Help Center/ Content Moderation/ API Reference/ APIs/ Text Moderation/ Text Moderation (V2)

Updated on 2024-03-27 GMT+08:00

View PDF

Text Moderation (V2)

Function

Moderation (Text) analyzes and identifies whether the uploaded text contains sensitive information and returns the result to you.

Currently, only Chinese content moderation is supported.
By default, the maximum number of concurrent API calls is 50. To increase concurrency, contact Huawei technical support.
You can configure a custom dictionary to filter and detect specified text content. For details about how to create and use a custom dictionary, see Configuring a Custom Dictionary.

Prerequisites

Before using Text Moderation, you need to apply for the service and complete authentication. For details, see Getting Started with Moderation (Text).

URI

POST /v2/{project_id}/moderation/text

**Table 1** Path parameters
Parameter	Mandatory	Type	Description
project_id	Yes	String	Project ID.

Request Parameters

**Table 2** Request header parameters
Parameter	Mandatory	Type	Description
X-Auth-Token	Yes	String	Indicates the user token. Used to obtain the permission to operate APIs. For details about how to obtain the token, see Authentication. The value of X-Subject-Token in the response header is the token.

**Table 3** Request body parameters
Parameter	Mandatory	Type	Description
categories	No	Array of strings	Indicates the detection scenario. Currently, the following scenarios are supported: Default scenarios: porn: indicates pornographic information detection. abuse: indicates offensive content detection. contraband: indicates contraband information detection. flood: indicates the spamming detection. (Spamming refers to one or more digits, characters, or punctuations that appear repeatedly in a text.) Custom scenario: custom blocklist dictionary NOTE: In the default scenarios, AI-based text detection technology is used to identify the text you upload. In the custom scenario, you can configure a blocklist library to filter and detect specified text. For details about how to create and use a custom dictionary, see Configuring a Custom Dictionary. The custom allowlist dictionary cannot be used in the flood scenario.
white_glossaries	No	Array of strings	Indicates the enabled whitelists. If this parameter is not set, the whitelist dictionaries created before 16:00:00 on September 2, 2022 are used by default. The rules for configuring this parameter are as follows: If you set this parameter to an empty list (that is, [ ]), no whitelist dictionary will be used. If you set this parameter to the name of the whitelist dictionary you have created, the dictionary will be used. NOTE: If you want to use multiple whitelist dictionaries, for example, A, B, and C, set this parameter to ["A", "B", "C"]. For details about how to create and use whitelist dictionaries, see Creating a Custom Allowlist Dictionary.
items	Yes	Array of TextDetectionItemsReq objects	Indicates the items to be checked. Currently, only one item can be checked each time.

**Table 4** TextDetectionItemsReq parameters
Parameter	Mandatory	Type	Description
text	Yes	String	Indicates the text to be detected. The text is encoded using UTF-8 and contains 1 to 5,000 characters. If the text contains more than 5,000 characters, only the first 5,000 characters are detected.
type	No	String	Indicates the text type. The default value is content. Currently, only the content type is supported.

Response Parameters

Status code: 200

**Table 5** Response body parameters
Parameter	Type	Description
result	result object	Indicates the calling result of a successful API call. This parameter is not included when the API fails to be called.

**Table 6** result parameters
Parameter	Type	Description
suggestion	String	Indicates whether the check is passed. block: indicates that sensitive information is detected and the information fails to pass the check. pass: indicates that no sensitive information is detected and the information passes the check. review: indicates that a manual review is required.
detail	Object	Indicates details about the returned check result. Possible values are as follows: porn: indicates a list of pornographic words. abuse: indicates a list of offensive words. contraband: indicates a list of words related to contraband. flood: indicates spam, or unwanted content particularly in forums that provide little value to readers. NOTE: The spam content contains a maximum of 200 characters. The details about the returned check result of each scenario refer to only the detected words instead of the whole content.

Status code: 400

**Table 7** Response body parameters
Parameter	Type	Description
error_code	String	Indicates the error code of a failed API call. For details, see Error Codes. This parameter is not included when the API is successfully called.
error_msg	String	Indicates the error message of a failed API call. This parameter is not included when the API is successfully called.
fail_category	String	Indicates the API calling failure scenario when there are multiple scenarios.

Example Requests

Check whether the asdfasdfasdf text contains sensitive content, including advertisements, abuse, porn, contraband, and spam.

endpoint is the request URL for calling an API. Endpoints vary depending on services and regions. For details, see Endpoints.

For example, the endpoint of the service deployed in the CN-Hong Kong region is moderation.ap-southeast-1.myhuaweicloud.com, the request URL is https://moderation.ap-southeast-1.myhuaweicloud.com/v2/{project_id}/moderation/text, and project_id is the project ID. For details, see Obtaining a Project ID and Name.

POST https://{endpoint}/v2/{project_id}/moderation/text

{
  "categories" : [  "abuse", "porn", "contraband", "flood" ],
  "items" : [ {
    "text" :  "asdfasdfasdf",
    "type" : "content"
  }
 ]
}

Example Responses

Status code: 200

Example of a successful response

{
  "result" : {
    "detail" : {
      "abuse" : [ "fuck" ]
    },
    "suggestion" : "block"
  }
}

Status code: 400

Example of a failed response

{
  "error_code" : "AIS.0005",
  "error_msg" : "The service does not exist."
}

Status Codes

Status Code	Description
200	Example of a successful response
400	Example of a failed response

Error Codes

For details, see Error Codes.

Parent topic: Text Moderation

Previous topic: Text Moderation (V3)

Next topic: Image Moderation

Feedback

Was this page helpful?

Helpful Not helpful

Provide feedback

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

Which of the following issues have you encountered?

Content is inconsistent with the product UI

Unclear descriptions

Lack of examples or code

Incorrect steps

Can't find what I need

Lack of best practices

Feedback (optional)

0/500

Select at least one type of issue, and enter your comments or suggestions.

Enter a maximum of 500 characters.

Submit Cancel

For any further questions, feel free to contact us through the chatbot.

Chatbot