Moderations

Moderations scan text and report whether it contains potentially harmful content. This is an essential tool for messaging and social platforms. Each request is scored against the following categories:

Sexual
Hate
Harassment
Self-harm
Sexual/minors
Hate/threatening
Violence/graphic
Self-harm/intent
Self-harm/instructions
Harassment/threatening
Violence

Moderations are served by OpenAI models through the endpoint below.

Request

URL: https://ai.purlabs.xyz/openai/moderations

Request Method: POST

TS Request Interface


interface Request {
	input: string | string[];
	model?: string;
    user?: string;
};

Request API Reference

Parameter	Type (check TS Interface)	Required	Description
`input`	`string \| string[]`	Required	The input text to evaluate
`model`	`string`	Optional	The model you would like to use. Refer to the Listing Available Models page for more information.
`user`	`string`	Optional	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more .

Example JSON Request Body


{
    "model": "text-moderation-stable",
    "input": "hello"
}

Response

TS Response Interface


interface Response {
	id: `modr-${string}`;
	model: string;
	results: {
		flagged: boolean;
		categories: {
			sexual: boolean,
            hate: boolean,
            harassment: boolean,
            'self-harm': boolean,
            'sexual/minors': boolean,
            'hate/threatening': boolean,
            'violence/graphic': boolean,
            'self-harm/intent': boolean,
            'self-harm/instructions': boolean,
            'harassment/threatening': boolean,
            violence: boolean;
        };
        category_scores: {
            sexual: number,
            hate: number,
            harassment: number,
            'self-harm': number,
            'sexual/minors': number,
            'hate/threatening': number,
            'violence/graphic': number,
            'self-harm/intent': number,
            'self-harm/instructions': number,
            'harassment/threatening': number,
            violence: number;
		};
	}[];
	overwritten: boolean;
	provider: string;
	cache?: {
		status: 500,
		error: {
			message: 'Some of our providers returned with errors. Errors are automatically reported to our developers.';
			records: {
				provider: string;
				response: {
					status: number;
					data?: any;
				};
			}[];
		};
	};
} | {
	status: 500,
	message: string;
	records: {
		provider: string;
		response: {
			status: number;
			data?: any;
		};
	}[];
};

Example JSON Response


{
    "id": "modr-7gaMSTsOSO4jzqXp8WVyAlcN08OXV",
    "model": "text-moderation-005",
    "results": [
        {
            "flagged": false,
            "categories": {
                "sexual": false,
                "hate": false,
                "harassment": false,
                "self-harm": false,
                "sexual/minors": false,
                "hate/threatening": false,
                "violence/graphic": false,
                "self-harm/intent": false,
                "self-harm/instructions": false,
                "harassment/threatening": false,
                "violence": false
            },
            "category_scores": {
                "sexual": 0.0005927102,
                "hate": 2.7723228e-8,
                "harassment": 7.662779e-8,
                "self-harm": 2.5427553e-8,
                "sexual/minors": 0.0000012251222,
                "hate/threatening": 9.390831e-9,
                "violence/graphic": 6.338083e-8,
                "self-harm/intent": 2.9169966e-8,
                "self-harm/instructions": 1.025219e-7,
                "harassment/threatening": 3.5038823e-8,
                "violence": 5.588273e-8
            }
        }
    ],
    "provider": "provider-1",
    "overwritten": false
}