相关疑难解决方法(0)

当收到来自 OpenAI 模型的响应时text-davinci-003，我能够使用以下 PHP 代码从响应中提取文本：

$response = $response->choices[0]->text;

这是text-davinci-003响应代码：

{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}

我现在尝试更改我的代码以使用最近发布的gpt-3.5-turbo模型，该模型返回的响应略有不同：

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "\n\nHello there, how may I assist you today?",
    },
    "finish_reason": "stop"
  }], …