Skip to main content

​
What is Profanity Policy?

Profanity policies detect profanity, toxic content, and inappropriate language using the Detoxify ML library. Supports multiple models including unbiased, original, multilingual, and lightweight variants.

​
Usage

from upsonic import Agent, Task
from upsonic.safety_engine.policies import ProfanityBlockPolicy

agent = Agent(
    model="openai/gpt-4o",
    user_policy=ProfanityBlockPolicy
)

task = Task("You are an idiot!")
result = agent.do(task)
# Blocked with educational message

​
Available Variants

  • ProfanityBlockPolicy: Standard blocking with unbiased model
  • ProfanityBlockPolicy_Original: BERT-based original model
  • ProfanityBlockPolicy_Multilingual: Multi-language support (7 languages)
  • ProfanityBlockPolicy_LLM: LLM-powered contextual block messages
  • ProfanityRaiseExceptionPolicy: Raises DisallowedOperation exception
  • ProfanityRaiseExceptionPolicy_LLM: LLM-generated exception messages
  • GPU variants: ProfanityBlockPolicy_GPU, ProfanityRaiseExceptionPolicy_GPU, etc.
  • CPU variants: ProfanityBlockPolicy_CPU, ProfanityRaiseExceptionPolicy_CPU, etc.

​
Installation

uv sync --extra safety-engine

​
Custom Policy

from upsonic.safety_engine.policies.profanity_policies import ProfanityRule, ProfanityBlockAction
from upsonic.safety_engine.base.policy import Policy

custom_rule = ProfanityRule(
    model_name="unbiased",  # or "original", "multilingual", "original-small", "unbiased-small"
    device="cuda"  # or "cpu" or None for auto
)

policy = Policy(
    name="Custom Profanity Policy",
    description="With custom model and device",
    rule=custom_rule,
    action=ProfanityBlockAction(min_confidence=0.5)
)