ai.z.openapi.api.moderations

Interface ModerationApi

public interface ModerationApi

Moderation API for content safety detection Provides content moderation capabilities for text, image, audio, and video formats Accurately identifies risky content including adult content, violence, illegal content, etc. Returns structured moderation results including content type, risk type, and specific risk segments

Method Summary

Modifier and Type	Method and Description
io.reactivex.rxjava3.core.Single<ModerationResult>	createModeration(ModerationCreateParams request) Create a content moderation request for safety detection Analyzes content for potential risks including adult content, violence, illegal activities Supports multiple content types: text strings, images, audio, and video files Returns detailed risk assessment with structured results and specific risk segments

Method Detail

createModeration

@POST(value="moderations")
io.reactivex.rxjava3.core.Single<ModerationResult> createModeration(@Body
                                                                                               ModerationCreateParams request)

Create a content moderation request for safety detection Analyzes content for potential risks including adult content, violence, illegal activities Supports multiple content types: text strings, images, audio, and video files Returns detailed risk assessment with structured results and specific risk segments

Parameters:

request - Moderation parameters including content to analyze (text string or multimedia object) Text: maximum 2000 characters Images: less than 10M, minimum resolution 20x20, maximum 6000x6000 Video: recommended duration 30 seconds Audio: recommended duration 60 seconds

Returns:

Moderation response with risk level (PASS/REVIEW/REJECT), content type, risk types, and processing time information