Docker项目：ChatGPT API 平台
视频被吞了，可以前往 xx 自行观看（xx和刘华强、郝哥有一定的关系）
自行搭建
复制下列代码，并自行修改配置
version: '3'
services:
web:
image: sengedev/chatgpt:latest
ports:
- "5000:5000"
volumes:
- ./app:/app
restart: always
environment:
API_KEY: YourOpenAIApiKey
HOUR_LIMIT: 50
MINUTE_LIMIT: 3
SECOND_LIMIT: 1
ROUTE: chatgpt
字段含义
字段含义volumes持久化配置，文件映射API_KEYAPI密钥，配置后无需请求头即可完成调用，不建议设置，除非你开启了IP地址白名单HOUR_LIMIT每小时调用次数限制，如果设置为0则无限制MINUTE_LIMIT每分钟调用次数限制，如果设置为0则无限制SECOND_LIMIT每秒调用次数限制，如果设置为0则无限制ROUTE例如你的网站是https://api.example.com，路由为route，则请求链接为https://api.example.com/route
实例介绍
使用教程
下方是一个示例API地址，请替换为您自己的IP/域名。
API链接: https://api.example.com/
获取ChatGPT回答
请求方式：GET，路由：/chatgpt
请求头
ApiKey：ChatGPT的API密钥，不允许为空，除非在docker-compose中声明了你的密钥
Model：ChatGPT API模型，默认使用text-davinci-003模型，允许为空
请求数据
prompt：向ChatGPT发送的文本，不允许为空
返回值
成功
{
"code": 200,
"msg": "success",
"data": {
"response": "ChatGPT回答的内容"
}
}
失败
{
"code": 4xx,
"msg": "failed",
"data": {
"response": "请求失败的原因"
}
}
常见返回值
code描述200成功400请求参数错误(API未填写或填写错误、模型使用错误、缺少prompt或prompt为空)401未授权403禁止访问404请求路径不存在500服务器内部错误429请求过于频繁
默认调用次数限制（每个IP）
API完全开放使用，无需申请，但是需要自行申请API Key
时间段频率天无限制小时50次分钟3次秒1次
示例代码
将https://api.example.com替换为你的服务器IP/域名地址
Python
import requests
url = "https://api.example.com/chatgpt"
headers = {
"ApiKey": "YourApiKey",
"Model": "text-davinci-003"
}
params = {
"prompt": "Hello"
}
response = requests.get(url, headers=headers, params=params)
print(response.json()["data"]["response"])
Java
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.Response;
import java.io.IOException;
public class ChatGPTClient {
public static void main(String[] args) throws IOException {
OkHttpClient client = new OkHttpClient();
String apiKey = "YourApiKey";
String model = "text-davinci-003";
String prompt = "Hello";
String url = "https://api.example.com/chatgpt?prompt=" + prompt;
Request request = new Request.Builder()
.url(url)
.addHeader("ApiKey", apiKey)
.addHeader("Model", model)
.get()
.build();
Response response = client.newCall(request).execute();
System.out.println(response.body().string());
}
}
JavaScript
const axios = require('axios');
const url = "https://api.example.com/chatgpt";
const apiKey = "YourApiKey";
const model = "text-davinci-003";
const prompt = "Hello";
axios.get(url, {
headers: {
ApiKey: apiKey,
Model: model
},
params: {
prompt: prompt
}
})
.then(response => {
console.log(response.data.data.response);
})
.catch(error => {
console.log(error.response.data.data.response);
});
curl
curl -H "ApiKey: YourApiKey" -H "Model: text-davinci-003" -X GET "https://api.example.com/chatgpt?prompt=Hello"
GoLang
package main
import (
"fmt"
"net/http"
"io/ioutil"
)
func main() {
url := "https://api.example.com/chatgpt?prompt=Hello"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("ApiKey", "YourApiKey")
req.Header.Add("Model", "text-davinci-003")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := ioutil.ReadAll(res.Body)
fmt.Println(string(body))
}
PHP
<?php
$url = "https://api.example.com/chatgpt";
$apiKey = "YourApiKey";
$model = "text-davinci-003";
$prompt = "Hello";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url . "?prompt=" . $prompt);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, array(
"ApiKey: " . $apiKey,
"Model: " . $model
));
$response = curl_exec($ch);
curl_close($ch);
$response = json_decode($response, true);
echo $response["data"]["response"];
?>
