model_path = "/data1/yuyr/models--bytedance-research--UI-TARS-7B-DPO/snapshots/727b0df39207dafc6cf211a61f29d84b7659c39c/"

# 打开图片
# image_path = "file:///data1/yuyr/crawlee/screenshots/0fuABgATggRcGam_57.png"
image_path = "/data1/yuyr/crawlee/aaa5.png"

import base64

def encode_image_to_base64(image_path):
    """
    将图片编码为base64字符串
    """
    try:
        with open(image_path, "rb") as image_file:
            return base64.b64encode(image_file.read()).decode('utf-8')
    except Exception as e:
        print(f"图片编码失败: {e}")
        return None

image_base64 = encode_image_to_base64(image_path)

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

# 从本地加载模型
model = Qwen2VLForConditionalGeneration.from_pretrained(
    model_path, torch_dtype="auto", device_map="cuda:0"
)

# 从本地加载processor
processor = AutoProcessor.from_pretrained(model_path)

# 设置消息，这里图片使用本地png文件路径
messages = [
    {
                "role": "system",
                "content": """You are a GUI agent. You are given a task and your action history, with screenshots. You need to perform the next action to complete the task. 

## Output Format
```
Thought: ...
Action: ...
```

## Action Space
click(start_box='<|box_start|>(x1,y1)<|box_end|>')
left_double(start_box='<|box_start|>(x1,y1)<|box_end|>')
right_single(start_box='<|box_start|>(x1,y1)<|box_end|>')
drag(start_box='<|box_start|>(x1,y1)<|box_end|>', end_box='<|box_start|>(x3,y3)<|box_end|>')
hotkey(key='')
type(content='') #If you want to submit your input, use \"\" at the end of `content`.
scroll(start_box='<|box_start|>(x1,y1)<|box_end|>', direction='down or up or right or left')
wait() #Sleep for 5s and take a screenshot to check for any changes.
finished()
call_user() # Submit the task and call the user when the task is unsolvable, or when you need the user's help.

## Note
- Use Chinese in `Thought` part.
- Summarize your next action (with its target element) in one sentence in `Thought` part."""
    },
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image_url": f"file://{image_path}"
            },
            {"type": "text", "text": "点击购物"},
        ],
    }
]

# 准备推理输入
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to(model.device)

# 推理：生成输出
generated_ids = model.generate(**inputs, max_new_tokens=1024)
print(f"generated_ids: {generated_ids}")
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
print(f"generated_ids_trimmed: {generated_ids_trimmed}")
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(f"output_text: {output_text}")