Python調用墨跡天氣API實踐指南
你可能也喜歡這些API文章!
在您的配置文件（application.properties）中，在屬性中設置 OpenAI 密鑰openai.api.key。您還可以在屬性文件中替換模型版本以使用不同的 API 版本，例如gpt-4o-mini。
spring.application.name=spring-openai
openai.api.url=https://api.openai.com/v1/chat/completions
openai.api.key=YOUR-OPENAI-API-KEY-GOES-HERE
openai.api.model=gpt-3.5-turbo通過 Java 連接此服務的一個棘手部分是，默認情況下，它將要求您的 HTTP 客戶端在執行此請求時使用有效證書。為了解決這個問題，我們將跳過此驗證步驟。
要禁用 JDK 對 HTTPS 請求所需的安全證書要求，您必須通過配置類在RestTemplate bean 中包含以下修改：
import org.apache.hc.client5.http.classic.HttpClient;
import org.apache.hc.client5.http.impl.classic.HttpClients;
import org.apache.hc.client5.http.impl.io.BasicHttpClientConnectionManager;
import org.apache.hc.client5.http.socket.ConnectionSocketFactory;
import org.apache.hc.client5.http.socket.PlainConnectionSocketFactory;
import org.apache.hc.client5.http.ssl.NoopHostnameVerifier;
import org.apache.hc.client5.http.ssl.SSLConnectionSocketFactory;
import org.apache.hc.core5.http.config.Registry;
import org.apache.hc.core5.http.config.RegistryBuilder;
import org.apache.hc.core5.ssl.SSLContexts;
import org.apache.hc.core5.ssl.TrustStrategy;
import org.springframework.boot.web.client.RestTemplateBuilder;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import org.springframework.http.client.HttpComponentsClientHttpRequestFactory;
import org.springframework.web.client.RestTemplate;
import javax.net.ssl.SSLContext;
@Configuration
public class SpringOpenAIConfig {
@Bean
public RestTemplate secureRestTemplate(RestTemplateBuilder builder) throws Exception {
// This configuration allows your application to skip the SSL check
final TrustStrategy acceptingTrustStrategy = (cert, authType) -> true;
final SSLContext sslContext = SSLContexts.custom()
.loadTrustMaterial(null, acceptingTrustStrategy)
.build();
final SSLConnectionSocketFactory sslsf =
new SSLConnectionSocketFactory(sslContext, NoopHostnameVerifier.INSTANCE);
final Registry<ConnectionSocketFactory> socketFactoryRegistry =
RegistryBuilder.<ConnectionSocketFactory>create()
.register("https", sslsf)
.register("http", new PlainConnectionSocketFactory())
.build();
final BasicHttpClientConnectionManager connectionManager =
new BasicHttpClientConnectionManager(socketFactoryRegistry);
HttpClient client = HttpClients.custom()
.setConnectionManager(connectionManager)
.build();
return builder
.requestFactory(() -> new HttpComponentsClientHttpRequestFactory(client))
.build();
}
}現在我們已經準備好了所有配置，是時候實現一個處理與 ChatGPT API 通信的服務了。我正在使用 Spring 組件RestTemplate，它允許執行對 OpenAI 端點的 HTTP 請求。
import org.springframework.beans.factory.annotation.Value;
import org.springframework.http.HttpEntity;
import org.springframework.http.HttpHeaders;
import org.springframework.http.HttpMethod;
import org.springframework.http.MediaType;
import org.springframework.stereotype.Service;
import org.springframework.web.client.RestTemplate;
@Service
public class JavaOpenAIService {
@Value("${openai.api.url}")
private String apiUrl;
@Value("${openai.api.key}")
private String apiKey;
@Value("${openai.api.model}")
private String modelVersion;
private final RestTemplate restTemplate;
public JavaOpenAIService(RestTemplate restTemplate) {
this.restTemplate = restTemplate;
}
/**
* Sends a request to the OpenAI API with the given prompt and returns the response.
*
* @param prompt the question to ask the AI
* @return the response in JSON format
*/
public String ask(String prompt) {
HttpEntity<String> entity = new HttpEntity<>(buildMessageBody(modelVersion, prompt), buildOpenAIHeaders());
return restTemplate
.exchange(apiUrl, HttpMethod.POST, entity, String.class)
.getBody();
}
private HttpHeaders buildOpenAIHeaders() {
HttpHeaders headers = new HttpHeaders();
headers.set("Authorization", "Bearer " + apiKey);
headers.set("Content-Type", MediaType.APPLICATION_JSON_VALUE);
return headers;
}
private String buildMessageBody(String modelVersion, String prompt) {
return String.format("{ \"model\": \"%s\", \"messages\": [{\"role\": \"user\", \"content\": \"%s\"}]}", modelVersion, prompt);
}
}然后，您可以創建自己的 REST API 來接收問題并將其重定向到您的服務。
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.bind.annotation.RestController;
import br.com.erakles.springopenai.service.SpringOpenService;
@RestController
public class SpringOpenAIController {
private final SpringOpenService springOpenService;
SpringOpenAIController(SpringOpenService springOpenService) {
this.springOpenService = springOpenService;
}
@GetMapping("/chat")
public ResponseEntity<String> sendMessage(@RequestParam String prompt) {
return ResponseEntity.ok(springOpenService.askMeAnything(prompt));
}
}這些是將您的 Web 應用程序與 OpenAI 服務集成所需的步驟，因此您以后可以通過添加更多功能（例如向其端點發送語音、圖像和其他文件）來改進它。
啟動 Spring Boot 應用程序 ( ./mvnw spring-boot:run) 后，要測試 Web 服務，您必須運行以下 URL http://localhost:8080/ask?promp={add-your-question}。
如果您所有操作正確，您將能夠在響應主體中讀取以下結果：
{
"id": "chatcmpl-9vSFbofMzGkLTQZeYwkseyhzbruXK",
"object": "chat.completion",
"created": 1723480319,
"model": "gpt-3.5-turbo-0125",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Scuba stands for \"self-contained underwater breathing apparatus.\" It is a type of diving equipment that allows divers to breathe underwater while exploring the underwater world. Scuba diving involves using a tank of compressed air or other breathing gas, a regulator to control the flow of air, and various other accessories to facilitate diving, such as fins, masks, and wetsuits. Scuba diving allows divers to explore the underwater environment and observe marine life up close.",
"refusal": null
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 90,
"total_tokens": 102
},
"system_fingerprint": null
}希望本教程能幫助您首次與 OpenAI 互動，讓您在深入 AI 之旅時生活更輕松。
原文鏈接：https://dzone.com/articles/integrate-spring-with-open-ai
