Guardrail Configurations
Guardrail configurations define the safety policies that protect your LLM interactions. A configuration specifies which safety checks (rails) to apply, the models to use, and the prompts to use for the safety checks.
Overview
A guardrail configuration contains several properties that customize how the service interacts with models and applies safety checks. Most configurations define these core components:
- Models – The models to use for each task.
- Prompts – Prompt templates to use for each task.
- Rails – Configuration that defines how to apply checks on the user input or LLM output.
A guardrail configuration also supports general options such as instructions and sample conversations that you can customize.