创建内容审核

POST

https://api.ninhao.cc/v1/moderations

给定输入文本，如果模型将其分类为违反 OpenAI 的内容策略，则输出。

请求参数

Header 参数

Authorization

string

可选

示例值:

Bearer {{YOUR_API_KEY}}

Body 参数application/json

input

string

必需

示例

{
  "input": "I want to kill them."
}

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.ninhao.cc/v1/moderations' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
  "input": "I want to kill them."
}'

返回响应

🟢200Create moderation

application/json

Body

string

必需

审核任务的唯一标识符

model

string

用于审核的模型

必需

results

array [object {3}]

审核结果的详细信息

必需

categories

object

可选

审核模型检测到的所有分类标签

category_scores

object

可选

审核模型对所有分类标签的得分

flagged

boolean

可选

审核模型是否将输入内容标记为可疑内容

示例

{
  "id": "modr-5MWoLO",
  "model": "text-moderation-001",
  "results": [
    {
      "categories": {
        "hate": false,
        "hate/threatening": true,
        "self-harm": false,
        "sexual": false,
        "sexual/minors": false,
        "violence": true,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.22714105248451233,
        "hate/threatening": 0.4132447838783264,
        "self-harm": 0.005232391878962517,
        "sexual": 0.01407341007143259,
        "sexual/minors": 0.0038522258400917053,
        "violence": 0.9223177433013916,
        "violence/graphic": 0.036865197122097015
      },
      "flagged": true
    }
  ]
}

删除微调模型