如何为gpt-4-vision-preview启用JSON模式？文档问题与报错咨询

问题原因 #

OpenAI API文档曾存在错误，现已修正。旧文档声称调用gpt-4-vision-preview或gpt-3.5-turbo时可启用JSON模式，实际仅gpt-4-1106-preview和gpt-3.5-turbo-1106这两个版本支持response_format参数设置为json_object。

按照旧文档指引调用gpt-4-vision-preview并配置response_format: {"type": "json_object"}时，会触发以下验证错误：

{'error': {'message': '1 validation error for Request
body -> response_format
extra fields not permitted (type=value_error.extra)', 'type': 'invalid_request_error', 'param': None, 'code': None}}

解决方案 #

有两种处理方式可选：

1. 切换到支持JSON模式的模型

将请求中的模型替换为gpt-4-1106-preview或gpt-3.5-turbo-1106，保留response_format参数即可强制返回JSON格式。修正后的代码示例：

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {api_key}"
}

payload = {
    "model": "gpt-4-1106-preview",
    "response_format": {"type": "json_object"},
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant. Your response should be in JSON format."
      },
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": prompt
          },
          {
            "type": "image_url",
            "image_url": {
              "url": f"data:image/jpeg;base64,{base64_image}"
            }
          }
        ]
      }
    ],
    "max_tokens": 1000,
}

response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
print(response.json())

2. 保留gpt-4-vision-preview，移除response_format参数

若必须使用视觉模型，需删除response_format配置，同时通过系统提示词引导模型返回JSON。注意这种方式无法强制模型严格输出JSON，仅为软性约束：

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {api_key}"
}

payload = {
    "model": "gpt-4-vision-preview",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant. Your response should be in JSON format."
      },
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": prompt
          },
          {
            "type": "image_url",
            "image_url": {
              "url": f"data:image/jpeg;base64,{base64_image}"
            }
          }
        ]
      }
    ],
    "max_tokens": 1000,
}

response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
print(response.json())

内容的提问来源于stack exchange，提问作者chibop