Nemo Guardrails
원문: nemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
무엇을 하나요
NeMo Guardrails Programmable Safety for LLMs Quick start NeMo Guardrails adds programmable safety rails to LLM applications at runtime. Installation : Basic example (input validation): Common workflows Workflow 1: Jailbreak detection Detect prompt injection attempts : Workflow 2: Self check input/output Validate both input and output : Workflow 3: Fact checking with retrieval Verify factual claims : Workflow 4: PII detection with Presidio Filter sensitive information : Workflow 5: LlamaGuard integration Use Meta's moderation model : When to use vs alternatives Use NeMo Guardrails when : Need runtime safety checks Want programmable safety rules Need multiple safety mechanisms (jailbreak, hall…
실행 시 본인 API 키(BYOK)로 동작하며, 모델 비용은 사용자 계정에서 직접 결제됩니다.