resource not found with Azure OpenAI service

营赢盈英2024-08-11 19:55

题意：使用 Azure OpenAI 服务时，系统未能找到所请求的资源

问题背景：

when I am using this demo code to use the Azure OpenAI service in Java 11:

当我在Java 11环境中使用这段示例代码来调用Azure OpenAI服务时：

cs 复制代码 
package com.dolphin.soa.post.config.ai.azure;

import com.azure.ai.openai.OpenAIClient;
import com.azure.ai.openai.OpenAIClientBuilder;
import com.azure.ai.openai.models.*;
import com.azure.core.credential.AzureKeyCredential;
import lombok.extern.slf4j.Slf4j;
import org.springframework.stereotype.Component;

import java.util.ArrayList;
import java.util.List;

@Slf4j
public class AzureOpenAIClient {

    public static void getChatCompletion(){
        String azureOpenaiKey = "the-key";
        String endpoint = "https://reddwarfcv.openai.azure.com/";
        String deploymentOrModelId = "gpt-35-turbo";

        OpenAIClient client = new OpenAIClientBuilder()
                .endpoint(endpoint)
                .credential(new AzureKeyCredential(azureOpenaiKey))
                .buildClient();

        List<ChatMessage> chatMessages = new ArrayList<>();
        chatMessages.add(new ChatMessage(ChatRole.SYSTEM).setContent("You are a helpful assistant."));
        chatMessages.add(new ChatMessage(ChatRole.USER).setContent("Does Azure OpenAI support customer managed keys?"));
        chatMessages.add(new ChatMessage(ChatRole.ASSISTANT).setContent("Yes, customer managed keys are supported by Azure OpenAI?"));
        chatMessages.add(new ChatMessage(ChatRole.USER).setContent("Do other Azure Cognitive Services support this too?"));

        ChatCompletions chatCompletions = client.getChatCompletions(deploymentOrModelId, new ChatCompletionsOptions(chatMessages));

        System.out.printf("Model ID=%s is created at %d.%n", chatCompletions.getId(), chatCompletions.getCreated());
        for (ChatChoice choice : chatCompletions.getChoices()) {
            ChatMessage message = choice.getMessage();
            System.out.printf("Index: %d, Chat Role: %s.%n", choice.getIndex(), message.getRole());
            System.out.println("Message:");
            System.out.println(message.getContent());
        }

        System.out.println();
        CompletionsUsage usage = chatCompletions.getUsage();
        System.out.printf("Usage: number of prompt token is %d, "
                        + "number of completion token is %d, and number of total tokens in request and response is %d.%n",
                usage.getPromptTokens(), usage.getCompletionTokens(), usage.getTotalTokens());
    }

