其他
Spring Boot 整合 ChatGPT API 项目实战，十分钟快速搞定！
"model": "text-davinci-003",
"prompt": "Say this is a test",
"max_tokens": 7,
"temperature": 0,
"top_p": 1,
"n": 1,
"stream": false
}
<html class="no-js" lang="">
<head>
<meta charset="utf-8">
<meta http-equiv="x-ua-compatible" content="ie=edge">
<title>Ai - Chat</title>
<meta name="description" content="">
<meta name="viewport" content="width=device-width, initial-scale=1">
<style>
#chatgpt-response {
font-family: "宋体";
font-size: 20px;
color: #0000FF;
font-weight: bold;
}
</style>
<script>
async function callCHATGPT() {
var responseText1 = document.getElementById("chatgpt-response");
responseText1.innerHTML = ""
function printMessage(message) {
var responseText = document.getElementById("chatgpt-response");
var index = 0;
// 创建一个定时器，每隔一段时间打印一个字符
var interval = setInterval(function() {
responseText.innerHTML += message[index];
index++;
// 当打印完成时，清除定时器
if (index >= message.length) {
clearInterval(interval);
}
},
150); // 每隔50毫秒打印一个字符
}
var xhr = new XMLHttpRequest();
var url = "https://api.openai.com/v1/completions";
xhr.open("POST", url, true);
xhr.setRequestHeader("Content-Type", "application/json");
xhr.setRequestHeader("Authorization", "Bearer API-KEY");
xhr.onreadystatechange = function() {
if (xhr.readyState === 4 && xhr.status === 200) {
var json = JSON.parse(xhr.responseText);
var response = json.choices[0].text;
// 将CHATGPT的返回值输出到文本框
var responseText = document.getElementById("chatgpt-response");
var index = 0;
// 创建一个定时器，每隔一段时间打印一个字符
var interval = setInterval(function() {
responseText.innerHTML += response[index];
index++;
// 当打印完成时，清除定时器
if (index >= response.length) {
clearInterval(interval);
}
},
50); // 每隔50毫秒打印一个字符
}
};
var data = JSON.stringify({
"prompt": document.getElementById("chat-gpt-input").value,
"max_tokens": 2048,
"temperature": 0.5,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0,
"model": "text-davinci-003"
});
console.log(data);
await printMessage('正在思考，请等待......');
await xhr.send(data);
}
</script>
</head>
<body>
<div class="filter-menu text-center mb-40">
<h4>与Ai对话，请描述您的需求-支持中文、英语、日本语等</h4>
</div>
<textarea class="form-control" id="chat-gpt-input" placeholder="输入描述" rows="3" resize="none"
style="width: 135%; margin: 0 auto; background-color: #f4f4f4; color: #333; border: 1px solid #ccc; border-radius: 12px;"></textarea>
<button onclick="callCHATGPT()" autocomplete="off" class="btn btn-large" href="#"
style="background-color: #333; color: #f4f4f4; border-radius: 10px">
<span class="spinner-border spinner-border-sm" role="status" aria-hidden="true"></span>回答
</button>
<textarea class="form-control" id="chatgpt-response"
placeholder="请耐心等待回答 Ai生成它很快，但是由于网络问题我们需要等待，通常内容越长等待越久 如果长时间没反应请刷新页面重试" rows="26" resize="none"
style="width: 150%;height: auto; margin: 0 auto; background-color: #f4f4f4; color: #333; border: 1px solid #ccc; border-radius: 10px; overflow: scroll;"
readonly="true"></textarea>
<groupId>com.theokanning.openai-gpt3-java</groupId>
<artifactId>service</artifactId>
<version>0.10.0</version>
</dependency>
OpenAiService service = new OpenAiService(token);
CompletionRequest completionRequest = CompletionRequest.builder()
.model("text-davinci-003")
.prompt("今天天气怎么样？")
.temperature(0.5)
.maxTokens(2048)
.topP(1D)
.frequencyPenalty(0D)
.presencePenalty(0D)
.build();
service.createCompletion(completionRequest).getChoices().forEach(System.out::println);
我就是我，是与众不同的小苹果。
END
往期精彩一款现代化的开源内存数据库，性能是 Redis 的 25 倍，且完全兼容Redis！
Spring Boot 优雅停止服务的几种方法
在 MySQL 中使用枚举的陷阱一定要注意！
Spring Boot 启动时自动执行代码的几种方式，还有谁不会？？