Manual image review
This topic describes how to call the /green/image/manual/asyncScan operation to manually review images. In addition to its automated detection service, AI Guardrails provides a manual review service. You can use the manual review feature if you require a high accuracy and recall rate for your detection results.
Before you use this service, contact your account manager to confirm the audit standards and content scope. Calling this API does not return machine detection results. If you need machine detection results, call a detection service API. For more information about the detection service APIs, see Synchronous detection and Asynchronous detection.
Usage notes for manual image review
API operation: /green/image/manual/asyncScan
The manual review operation does not return detection results in real time. You can obtain the results through callbacks or by polling. The detection results are retained for a maximum of 30 days.
-
Billing information:
This is a paid API operation. For more information about billing, see Content Moderation Pricing.
-
Return results:
The time required to return the results of a manual review depends on the volume of data to be reviewed.
-
Obtain review results using callbacks: When you submit manual review tasks, pass the callback parameter in the request to receive detection results automatically. For more information, see Request parameters (Manual review).
-
Obtain review results by polling: When you submit manual review tasks, you do not need to pass the callback parameter. After you submit the tasks, call the result query operation to retrieve the detection results. For more information, see Usage notes for querying manual image review results.
-
-
Image requirements:
-
Image URLs must use the HTTP or HTTPS protocol.
-
Supported image formats: PNG, JPG, JPEG, BMP, GIF, and WEBP.
-
The image size cannot exceed 20 MB for both synchronous and asynchronous invocations, the height or width cannot exceed 30,000 pixels, and the total number of pixels in the image cannot exceed 250 million.
-
The image download timeout period is 3 seconds. If an image fails to download within 3 seconds, a timeout error is returned.
-
Ensure that the storage service for the images to be detected is stable and reliable. We recommend that you use Alibaba Cloud Object Storage Service (OSS) or Alibaba Cloud CDN.
-
For more information about how to use this operation, see Use the manual review service.
QPS limit
The queries per second (QPS) limit for this API is 50 per user. Exceeding this limit triggers throttling, which can impact your business. Plan your calls accordingly.
Request parameters (Manual review)
For more information about the common request parameters that must be included in a request, see Common parameters.
The request body is a JSON struct that contains the following fields.
|
Name |
Type |
Required |
Example value |
Description |
|
callback |
String |
No |
http://www.aliyundoc.com |
The
Note
After your callback server receives a result notification, it must return an HTTP status code of 200 to indicate success. Any other status code is treated as a failure. If the notification fails, Content Moderation retries up to 16 times until it succeeds. If it still fails after 16 retries, no more attempts are made. We recommend that you check the status of your callback endpoint. |
|
seed |
String |
Yes |
seedxxx |
A random string used for the signature in the callback notification request. The string can contain letters, digits, and underscores (_), and must be 64 characters or less. Customize this string to verify the origin of callback requests. Note
This parameter is required when you use a callback. |
|
tasks |
JSONArray |
No |
The detection objects. Each element in the JSON array is a detection task struct. You can specify up to 100 elements, which means you can submit 100 pieces of content for detection at a time. To support 100 elements, you must adjust the number of concurrent tasks to 100 or more. For more information about the structure of each element, see task. |
|
Name |
Type |
Required |
Example value |
Description |
|
url |
String |
Yes |
http://www.aliyundoc.com/xxx.jpg |
The URL of the object to detect.
