Azure OpenAI Phi-4多模态模型调用runTools()工具选择报错咨询

将Azure AI服务的Next.js应用中的模型从GPT-4o切换为Phi-4-multimodel-instruct后，原本运行正常的runTools()方法调用时出现以下错误：

BadRequestError: 400 {"object":"error","message":""auto" tool choice requires --enable-auto-tool-choice and --tool-call-parser to be set","type":"BadRequestError","param":null,"code":400}

实现代码 #

OpenAI实例配置 #

import { AzureOpenAI } from "openai";
export const OpenAIInstance = () => {
  try {
    if (
      !process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_API_KEY ||
      !process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_API_VERSION ||
      !process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_INSTANCE_NAME
    ) {
      throw new Error(
        "Missing required environment variables for OpenAI instance."
      );
    }
    
    const azureOpenAI = new AzureOpenAI({
      apiKey: process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_API_KEY,
      apiVersion: process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_API_VERSION,
      baseURL: `https://${process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_INSTANCE_NAME}.openai.azure.com/models/chat/completions?api-version=${process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_API_VERSION}`
    });

    return azureOpenAI;
  } catch (error) {
    console.error(
      "Error initializing OpenAI instance:",
      (error as Error).message
    );
    throw error;
  }
};

Chat API扩展实现 #

export const ChatApiExtensions = async (props: {
  chatThread: ChatThreadModel;
  userMessage: string;
  history: ChatCompletionMessageParam[];
  extensions: RunnableToolFunction<any>[];
  signal: AbortSignal;
}): Promise<ChatCompletionStreamingRunner> => {
  const { userMessage, history, signal, chatThread, extensions } = props;
  const openAI = OpenAIInstance();
  
  const model = process.env.AZURE_SERVICE_PHI_4_MULTIMODEL_MODEL_NAME;
  if (!model) {
    throw new Error("Model deployment name is not configured");
  }

  const systemMessage = await extensionsSystemMessage(chatThread);
  try {
    return await openAI.beta.chat.completions.runTools(
      {
        model: model,
        stream: true,
        messages: [
          {
            role: "system",
            content: chatThread.personaMessage + "\n" + systemMessage,
          },
          ...history,
          {
            role: "user",
            content: userMessage,
          },
        ],
        tools: extensions,
        temperature: 0.7,
        max_tokens: 4000,
      },
      { 
        signal: signal,
      }
    );
  } catch (error) {
    console.error("Error in ChatApiExtensions:", error);
    throw error;
  }
};

疑问 #

根据错误提示，Phi-4-multimodel-instruct需要GPT-4o不需要的工具调用额外参数，但查阅Azure文档未找到--enable-auto-tool-choice和--tool-call-parser这两个标识的具体信息。有没有人在Azure上成功为Phi-4-multimodel-instruct配置工具调用？该如何修改代码解决此问题？

环境 #

• Next.js（服务端组件）
• Azure OpenAI服务
• OpenAI Node.js SDK

内容的提问来源于stack exchange，提问作者Junaid Nazir