Use /green/text/feedback to submit feedback for text moderation - Content Moderation - Alibaba Cloud - AI Guardrails

Provides feedback on invalid moderation results returned by Alibaba Cloud AI Guardrails for a text moderation task.

QPS limits

This operation supports up to 20 calls per second per account. Exceeding this limit triggers throttling, which may affect your business. Plan your call rate accordingly.

Request parameters

For common parameters required in all AI Guardrails API requests, see Common parameters.

The request body is a JSON array. Each element contains the following parameters.

Parameter	Type	Required	Example	Description
taskId	String	Yes	taskid xxx	The ID of the moderation task, as returned by the AI Guardrails server, which uniquely identifies the moderation task.
dataId	String	No	test7fcmzGkKbNp7@JqPQRnwIe-1mwwZX	The ID of the moderated content, specified in the `dataId` parameter of the original moderation request.
content	String	No	foobar	The text content that was moderated. Maximum length: 10,000 characters.
label	String	No	spam	The expected moderation category for the text in the specified moderation scenario. For valid values, see Text moderation.
note	String	No	blabla...	A description of the moderated text, such as keywords in the content.

The label value determines how the text is added to the feedback-based text library in the AI Guardrails console:

normal: adds the text to the whitelist

Any other value: adds the text to the block list

Response parameters

For common response parameters, see Common response parameters.

The data field in the response body is empty.

Examples

Sample request

http(s)://[Endpoint]/green/text/feedback
&<Common request parameters>
{
  "dataId": "test7fcmzGkKbNp7@JqPQRnwIe-1mwwZX",
  "taskId": "taskid xxx",
  "content": "foobar",
  "label": "spam",
  "note": "blabla..."
}

Sample response

{
  "msg": "OK",
  "code": 200,
  "requestId": "02C418E7-81D4-4375-9732-900B64D07CEE"
}