Java calls the API interface of ChatGPT to realize dialogue and picture generation

Step 1: Configure the proxy

Some magic requires configuration. Otherwise, code testing cannot be implemented correctly. Here are the tools I use as an example.


Step 2: Add dependencies

Add in pom.xml file:

<dependency>
	<groupId>com.theokanning.openai-gpt3-java</groupId>
	<artifactId>client</artifactId>
	<version>0.8.1</version>
</dependency>

Step 3: Write the Constants class

  • In the Constants class, declare your own API Key
public class Constants {
    
    
//大家填写自己的key,这个是瞎写的,没有用的
public static final String OPENAPI_TOKEN = "sk-JPPwaelHv5QwdN3CL97UKLMbo7XIJDRy";
}

Among them, check the location of API Key:
https://platform.openai.com/account/api-keys
Balance query:
https://platform.openai.com/account/usage


Step 4: Implement Q&A interaction

package com.atguigu.demo;
import com.atguigu.Constants;
import com.theokanning.openai.OpenAiService;
import com.theokanning.openai.completion.CompletionRequest;

public class Demo1 {
    
    
public static void main(String[] args) {
    
    
	String info1 = "Q: 能不能我写一封简短的情话,使用诗经的语言风格?A:";
	info(info1);
}
public static void info(String promptInfo){
    
    
	//注意:参数2用于设置超时时间
	OpenAiService service = new OpenAiService(Constants.OPENAPI_TOKEN,5000);
	CompletionRequest completionRequest = CompletionRequest.builder()
	.model("text-davinci-003") //使用的模型
	.prompt(promptInfo) //生成提示
	.temperature(0D) //创新采样
	.maxTokens(1000) //Token大小设置
	.topP(1D) //情绪采样。[0,1]:从悲观到乐观
	.frequencyPenalty(0D) //频率处罚系数。用来设置文本中出现重复词汇时的处罚参数
	.presencePenalty(0D) //重复处罚系数
	.build();
	service.createCompletion(completionRequest)
	.getChoices()
	.forEach(System.out::println);
	}
}

Step 5: Implement image generation

package com.atguigu.demo;
import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import com.atguigu.Constants;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import java.io.IOException;

public class Demo2 {
    
    
public static void main(String[] args) throws IOException {
    
    
	String json = "{" +
		"\"prompt\":\"古装将军\"," +
		"\"n\":1," +
		"\"size\":\"1024x1024\"," +
		"\"response_format\":\"url\"" +
		"}";
		show(json);
		}
		public static void show(String json) throws IOException{
    
    
		Document document =
		Jsoup.connect("https://api.openai.com/v1/images/generations")
		.header("Authorization", "Bearer " + Constants.OPENAPI_TOKEN)
		.header("Content-Type", "application/json")
		.ignoreHttpErrors(true)
		.ignoreContentType(true)
		.requestBody(json)
		.post();
		JSONObject jsonObject = JSON.parseObject(document.body().text());
		JSONArray data = jsonObject.getJSONArray("data");
		for (int i = 0; i < data.size(); i++) {
    
    
		JSONObject temp = data.getJSONObject(i);
		System.out.println(temp.get("url"));
		}
	}
}

Dependencies need to be added to the pom.xml file:

<dependency>
	<groupId>org.jsoup</groupId>
	<artifactId>jsoup</artifactId>
	<version>1.14.3</version>
</dependency>
<dependency>
	<groupId>com.alibaba</groupId>
	<artifactId>fastjson</artifactId>
	<version>1.2.76</version>
</dependency>

Guess you like

Origin blog.csdn.net/qq_57163366/article/details/132746866