    public static void main(String[] args) {
        getChatCompletion();
    }

}

show error: 显示错误：

cs 复制代码 
com.azure.core.exception.ResourceNotFoundException: Status code 404, "{"error":{"code":"DeploymentNotFound", "message":"The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again."}}"
Exception in thread "main"  at com.azure.core.implementation.http.rest.RestProxyBase.instantiateUnexpectedException(RestProxyBase.java:347)
    at com.azure.core.implementation.http.rest.SyncRestProxy.ensureExpectedStatus(SyncRestProxy.java:130)
    at com.azure.core.implementation.http.rest.SyncRestProxy.handleRestReturnType(SyncRestProxy.java:213)
com.azure.core.exception.ResourceNotFoundException: Status code 404, "{"error":{"code":"DeploymentNotFound", "message":"The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again."}}"
    at com.azure.core.implementation.http.rest.RestProxyBase.instantiateUnexpectedException(RestProxyBase.java:347)
    at com.azure.core.implementation.http.rest.SyncRestProxy.ensureExpectedStatus(SyncRestProxy.java:130)
    at com.azure.core.implementation.http.rest.SyncRestProxy.handleRestReturnType(SyncRestProxy.java:213)
    at com.azure.core.implementation.http.rest.SyncRestProxy.invoke(SyncRestProxy.java:81)
    at com.azure.core.implementation.http.rest.SyncRestProxy.invoke(SyncRestProxy.java:81)
    at com.azure.core.implementation.http.rest.RestProxyBase.invoke(RestProxyBase.java:109)
    at com.azure.core.http.rest.RestProxy.invoke(RestProxy.java:91)
    at jdk.proxy2/jdk.proxy2.$Proxy3.getChatCompletionsSync(Unknown Source)
    at com.azure.core.implementation.http.rest.RestProxyBase.invoke(RestProxyBase.java:109)
    at com.azure.ai.openai.implementation.OpenAIClientImpl.getChatCompletionsWithResponse(OpenAIClientImpl.java:757)
    at com.azure.core.http.rest.RestProxy.invoke(RestProxy.java:91)
    at jdk.proxy2/jdk.proxy2.$Proxy3.getChatCompletionsSync(Unknown Source)
    at com.azure.ai.openai.implementation.OpenAIClientImpl.getChatCompletionsWithResponse(OpenAIClientImpl.java:757)
    at com.azure.ai.openai.OpenAIClient.getChatCompletionsWithResponse(OpenAIClient.java:255)
    at com.azure.ai.openai.OpenAIClient.getChatCompletionsWithResponse(OpenAIClient.java:255)
    at com.azure.ai.openai.OpenAIClient.getChatCompletions(OpenAIClient.java:381)
    at com.dolphin.soa.post.config.ai.azure.AzureOpenAIClient.getChatCompletion(AzureOpenAIClient.java:37)
    at com.azure.ai.openai.OpenAIClient.getChatCompletions(OpenAIClient.java:381)
    at com.dolphin.soa.post.config.ai.azure.AzureOpenAIClient.main(AzureOpenAIClient.java:55)
    at com.dolphin.soa.post.config.ai.azure.AzureOpenAIClient.getChatCompletion(AzureOpenAIClient.java:37)
    at com.dolphin.soa.post.config.ai.azure.AzureOpenAIClient.main(AzureOpenAIClient.java:55)
13:35:44.075 [main] ERROR com.azure.core.implementation.http.rest.RestProxyBase - Status code 404, "{"error":{"code":"DeploymentNotFound", "message":"The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again."}}"
com.azure.core.exception.ResourceNotFoundException: Status code 404, "{"error":{"code":"DeploymentNotFound", "message":"The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again."}}"
    at com.azure.core.implementation.http.rest.RestProxyBase.instantiateUnexpectedException(RestProxyBase.java:347)
    at com.azure.core.implementation.http.rest.SyncRestProxy.ensureExpectedStatus(SyncRestProxy.java:130)
    at com.azure.core.implementation.http.rest.SyncRestProxy.handleRestReturnType(SyncRestProxy.java:213)
    at com.azure.core.implementation.http.rest.SyncRestProxy.invoke(SyncRestProxy.java:81)
    at com.azure.core.implementation.http.rest.RestProxyBase.invoke(RestProxyBase.java:109)
    at com.azure.core.http.rest.RestProxy.invoke(RestProxy.java:91)
    at jdk.proxy2/jdk.proxy2.$Proxy3.getChatCompletionsSync(Unknown Source)
    at com.azure.ai.openai.implementation.OpenAIClientImpl.getChatCompletionsWithResponse(OpenAIClientImpl.java:757)
    at com.azure.ai.openai.OpenAIClient.getChatCompletionsWithResponse(OpenAIClient.java:255)
    at com.azure.ai.openai.OpenAIClient.getChatCompletions(OpenAIClient.java:381)
    at com.dolphin.soa.post.config.ai.azure.AzureOpenAIClient.getChatCompletion(AzureOpenAIClient.java:37)
    at com.dolphin.soa.post.config.ai.azure.AzureOpenAIClient.main(AzureOpenAIClient.java:55)

I have checked all the configuration and make sure the endpoint was correct, the deployment was created more than 10 hours. Am I missing something? This is the dependencies:

我已经检查了所有配置，并确保端点地址是正确的，部署已经超过10个小时了。我是不是遗漏了什么？这是依赖项："

cs 复制代码 
implementation'com.azure:azure-ai-openai:1.0.0-beta.1'

I have already tried to upgrade the azure openai dependencies version to 1.0.0-beta.2 but still could not fixed this issue.

我已经尝试将Azure OpenAI的依赖项版本升级到1.0.0-beta.2，但仍然无法解决这个问题。

问题解决：

I tried in my environment and got the below results:

"我在我的环境中尝试了，并得到了以下结果："

Initially, I got the same error in my environment.

"最初，我在我的环境中遇到了同样的错误。"

[main] ERROR com.azure.core.implementation.http.rest.RestProxyBase Status code 404, "{"error":{"code":"DeploymentNotFound", "message":"The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again."}}"

In your code, at deploymentOrModelId , you have given gpt-35-turbo but you need to mention your deployment name. You can get the deployment name using the portal below.

在你的代码中，deploymentOrModelId 这个位置你填写了 gpt-35-turbo，但你需要提供你的部署名称。你可以使用下面的门户来获取你的部署名称。

Portal:

I tried with the same code change deployment id into deployment1 it executed successfully.

