guardrails-ai-toxic-language-llm 0.1.0

Detects toxic language in LLM-generated text using an LLM as the detection backbone. Evaluates text across seven toxicity categories: toxicity, severe toxicity, obscene, threat, insult, identity attack, and sexual explicit content.

guardrails-ai-toxic-language-llm

Detects toxic language in LLM-generated text using an LLM as the detection backbone. Evaluates text across seven toxicity categories: toxicity, severe toxicity, obscene, threat, insult, identity attack, and sexual explicit content.

Installation

pip install guardrails-ai-toxic-language-llm

This validator ships local models. After installing, run the post-install step to download them:

python -m guardrails_ai.toxic_language_llm.post_install

Usage

from guardrails import Guard
from guardrails_ai.toxic_language_llm import ToxicLanguageLLM

guard = Guard().use(ToxicLanguageLLM)

License

MIT — © Guardrails AI.