审核

POST

/v1/moderations

请求示例

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.uniapi.io/v1/moderations' \
--header 'Content-Type: application/json' \
--data-raw '{
    "input": "",
    "model": "string"
}'

响应示例

{
    "id": "string",
    "model": "string",
    "results": [
        {
            "flagged": true,
            "categories": {
                "hate": true,
                "hate/threatening": true,
                "harassment": true,
                "harassment/threatening": true,
                "illicit": true,
                "illicit/violent": true,
                "self-harm": true,
                "self-harm/intent": true,
                "self-harm/instructions": true,
                "sexual": true,
                "sexual/minors": true,
                "violence": true,
                "violence/graphic": true
            },
            "category_scores": {
                "hate": 0,
                "hate/threatening": 0,
                "harassment": 0,
                "harassment/threatening": 0,
                "illicit": 0,
                "illicit/violent": 0,
                "self-harm": 0,
                "self-harm/intent": 0,
                "self-harm/instructions": 0,
                "sexual": 0,
                "sexual/minors": 0,
                "violence": 0,
                "violence/graphic": 0
            },
            "category_applied_input_types": {
                "hate": [
                    "text"
                ],
                "hate/threatening": [
                    "text"
                ],
                "harassment": [
                    "text"
                ],
                "harassment/threatening": [
                    "text"
                ],
                "illicit": [
                    "text"
                ],
                "illicit/violent": [
                    "text"
                ],
                "self-harm": [
                    "text"
                ],
                "self-harm/intent": [
                    "text"
                ],
                "self-harm/instructions": [
                    "text"
                ],
                "sexual": [
                    "text"
                ],
                "sexual/minors": [
                    "text"
                ],
                "violence": [
                    "text"
                ],
                "violence/graphic": [
                    "text"
                ]
            }
        }
    ]
}

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Body 参数application/json

input

必需

要分类的输入（或输入）。可以是单个字符串、字符串数组，或类似于其他模型的多模态输入对象数组。

One of

string

array[string]

array [oneOf]

一串用于审核分类的文本。

默认值:

示例值:

I want to kill them.

model

可选

您想使用的内容审核模型。

Any of

string

默认值:

omni-moderation-latest

示例值:

omni-moderation-2024-09-26

示例

返回响应

🟢200成功

application/json

Body

表示给定文本输入是否可能有害。

string

必需

审核请求的唯一标识符。

model

string

必需

用于生成审核结果的模型。

results

array [object {4}]

审核对象列表

必需

flagged

boolean

必需

以下类别中是否有任何被标记。