|
|
dataId |
String |
No |
dataIdxxxx |
The data ID of the detection object. This ID can contain uppercase and lowercase letters, digits, underscores (_), hyphens (-), and periods (.), and must be 128 characters or less. Use it to uniquely identify your business data. |
Returned data (manual review)
|
Name |
Type |
Example |
Description |
|
code |
Integer |
200 |
The error code. It is the same as the HTTP status code. For more information, see Common error codes. |
|
data |
JSONArray |
The data returned for the request. Each element in the array indicates the result of a manual review task. For more information about the structure of each element, see data. |
|
|
msg |
String |
OK |
The response message. |
|
requestId |
String |
147DE21C-6B0E-4331-87E9-77941376E109 |
The request ID. |
|
Name |
Type |
Example |
Description |
|
code |
Integer |
200 |
The error code. It is the same as the HTTP status code. For more information, see Common error codes. |
|
dataId |
String |
dataIdxxxx |
The data ID of the detection object. Note
If dataId was passed in the detection request, the same dataId is returned here. |
|
msg |
String |
OK |
The response message for the detection task. |
|
taskId |
String |
img6I5NQPVSQ7G4PsB79Z40iJ-1tyzUJ |
The ID of the manual review task. You can use this ID to call the result query operation to query the result of the manual review task. |
|
url |
String |
http://www.aliyundoc.com/xxx.jpg |
The URL of the object to detect.
|
Examples (Manual review)
Sample request
http(s)://[Endpoint]/green/image/manual/asyncScan
&<Common request parameters>
{
"callback": "http://www.aliyundoc.com",
"seed": "seedxxx",
"tasks": [{
"url": "http://www.aliyundoc.com/xxx.jpg",
"dataId": "dataIdxxxx"
}]
}
Sample success response
{
"code": 200,
"data": [{
"code": 200,
"dataId": "dataIdxxxx",
"msg": "OK",
"taskId": "img6I5NQPVSQ7G4PsB79Z40iJ-1tyzUJ",
"url": "http://www.aliyundoc.com/xxx.jpg"
}],
"msg": "OK",
"requestId": "147DE21C-6B0E-4331-87E9-77941376E109"
}
Usage notes for querying manual image review results
API operation: /green/image/manual/scan/results. You can use this operation to query the results of a manual image review.
QPS limit
The queries per second (QPS) limit for this API is 50 per user. Exceeding this limit triggers throttling, which can impact your business. Plan your calls accordingly.
Request parameters (Result query)
|
Name |
Type |
Required |
Sample value |
Description |
|
body |
StringArray |
Yes |
["img6I5NQPVSQ7G4PsB79Z40iJ-1tyzUJ"] |
A list of taskIds for the manual review tasks that you want to query. The array can contain a maximum of 100 elements. |
Response parameters (Result query)
|
Name |
Type |
Example |
Description |
|
code |
Integer |
200 |
The error code. It is the same as the HTTP status code. For more information, see Common error codes. |
|
data |
JSONArray |
The data returned for the request. Each element in the array indicates the result of a manual review task. For more information about the structure of each element, see data. |
|
|
msg |
String |
OK |
The response message. |
|
requestId |
String |
1608A116-39C9-4080-A615-1E445DEF8841 |
The request ID. |
|
Name |
Type |
Example |
Description |
|
code |
Integer |
200 |
The error code. It is the same as the HTTP status code. For more information, see Common error codes. |
|
dataId |
String |
dataIdxxxx |
The data ID of the detection object. Note
If dataId was passed in the detection request, the same dataId is returned here. |
|
msg |
String |
OK |
The response message for the detection task. |
|
suggestion |
String |
block |
The recommended subsequent operation. Valid values:
|
|
taskId |
String |
img6I5NQPVSQ7G4PsB79Z40iJ-1tyzUJ |
The task ID. |
|
url |
String |
http://www.aliyundoc.com/xxx.jpg |
The URL of the object to detect.
|
Examples (Result query)
Sample request
http(s)://[Endpoint]/green/image/manual/scan/results
&<Common request parameters>
[
"img6I5NQPVSQ7G4PsB79Z40iJ-1tyzUJ"
]
Sample success response
{
"code": 200,
"data": [{
"code": 200,
"dataId": "dataIdxxxx",
"msg": "OK",
"suggestion": "block",
"taskId": "img6I5NQPVSQ7G4PsB79Z40iJ-1tyzUJ",
"url": "http://www.aliyundoc.com/xxx.jpg"
}],
"msg": "OK",
"requestId": "1608A116-39C9-4080-A615-1E445DEF8841"
}