profanity-check
Lightweight LLM agent for text moderation with deterministic pipeline: profanity rules → ML → LLM. Production-grade, YAML configurable. Uses glin-profanity + rapidfuzz + detoxify with Qwen LLM agent (llamacpp/Ollama) + RAG. Early-stop logic. Pure Python, CLI/API/SDK.
This is a python API which allows you to check for swear words in a youtube video, srt file, text file, custom source with multi language support. There are additional features like getting youtube transcript of a video, srt parser etc.
A fast, robust library to check for offensive language in strings. This version of "profanity-check" is used by Bleepy.
