Define and enforce conversational guardrails with NVIDIA NeMo Guardrails using Colang flows

Steps

1. Install nemoguardrails and create a config directory with a config.yml file that specifies your LLM engine configuration and sets the Colang version (1.0 or 2.x)
2. Write .co files in the config directory containing Colang flow definitions that handle prohibited intents, such as redirecting off-topic requests or refusing sensitive queries
3. Define canonical message forms in the .co files for user intents and bot responses that your flows reference
4. Instantiate RailsConfig.from_path() pointing to your config directory, then create an LLMRails instance from the config
5. Call rails.generate(messages=[...]) to run a conversation through the guardrails; Colang flows intercept and reroute any matching patterns
6. Test edge cases by providing adversarial inputs and confirm the guardrail flows trigger the expected bot responses rather than passing through to the LLM