如何使用 Microsoft Foundry 模型生成文本响应

1. 安装库，包括 Azure 标识客户端库：

   pip install azure-identity
   pip install openai
   pip install --pre azure-ai-projects>=2.0.0b1 
   

2. 使用以下代码在项目路由中配置 OpenAI 客户端对象，指定部署并生成响应。

   import os
   from azure.identity import DefaultAzureCredential
   from azure.ai.projects import AIProjectClient
   
   project_client = AIProjectClient(
       endpoint="https://YOUR-RESOURCE-NAME.services.ai.azure.com/api/projects/YOUR_PROJECT_NAME",
       credential=DefaultAzureCredential(),
   )
   
   openai_client = project_client.get_openai_client()
   
   response = openai_client.responses.create(
       model="MAI-DS-R1", # Replace with your deployment name, not the model ID 
       input="What is the capital/major city of France?",
   )
   
   print(response.model_dump_json(indent=2)) 
   

1. 安装 Azure 标识客户端库：

   dotnet add package Azure.Identity
   

2. 使用以下代码在项目路由中配置 OpenAI 客户端对象，指定部署并生成响应。

   using Azure.Identity;
   using Azure.AI.Projects; 
   using OpenAI;
   using OpenAI.Responses;
   using System.ClientModel.Primitives;
   
   #pragma warning disable OPENAI001
   
   const string deploymentName = "MAI-DS-R1"; // Replace with your deployment name, not the model ID 
   const string endpoint = "https://YOUR-RESOURCE-NAME.services.ai.azure.com/api/projects/YOUR_PROJECT_NAME";
   
   AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
   
   OpenAIResponseClient responseClient = projectClient.OpenAI.GetProjectResponsesClientForModel(deploymentName);
   
   OpenAIResponse response = responseClient.CreateResponse("What is the capital/major city of France?");
   
   Console.WriteLine($"[ASSISTANT]: {response.GetOutputText()}");
   

JavaScript v1 示例

1. 安装 Azure 标识客户端库，然后才能使用 DefaultAzureCredential：

   npm install @azure/identity
   

2. 使用以下代码在项目路由中配置 OpenAI 客户端对象，指定部署并生成响应。

   import { AIProjectClient } from "@azure/ai-projects";
   import { DefaultAzureCredential } from "@azure/identity";
   
   const endpoint = "https://YOUR-RESOURCE-NAME.services.ai.azure.com/api/projects/YOUR_PROJECT_NAME";
   const deploymentName = "MAI-DS-R1"; // Replace with your deployment name, not the model ID 
   
   async function main() {
       const projectClient = new AIProjectClient(endpoint, new DefaultAzureCredential());
       const openAIClient = await projectClient.getOpenAIClient();
   
       const response = await openAIClient.responses.create({
           model: deploymentName,
           input: "What is the capital/major city of France?"
       });
       console.log(response.output_text);
   }
   
   main();
   

使用 Microsoft Entra ID 进行身份验证需要一些初始设置。 首先，安装 Azure 标识客户端库。 有关如何安装此库的更多选项，请参阅 适用于 Java 的 Azure 标识客户端库。

1. 添加 Azure 标识客户端库：

   <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-identity</artifactId>
       <version>1.18.0</version>
   </dependency>
   

   设置后，选择从 azure.identity 中要使用的凭据类型。 例如，用于 DefaultAzureCredential 对客户端进行身份验证。 使用 DefaultAzureCredential 进行身份验证最为简便，它会自动匹配其运行环境中最优的凭据。

2. 使用以下代码在项目路由中配置 OpenAI 客户端对象，指定部署并生成响应。

   import com.azure.ai.agents;
   import com.azure.core.util.Configuration;
   import com.azure.identity.DefaultAzureCredentialBuilder;
   import com.openai.models.responses.Response;
   import com.openai.models.responses.ResponseCreateParams;
   
   public class Sample {
       public static void main(String[] args) {
           String endpoint = "https://YOUR-RESOURCE-NAME.services.ai.azure.com/api/projects/YOUR_PROJECT_NAME";
           String deploymentName = "MAI-DS-R1"; // Replace with your deployment name, not the model ID
   
           ResponsesClient responsesClient = new AgentsClientBuilder()
                   .credential(new DefaultAzureCredentialBuilder().build())
                   .endpoint(endpoint)
                   .serviceVersion(AgentsServiceVersion.V2025_11_15_PREVIEW)
                   .buildResponsesClient();
   
           ResponseCreateParams responseRequest = new ResponseCreateParams.Builder()
                   .input("What is the capital/major city of France?")
                   .model(deploymentName)
                   .build();
   
           Response response = responsesClient.getResponseService().create(responseRequest);
       }
   }
   

curl -X POST https://YOUR-RESOURCE-NAME.services.ai.azure.com/api/projects/YOUR_PROJECT_NAME/openai/responses?api-version={{API_VERSION}} \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $AZURE_OPENAI_AUTH_TOKEN" \

-d '{
    "model": "MAI-DS-R1",
    "input": "What is the capital/major city of France?"
}'