结构化输出 - wenwen

输出json格式结构数据
所有对话模型，都可使用此接口，修改 model 属性为模型名
模型列表请参考问问平台：https://api.wenwen-ai.com/pricing
BASE_URL: https://api.wenwen-ai.com/v1

请求参数

Header 参数

Body 参数application/json

示例

{
           "model": "gpt-4o-2024-08-06",
           "messages": [
              {
                 "role": "system",
                 "content": "You are a helpful math tutor. Guide the user through the solution step by step."
              },
              {
                 "role": "user",
                 "content": "9.11和9.8谁大"
              }
           ],
           "response_format": {
              "type": "json_schema",
              "json_schema": {
                 "name": "math_reasoning",
                 "schema": {
                    "type": "object",
                    "properties": {
                       "steps": {
                          "type": "array",
                          "items": {
                             "type": "object",
                             "properties": {
                                "explanation": {
                                   "type": "string"
                                },
                                "output": {
                                   "type": "string"
                                }
                             },
                             "required": [
                                "explanation",
                                "output"
                             ],
                             "additionalProperties": false
                          }
                       },
                       "final_answer": {
                          "type": "string"
                       }
                    },
                    "required": [
                       "steps",
                       "final_answer"
                    ],
                    "additionalProperties": false
                 },
                 "strict": true
              }
           }
         }

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.wenwen-ai.com/v1/chat/completions' \
--header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \
--data-raw '{
           "model": "gpt-4o-2024-08-06",
           "messages": [
              {
                 "role": "system",
                 "content": "You are a helpful math tutor. Guide the user through the solution step by step."
              },
              {
                 "role": "user",
                 "content": "9.11和9.8谁大"
              }
           ],
           "response_format": {
              "type": "json_schema",
              "json_schema": {
                 "name": "math_reasoning",
                 "schema": {
                    "type": "object",
                    "properties": {
                       "steps": {
                          "type": "array",
                          "items": {
                             "type": "object",
                             "properties": {
                                "explanation": {
                                   "type": "string"
                                },
                                "output": {
                                   "type": "string"
                                }
                             },
                             "required": [
                                "explanation",
                                "output"
                             ],
                             "additionalProperties": false
                          }
                       },
                       "final_answer": {
                          "type": "string"
                       }
                    },
                    "required": [
                       "steps",
                       "final_answer"
                    ],
                    "additionalProperties": false
                 },
                 "strict": true
              }
           }
         }'

返回响应

🟢200成功

application/json

Body

示例

{
    "id": "chatcmpl-Bg48iwIDEzYI4TrkuI8W7zvE0iPsn",
    "model": "gpt-4o-2024-08-06",
    "object": "chat.completion",
    "created": 1749365388,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "{\"final_answer\":\"9.8\",\"steps\":[{\"explanation\":\"比较两个数时，可以首先比较整数部分，然后比较小数部分。这里，我们首先看整数部分。\",\"output\":\"9.11和9.8的整数部分分别是9和9。\"},{\"explanation\":\"由于整数部分相同，我们需要比较小数部分。我们来看小数部分的第一位数字，也就是十分位。\",\"output\":\"9.11的十分位是1，9.8的十分位是8。\"},{\"explanation\":\"因为8比1大，所以9.8的小数部分大于9.11的小数部分。\",\"output\":\"因此，9.8比9.11大。\"}]}"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 97,
        "completion_tokens": 148,
        "total_tokens": 245,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "text_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0
        },
        "completion_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "reasoning_tokens": 0
        },
        "input_tokens": 0,
        "output_tokens": 0,
        "input_tokens_details": null
    }
}