All Products
Search
Document Center

Platform For AI:LLM-Sensitive Keywords Filter (DLC)

Last Updated:Nov 20, 2024

The LLM-Sensitive Keywords Filter (DLC) component of Platform for AI (PAI) is used to filter out texts that contain sensitive keywords. The input Object Storage Service (OSS) data file must be in the JSON Lines format and meet the following requirements: Each line in the file is a valid JSON object and the file consists of multiple lines of JSON objects, but the file is not a valid JSON object. For more information, see Example.

Supported computing resources

Deep Learning Containers (DLC)

Algorithm description

The LLM-Sensitive Keywords Filter (DLC) component checks and filters out the texts that contain sensitive keywords. The component can also return the detected sensitive keywords. By default, the algorithm can recognize more than 12,000 sensitive keywords. To view the keywords, see Default sensitive keywords.

Note

If you view the default sensitive keyword list in a browser and the list contains garbled characters, download the list to your on-premises device.

Configure the component

On the pipeline page of Machine Learning Designer, configure the parameters of the LLM-Sensitive Keywords Filter (DLC) component.

Tab

Parameter

Required

Description

Default value

Fields Setting

Target Process Field

Yes

The name of the field that you want to process.

N/A

OSS Directory for Saving OutputData

No

The OSS directory in which the generated data is stored. If you do not specify this parameter, the default path of the workspace is used.

N/A

Sensitive Keywords File

No

The path of the sensitive keyword file. If you leave this parameter empty, the default sensitive keyword list is used. The file content must be in the "Sensitive keyword 1\nSensitive keyword 2\n..." format. Separate multiple sensitive keywords with line feeds.

Default sensitive keyword list

Tuning

Number of Processes

No

The number of processes.

8

Select Resource Group

Public Resource Group

No

The instance type (CPU or GPU), number of instances, and virtual private cloud (VPC) that you want to use.

N/A

Dedicated resource group

No

The number of vCPUs, memory, shared memory, number of GPUs, and number of instances that you want to use.

N/A

Maximum Running Duration

No

The maximum period of time for which the component can run. If this period of time is exceeded, the job is terminated.

N/A