AI NVIDIA NeMo Guardrail Policy

Log blocked content

Configure the AI NVIDIA NeMo Guardrail policy to log the prompts and responses that NeMo blocks. The blocked prompt appears under ai.proxy.nvidia-nemo-guardrail.input_faulty_prompt and the blocked response under ai.proxy.nvidia-nemo-guardrail.output_faulty_response in each log entry. Blocked content can be sensitive or unsafe, so enable log_blocked_content only when your logging pipeline is authorized to store it.

Prerequisites

  • A running NeMo Guardrails microservice that AI Gateway can reach.

  • An AI Model.

  • An OpenAI API key.

  • A stored NeMo guardrail configuration named content_safety_input_output that defines an input rail and an output rail.

Environment variables

  • OPENAI_API_KEY: The OpenAI API key that the NeMo Guardrails microservice uses to evaluate your rails.

Set up the policy

Attach the policy

Help us make these docs great!

Kong Developer docs are open source. If you find these useful and want to make them better, contribute today!