使用Nginx代理Gemini

记录一下使用Nginx代理Gemini，可以大陆访问和调用Gemini

主要有以下步骤：

Gemini相关

1. 查找Gemini 官方文档

   • 找到调用API中Openai兼容性这一块
   • Python为例

     from openai import OpenAI
     
     client = OpenAI(
         api_key="GEMINI_API_KEY",
         base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
     )
     
     response = client.chat.completions.create(
         model="gemini-2.0-flash",
         n=1,
         messages=[
             {"role": "system", "content": "You are a helpful assistant."},
             {
                 "role": "user",
                 "content": "Explain to me how AI works"
             }
         ]
     )
     
     print(response.choices[0].message)

2. 创建Gemini API KEY

   • 记住AP_KEY后续调用时候用到

Nginx配置

sudo vim /etc/nginx/sites-available/default

在你已有的域名服务server下增加:

location /gemini/v1beta/openai/ {
        proxy_pass https://generativelanguage.googleapis.com/v1beta/openai/;
        proxy_set_header Host generativelanguage.googleapis.com;

        client_max_body_size 10M;  # 记得设置nginx上传文件大小，不然图片理解功能会被卡住
        proxy_buffering off;
        proxy_cache off;
        proxy_request_buffering off;
        # 保持长连接
        proxy_http_version 1.1;
        proxy_set_header Connection "";
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "Upgrade";
        # 透传关键头信息
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;

        # 调整超时（按需设置）
        proxy_read_timeout 3600s;  # 长流式请求需要更长时间
}

上述配置实现了流式和非流式调用，亲测可用。调用地址则为: https://www.xx.com/gemini/v1beta/openai/ 替换为你自己域名即可。

附Python调用示例:

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://www.xx.com/gemini/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-2.0-flash",
    n=1,
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ],
    stream=Flase
)

print(response.choices[0].message)