Linux免费调用API部署AI大模型(GLM-4 版)

1.登录智谱官网
https://bigmodel.cn/console/overview

2.api接入
点击控制台api接入

3.创建复制api key

4.安装python3（Ubuntu）
更新软件包列表
sudo apt update && sudo apt upgrade -y
安装Python3
sudo apt install python3
验证安装
python3 --version

5.编写python脚本
` 创建执行脚本
直接在终端复制并运行以下命令，这会将代码写入 /usr/local/bin/AI：

cat <<'EOF' > /usr/local/bin/AI

!/usr/bin/env python3

import requests
import sys
import json

这里填入你刚才测试成功的 API Key

API_KEY = ""
URL = "https://open.bigmodel.cn/api/paas/v4/chat/completions"

def main():
if len(sys.argv) < 2:
print("用法: AI '你的问题'")
return

prompt = sys.argv[1]
headers = {"Content-Type": "application/json","Authorization": f"Bearer {API_KEY}"
}
data = {"model": "glm-4","messages": [{"role": "user", "content": prompt}],"stream": True 
}try:# 设置 stream=True 实时获取回答response = requests.post(URL, headers=headers, json=data, stream=True, timeout=30)if response.status_code == 200:for line in response.iter_lines():if line:line_str = line.decode('utf-8')if line_str.startswith("data: "):content = line_str[6:]if content != "[DONE]":chunk = json.loads(content)delta = chunk['choices'][0]['delta'].get('content', '')print(delta, end="", flush=True)print() else:print(f"\nAPI报错: {response.status_code}")
except Exception as e:print(f"\n连接异常: {e}")

if name == "main":
main()
EOF
`
6. 赋予权限并设为快捷命令

赋予执行权限

chmod +x /usr/local/bin/AI

7.设置别名，让你输入小写的 ai 也能运行
echo "alias ai='/usr/local/bin/AI'" >> ~/.bashrc

8.命令行输入能中文
export LANG="en_US.UTF-8"
export LC_ALL="en_US.UTF-8"

使配置生效

source ~/.bashrc

效果