🧿
Moderations

Given a input text, outputs if the model classifies it as violating Eye-ai content policy.
Example request
1
curl https://api.eye-ai.com/v1/moderations \
2
  -H 'Content-Type: application/json' \
3
  -H 'Authorization: Bearer YOUR_API_KEY' \
4
  -d '{
5
  "input": "I want to kill them."
6
}'
Parameters
1
{
2
  "input": "I want to kill them."
3
}
Response
1
{
2
  "id": "modr-5MWoLO",
3
  "model": "text-moderation-001",
4
  "results": [
5
    {
6
      "categories": {
7
        "hate": false,
8
        "hate/threatening": true,
9
        "self-harm": false,
10
        "sexual": false,
11
        "sexual/minors": false,
12
        "violence": true,
13
        "violence/graphic": false
14
      },
15
      "category_scores": {
16
        "hate": 0.22714105248451233,
17
        "hate/threatening": 0.4132447838783264,
18
        "self-harm": 0.005232391878962517,
19
        "sexual": 0.01407341007143259,
20
        "sexual/minors": 0.0038522258400917053,
21
        "violence": 0.9223177433013916,
22
        "violence/graphic": 0.036865197122097015
23
      },
24
      "flagged": true
25
    }
26
  ]
27
}
Fine-tunes
Parameter details
Last modified 3mo ago