Before You Begin Configuring Rails#

Before configuring your guardrails, ensure you have the following components ready.

Required: LLM Backend#

You need a main LLM hosted and accessible via API. This LLM handles:

  • Generating responses to user queries

Options:

Provider

Requirements

NVIDIA NIM

Deploy NIM and note the API endpoint

OpenAI

Obtain API key

Azure OpenAI

Configure Azure endpoint and API key

Other providers

Refer to Supported LLMs

What you need:

  • [ ] LLM API endpoint URL

  • [ ] Authentication credentials (API key or token)

Optional: Knowledge Base Documents#

If using RAG (Retrieval-Augmented Generation) for grounded responses:

  • [ ] Prepare documents in markdown format (.md files)

  • [ ] Organize documents in a kb/ folder

Optional: Advanced Components#

For advanced use cases such as implementing your own custom scripts or guardrails, prepare the following as needed:

Component

Purpose

Format

Custom Actions

External API calls, validation logic

Python functions in actions.py

Custom Initialization

Register custom LLM/embedding providers

Python code in config.py

Custom Prompts

Override default guardrails prompts

YAML in config.yml

Checklist Summary#

Before starting configuration:

  • [ ] Main LLM endpoint and credentials ready

  • [ ] (Recommended) NemoGuard NIM endpoints deployed

  • [ ] (Optional) Knowledge base documents prepared

  • [ ] (Optional) Custom action requirements identified

Next Steps#

Once you have these components ready, proceed to:

If you need tutorials to understand how to use the NeMo Guardrails toolkit, revisit the Get Started section.