我尝试用相同的代码将部署ID更改为deployment1，它成功执行了。

Code:

cs 复制代码 
import com.azure.ai.openai.OpenAIClient;
import com.azure.ai.openai.OpenAIClientBuilder;
import com.azure.ai.openai.models.*;
import com.azure.core.credential.AzureKeyCredential;


import java.util.ArrayList;
import java.util.List;

public class App {

    public static void getChatCompletion(){
        String azureOpenaiKey = "";
        String endpoint = "https://xxxxx.openai.azure.com/";
        String deploymentOrModelId = "deployment1";

        OpenAIClient client = new OpenAIClientBuilder()
                .endpoint(endpoint)
                .credential(new AzureKeyCredential(azureOpenaiKey))
                .buildClient();

        List<ChatMessage> chatMessages = new ArrayList<>();
        chatMessages.add(new ChatMessage(ChatRole.SYSTEM).setContent("You are a helpful assistant."));
        chatMessages.add(new ChatMessage(ChatRole.USER).setContent("Does Azure OpenAI support customer managed keys?"));
        chatMessages.add(new ChatMessage(ChatRole.ASSISTANT).setContent("Yes, customer managed keys are supported by Azure OpenAI?"));
        chatMessages.add(new ChatMessage(ChatRole.USER).setContent("Do other Azure Cognitive Services support this too?"));

        ChatCompletions chatCompletions = client.getChatCompletions(deploymentOrModelId, new ChatCompletionsOptions(chatMessages));

        System.out.printf("Model ID=%s is created at %d.%n", chatCompletions.getId(), chatCompletions.getCreated());
        for (ChatChoice choice : chatCompletions.getChoices()) {
            ChatMessage message = choice.getMessage();
            System.out.printf("Index: %d, Chat Role: %s.%n", choice.getIndex(), message.getRole());
            System.out.println("Message:");
            System.out.println(message.getContent());
        }

        System.out.println();
        CompletionsUsage usage = chatCompletions.getUsage();
        System.out.printf("Usage: number of prompt token is %d, "
                        + "number of completion token is %d, and number of total tokens in request and response is %d.%n",
                usage.getPromptTokens(), usage.getCompletionTokens(), usage.getTotalTokens());
    }

    public static void main(String[] args) {
        getChatCompletion();
    }

}

Output: 输出

cs 复制代码 
Model ID=chatcmpl-xxxxx is created at 168776xxx.
Index: 0, Chat Role: assistant.
Message:
Yes, most Azure Cognitive Services support customer managed keys for enhanced security and compliance. Some of the popular services that support customer managed keys include Azure Cognitive Search, Azure Speech Services, Azure Language Understanding, and Azure Computer Vision.

Usage: number of prompt token is 59, number of completion token is 44, and number of total tokens in request and response is 103.

Reference: 引用

Azure OpenAI client library for Java | Microsoft Learn

相关推荐
fanstuck5 小时前
Prompt提示工程上手指南(七)Prompt编写实战-基于智能客服问答系统下的Prompt编写
人工智能·数据挖掘·openai
mortimer7 小时前
实现一个用于cosoyVoice2的接口并兼容OpenAI TTS
openai·阿里巴巴
米开朗基杨10 小时前
Sealos Devbox 基础教程：使用 Cursor 从零开发一个代码猜古诗小游戏
ai·cursor·sealos·devbox
GitCode官方11 小时前
GitCode 光引计划投稿｜JavaVision：引领全能视觉智能识别新纪元
人工智能·ai·gitcode
HUIBUR科技12 小时前
人工智能与云计算的结合：如何释放数据的无限潜力？
人工智能·ai·云计算
that's boy13 小时前
突围边缘：OpenAI开源实时嵌入式API，AI触角延伸至微观世界
人工智能·gpt·chatgpt·开源·openai·midjourney
杨浦老苏13 小时前
开源PDF翻译工具PDFMathTranslate
人工智能·docker·ai·pdf·群晖·翻译
hunteritself1 天前
AI Weekly『12月16-22日』：OpenAI公布o3，谷歌发布首个推理模型，GitHub Copilot免费版上线！
人工智能·gpt·chatgpt·github·openai·copilot
落魄实习生1 天前
AI应用-本地模型实现AI生成PPT(简易版)
python·ai·vue·ppt
ibrahim1 天前
Llama 3.2 900亿参数视觉多模态大模型本地部署及案例展示
ai·大模型·llama·提示词
热门推荐
01Cube-Studio：开源大模型全链路一站式中台02ARM学习（31）编译器对overlay方式的支持03玄机平台应急响应—webshell查杀04Ubuntu 20.04使用Livox mid 360 测试 FAST_LIO05校验 GPT-4 真实性的三个经典问题：快速区分 GPT-3.5 与 GPT-4，并提供免费测试网站06Docker 夺命连环 15 问07构建高效的广告投放系统：应用架构的设计与实现08基于大语言模型（LLM）的合成数据生成、策展和评估的综述09(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明10【一文读懂】NTN（非地面网络）技术介绍