一人挑战一支研发团队，3步搞定全栈开发

创建一个全栈网站，前端用 Vite+React，后端用 Node.js+Express。后端监听 3000 端口，前端开发服务器运行在5173端口。前后端分离，支持跨域。
要求:
1.用户上传一张图片，会通过阿里云 OSS获取临时URL。
2.通过API Key调用大模型通义万相2.1-图生视频-Plus生成舞蹈视频。

获取临时URL: 在调用前，需要获取API Key，再配置API Key到环境变量。

请安装必要的依赖包。
pip install -U requests

输入参数
api_key：阿里云百炼API KEY。
model_name：指定文件将要用于哪个模型，如qwen-vl-plus。
file_path：待上传的本地文件路径（图片、视频等）。

示例代码
import os
import requests
from pathlib import Path
from datetime import datetime, timedelta

def get_upload_policy(api_key, model_name):
    """获取文件上传凭证"""
    url = "https://dashscope.aliyuncs.com/api/v1/uploads"
    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json"
    }
    params = {
        "action": "getPolicy",
        "model": model_name
    }
    
    response = requests.get(url, headers=headers, params=params)
    if response.status_code != 200:
        raise Exception(f"Failed to get upload policy: {response.text}")
    
    return response.json()['data']
def upload_file_to_oss(policy_data, file_path):
    """将文件上传到临时存储OSS"""
    file_name = Path(file_path).name
    key = f"{policy_data['upload_dir']}/{file_name}"
    
    with open(file_path, 'rb') as file:
        files = {
            'OSSAccessKeyId': (None, policy_data['oss_access_key_id']),
            'Signature': (None, policy_data['signature']),
            'policy': (None, policy_data['policy']),
            'x-oss-object-acl': (None, policy_data['x_oss_object_acl']),
            'x-oss-forbid-overwrite': (None, policy_data['x_oss_forbid_overwrite']),
            'key': (None, key),
            'success_action_status': (None, '200'),
            'file': (file_name, file)
        }
        
        response = requests.post(policy_data['upload_host'], files=files)
        if response.status_code != 200:
            raise Exception(f"Failed to upload file: {response.text}")
    
    return f"oss://{key}"
def upload_file_and_get_url(api_key, model_name, file_path):
    """上传文件并获取URL"""
    # 1. 获取上传凭证，上传凭证接口有限流，超出限流将导致请求失败
    policy_data = get_upload_policy(api_key, model_name) 
    # 2. 上传文件到OSS
    oss_url = upload_file_to_oss(policy_data, file_path)
    
    return oss_url
# 使用示例if __name__ == "__main__":
    # 从环境变量中获取API Key 或者 在代码中设置 api_key = "your_api_key"
    api_key = os.getenv("DASHSCOPE_API_KEY")
    ifnot api_key:
        raise Exception("请设置DASHSCOPE_API_KEY环境变量")
        
    # 设置model名称
    model_name="qwen-vl-plus"

    # 待上传的文件路径
    file_path = "/tmp/cat.png"  # 替换为实际文件路径
    
    try:
        public_url = upload_file_and_get_url(api_key, model_name, file_path)
        expire_time = datetime.now() + timedelta(hours=48)
        print(f"文件上传成功，有效期为48小时，过期时间: {expire_time.strftime('%Y-%m-%d %H:%M:%S')}")
        print(f"临时URL: {public_url}")

    except Exception as e:
        print(f"Error: {str(e)}")
输出示例
 文件上传成功，有效期为48小时，过期时间: 2024-07-1817:36:15
临时URL: oss://dashscope-instant/xxx/2024-07-18/xxx/cat.png


调用大模型图生视频（使用视频特效）：
使用视频特效时，prompt字段无效，无需填写。
template值为：dance2
示例代码：
curl --location 'https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis' \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "通义万相2.1-图生视频-turbo",
    "input": {
        "prompt": "",
        "img_url": "https://cdn.translate.alibaba.com/r/wan-demo-1.png",
        "template": "flying"
    },
    "parameters": {
        "resolution": "720P"
    }
}'

DASHSCOPE_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxx

cd frontendnpm 
run dev

提示词：用我给你的组件代码应用到前端布局，不改变逻辑。