Moderations

Content moderation using PraisonAI capabilities

Overview

Check content for policy violations using OpenAI’s moderation API.

Python Usage

Basic Moderation

from praisonai.capabilities import moderate

result = moderate(
    input="Hello, how are you today?"
)

print(f"Flagged: {result[0].flagged}")  # False
print(f"Categories: {result[0].categories}")

Multiple Texts

from praisonai.capabilities import moderate

result = moderate(
    input=["Hello world", "Have a nice day", "This is a test"]
)

for i, r in enumerate(result):
    print(f"Text {i+1}: Flagged = {r.flagged}")

Async Usage

import asyncio
from praisonai.capabilities import amoderate

async def main():
    result = await amoderate(
        input="Check this content"
    )
    print(f"Flagged: {result[0].flagged}")

asyncio.run(main())

Parameters

Parameter	Type	Default	Description
input	str or List[str]	Required	Text(s) to moderate
model	str	”omni-moderation-latest”	Moderation model
timeout	float	600.0	Request timeout
api_key	str	None	API key override

Result Object

The ModerationResult object contains:

• flagged: Whether content was flagged
• categories: Dict of category flags
• category_scores: Dict of category scores
• model: Model used