创建内容审核 - ChatfireAPI

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 ********************

Header 参数

Authorization

string

可选

示例值:

Bearer {{YOUR_API_KEY}}

Body 参数application/json

input

array [object {3}]

必需

type

string

必需

text

string

可选

image_url

object

可选

model

enum<string>

必需

枚举值:

moark-text-moderationnsfw-classifierSecurity-semantic-filtering

示例

{
  "model": "omni-moderation-latest",
  "input": [
    {
      "type": "text",
      "text": "...text to classify goes here..."
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://oss.ffire.cc/files/sese2.jpg",
        // # can also use base64 encoded image URLs
        // # "url": "data:image/jpeg;base64,abcdefg..."
      }
    },
  ]
}

示例代码

Shell

JavaScript

Java

Swift

Go

PHP

Python

HTTP

C

C#

Objective-C

Ruby

OCaml

Dart

R

curl --location -g --request POST '{{YOUR_BASE_URL}}/v1/moderations' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "omni-moderation-latest",
  "input": [
    {
      "type": "text",
      "text": "...text to classify goes here..."
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://oss.ffire.cc/files/sese2.jpg",
        // # can also use base64 encoded image URLs
        // # "url": "data:image/jpeg;base64,abcdefg..."
      }
    },
  ]
}'

返回响应

🟢200成功

application/json

Body

id

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 {4}]

审核结果的详细信息

必需

flagged

boolean

可选

审核模型是否将输入内容标记为可疑内容

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

category_applied_input_types

object

可选

示例

{
  "id": "modr-4b7daa43b6911f46d080c899a2acdaa1",
  "model": "omni-moderation-latest",
  "results": [
    {
      "flagged": false,
      "categories": {
        "harassment": false,
        "harassment/threatening": false,
        "sexual": false,
        "hate": false,
        "hate/threatening": false,
        "illicit": false,
        "illicit/violent": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "self-harm": false,
        "sexual/minors": false,
        "violence": false,
        "violence/graphic": false
      },
      "category_scores": {
        "harassment": 0.0006805796002084943,
        "harassment/threatening": 0.00002913700606794303,
        "sexual": 0.20574255238063563,
        "hate": 0.00003682979260160596,
        "hate/threatening": 4.683888424952456e-6,
        "illicit": 0.0015019464607710874,
        "illicit/violent": 0.00004305570813246149,
        "self-harm/intent": 0.00022477355484446784,
        "self-harm/instructions": 0.00022121727903496864,
        "self-harm": 0.0005026766516422265,
        "sexual/minors": 0.000059766937110286536,
        "violence": 0.0012121048968397104,
        "violence/graphic": 0.00001941131867789626
      },
      "category_applied_input_types": {
        "harassment": [
          "text"
        ],
        "harassment/threatening": [
          "text"
        ],
        "sexual": [
          "text",
          "image"
        ],
        "hate": [
          "text"
        ],
        "hate/threatening": [
          "text"
        ],
        "illicit": [
          "text"
        ],
        "illicit/violent": [
          "text"
        ],
        "self-harm/intent": [
          "text",
          "image"
        ],
        "self-harm/instructions": [
          "text",
          "image"
        ],
        "self-harm": [
          "text",
          "image"
        ],
        "sexual/minors": [
          "text"
        ],
        "violence": [
          "text",
          "image"
        ],
        "violence/graphic": [
          "text",
          "image"
        ]
      }
    }
  ]
}