RailsConfig

Configuration class for NeMo Guardrails

RailsConfig

The RailsConfig class represents the configuration for a guardrails application. It defines models, rails, prompts, and other settings.

Loading Configuration

from_path

Load a configuration from a directory or file path.

@classmethod
def from_path(
    config_path: str,
    test_set_percentage: float = 0.0
) -> RailsConfig

config_path · str · required

Path to a directory containing configuration files (config.yml, .co files) or a single .co file.

test_set_percentage · float · default: "0.0"

The percentage of examples to use for testing.

config · RailsConfig

A RailsConfig instance loaded from the specified path.

Example - Load from Directory

from nemoguardrails import RailsConfig

config = RailsConfig.from_path("path/to/config")

from_content

Create a configuration from YAML and Colang content strings.

@classmethod
def from_content(
    colang_content: Optional[str] = None,
    yaml_content: Optional[str] = None
) -> RailsConfig

colang_content · Optional[str]

Colang (.co) file content as a string.

yaml_content · Optional[str]

YAML configuration content as a string.

Example

from nemoguardrails import RailsConfig

yaml_content = """
models:
  - type: main
    engine: openai
    model: gpt-4o
"""

colang_content = """
define user express greeting
  "hello"
  "hi"

define bot express greeting
  "Hello! How can I help you?"
"""

config = RailsConfig.from_content(
    colang_content=colang_content,
    yaml_content=yaml_content
)

Configuration Fields

models · List[Model] · default: "[]"

List of LLM model configurations. Each model has:

• type: “main”, “embeddings”, “content_safety”, etc.
• engine: Provider name (“openai”, “nvidia_ai_endpoints”, etc.)
• model: Model name (“gpt-4o”, “llama-3.1-8b”, etc.)
• parameters: Additional parameters for the model
• cache: Cache configuration for the model

rails · Rails

Configuration for different types of rails:

• input: Input rails configuration
• output: Output rails configuration
• retrieval: Retrieval rails configuration
• dialog: Dialog rails configuration
• tool_input: Tool input rails configuration
• tool_output: Tool output rails configuration
• config: Additional rail-specific configuration (fact checking, jailbreak detection, etc.)

prompts · List[TaskPrompt] · default: "[]"

List of custom prompts for specific tasks. Each prompt has:

• task: The task ID
• content: The prompt content (for text completion)
• messages: List of messages (for chat completion)
• models: Optional list of models this prompt applies to

user_messages · Dict[str, List[str]] · default: "{}"

Mapping of canonical user message forms to example utterances.

bot_messages · Dict[str, List[str]] · default: "{}"

Mapping of canonical bot message forms to example responses.

flows · List[dict] · default: "[]"

List of Colang flow definitions.

instructions · List[Instruction] · default: "[]"

Natural language instructions for the LLM.

docs · List[Document] · default: "[]"

Documents for knowledge base/RAG.

colang_version · str · default: "1.0"

The Colang version to use (“1.0” or “2.x”).

passthrough · bool · default: "False"

Whether to enable passthrough mode (direct LLM access without rails).

streaming · bool · default: "False"

Whether streaming is enabled by default.

custom_data · dict · default: "{}"

Custom configuration data for user-defined extensions.

knowledge_base · KnowledgeBaseConfig

Configuration for the knowledge base.

tracing · TracingConfig

Configuration for tracing/telemetry.

Model Configuration

Example - Model Config

models:
  - type: main
    engine: openai
    model: gpt-4o
    parameters:
      temperature: 0.7
      max_tokens: 1000
  
  - type: embeddings
    engine: openai
    model: text-embedding-3-small
  
  - type: content_safety
    engine: nvidia_ai_endpoints
    model: nemoguard-guardrailsmoderation-8b
    cache:
      enabled: true
      maxsize: 10000

Rails Configuration

Example - Rails Config

rails:
  input:
    flows:
      - check jailbreak
      - check sensitive data
  
  output:
    flows:
      - check hallucination
    streaming:
      enabled: true
      chunk_size: 200
  
  config:
    jailbreak_detection:
      nim_base_url: "http://localhost:8000/v1"
    
    sensitive_data_detection:
      input:
        entities:
          - EMAIL_ADDRESS
          - PHONE_NUMBER
          - SSN

Prompts Configuration

Example - Custom Prompts

prompts:
  - task: self_check_input
    content: |
      Your task is to check if the user message below complies with the policy.
      
      User message: {{ user_message }}
      
      Policy: {{ policy }}
      
      Answer with 'yes' if compliant or 'no' if not.
  
  - task: generate_user_intent
    messages:
      - role: system
        content: You are a helpful assistant that identifies user intent.
      - role: user
        content: "{{ user_message }}"

Methods

model_dump

Export the configuration as a dictionary.

def model_dump() -> dict

model_dump_json

Export the configuration as a JSON string.

def model_dump_json() -> str

Combining Configurations

You can combine multiple configurations using the + operator:

base_config = RailsConfig.from_path("base")
additional_config = RailsConfig.from_path("additional")

combined_config = base_config + additional_config