifrom langchain_core.messages import HumanMessagechatLLM = ChatTongyi(model_name="qwen-vl-max")image_message = {    "image": "https://lilianweng.github.io/posts/2023-06-23-agent/agent-overview.png",}text_message = {    "text": "summarize this picture",}message = HumanMessage(content=[text_message, image_message])chatLLM.invoke([message])

content=[{'text': '图中是一位身穿黄色衣服的女子站在床边喂一个男人喝药。女人身穿一身黄色旗袍，上面绣着精美的花纹。男人躺在床上似乎很虚弱的样子。'}] response_metadata={'model_name': 'qwen-vl-max', 'finish_reason': 'stop', 'request_id': '777814e2-873c-93c8-a280-eea5e91f59f1', 'token_usage': {'input_tokens': 335, 'output_tokens': 39, 'image_tokens': 299}} id='run-7708852a-7069-4940-9b25-9bcda0e99e10-0'

from PIL import Imageimport requestsimport torchfrom torchvision import iofrom typing import Dictfrom transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessorfrom modelscope import snapshot_downloadfrom utils import debugmodel_dir = snapshot_download("qwen/Qwen2-VL-7B-Instruct")# Load the model in half-precision on the available device(s)model = Qwen2VLForConditionalGeneration.from_pretrained(    model_dir, torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(model_dir)
def test_image():    # Image    url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"    image = Image.open(requests.get(url, stream=True).raw)    conversation = [        {            "role": "user",            "content": [                {                    "type": "image",                },                {"type": "text", "text": "Describe this image."},            ],        }    ]    # Preprocess the inputs    text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)    # Excepted output: '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Describe this image.<|im_end|>\n<|im_start|>assistant\n'    inputs = processor(        text=[text_prompt], images=[image], padding=True, return_tensors="pt"    )    inputs = inputs.to("cuda")    # Inference: Generation of the output    output_ids = model.generate(**inputs, max_new_tokens=128)    generated_ids = [        output_ids[len(input_ids):]        for input_ids, output_ids in zip(inputs.input_ids, output_ids)    ]    output_text = processor.batch_decode(        generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True    )    debug(output_text)