> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/NVIDIA-NeMo/Guardrails/llms.txt
> Use this file to discover all available pages before exploring further.

# config.yml Schema

> Complete reference for the config.yml configuration file

The `config.yml` file is the main configuration file for NeMo Guardrails. It defines LLM models, active rails, instructions, and custom configuration data.

## Configuration Sections

### Models

Define one or more LLM models to use in your guardrails configuration.

<ParamField path="models" type="array" required>
  List of model configurations
</ParamField>

<ParamField path="models[].type" type="string" required>
  The type of model. Common values:

  * `main` - Primary LLM for conversation
  * `content_safety` - Model for content safety checks
  * `jailbreak_detection` - Model for jailbreak detection
</ParamField>

<ParamField path="models[].engine" type="string" required>
  The LLM engine/provider. Supported values:

  * `openai` - OpenAI models
  * `nim` - NVIDIA NIM
  * `vertexai` - Google Vertex AI
  * `hf_pipeline` - HuggingFace pipeline
  * `hf_endpoint` - HuggingFace endpoint
</ParamField>

<ParamField path="models[].model" type="string" required>
  The specific model name (e.g., `gpt-4o-mini`, `meta/llama3-8b-instruct`)
</ParamField>

<ParamField path="models[].parameters" type="object">
  Additional model parameters like `temperature`, `max_tokens`, `base_url`, etc.
</ParamField>

#### Example: OpenAI Configuration

From `examples/bots/hello_world/config.yml`:

```yaml theme={null}
models:
  - type: main
    engine: openai
    model: gpt-4o-mini
```

#### Example: NIM Configuration

From `examples/configs/llm/nim/config.yml`:

```yaml theme={null}
models:
  - type: main
    engine: nim
    model: meta/llama3-8b-instruct
    parameters:
      base_url: http://localhost:7331/v1
```

#### Example: Multiple Models

From `examples/configs/content_safety/config.yml`:

```yaml theme={null}
models:
  - type: main
    engine: nim
    model: meta/llama-3.3-70b-instruct

  - type: content_safety
    engine: nim
    model: nvidia/llama-3.1-nemoguard-8b-content-safety
```

### Instructions

Provide system instructions that guide the LLM's behavior.

<ParamField path="instructions" type="array">
  List of instruction sets
</ParamField>

<ParamField path="instructions[].type" type="string">
  The type of instruction (e.g., `general`)
</ParamField>

<ParamField path="instructions[].content" type="string">
  The instruction text
</ParamField>

#### Example

From `examples/bots/abc/config.yml`:

```yaml theme={null}
instructions:
  - type: general
    content: |
      Below is a conversation between a user and a bot called the ABC Bot.
      The bot is designed to answer employee questions about the ABC Company.
      The bot is knowledgeable about the employee handbook and company policies.
      If the bot does not know the answer to a question, it truthfully says it does not know.
```

### Sample Conversation

Provide sample conversation patterns to guide the LLM.

<ParamField path="sample_conversation" type="string">
  Example conversation showing user/bot interaction patterns with canonical forms
</ParamField>

#### Example

From `examples/configs/sample/config.yml`:

```yaml theme={null}
sample_conversation: |
  user "Hello there!"
    express greeting
  bot express greeting
    "Hello! How can I assist you today?"
  user "What can you do for me?"
    ask about capabilities
  bot respond about capabilities
    "I am an AI assistant built to help you."
```

### Rails

Define which guardrails should be active and how they should be configured.

<ParamField path="rails" type="object">
  Container for all rail configurations
</ParamField>

<ParamField path="rails.input" type="object">
  Input rails configuration
</ParamField>

<ParamField path="rails.input.flows" type="array">
  List of input rail flow names to activate
</ParamField>

<ParamField path="rails.output" type="object">
  Output rails configuration
</ParamField>

<ParamField path="rails.output.flows" type="array">
  List of output rail flow names to activate
</ParamField>

<ParamField path="rails.dialog" type="object">
  Dialog rails configuration
</ParamField>

<ParamField path="rails.dialog.single_call" type="object">
  Configuration for single-call dialog mode
</ParamField>

<ParamField path="rails.dialog.single_call.enabled" type="boolean">
  Whether to enable single-call mode (default: varies by configuration)
</ParamField>

<ParamField path="rails.config" type="object">
  Custom configuration for specific rails
</ParamField>

#### Example: Self-Check Rails

From `examples/bots/abc/config.yml`:

```yaml theme={null}
rails:
  input:
    flows:
      - self check input

  output:
    flows:
      - self check output

  dialog:
    single_call:
      enabled: False
```

#### Example: Content Safety Rails

From `examples/configs/content_safety/config.yml`:

```yaml theme={null}
rails:
  input:
    flows:
      - content safety check input $model=content_safety
  output:
    flows:
      - content safety check output $model=content_safety
```

#### Example: Jailbreak Detection

From `examples/configs/jailbreak_detection/config.yml`:

```yaml theme={null}
rails:
  config:
    jailbreak_detection:
      server_endpoint: "http://localhost:1337/heuristics"
      lp_threshold: 89.79
      ps_ppl_threshold: 1845.65
      embedding: "Snowflake/snowflake-arctic-embed-m-long"

  input:
    flows:
      - jailbreak detection heuristics
      - jailbreak detection model
```

### Custom Configuration

You can add custom configuration sections for specific rails or features.

#### Example: Sensitive Data Detection

```yaml theme={null}
rails:
  config:
    sensitive_data_detection:
      input:
        entities:
          - PERSON
          - EMAIL_ADDRESS
          - PHONE_NUMBER
          - CREDIT_CARD
```

#### Example: Fact Checking

From `examples/configs/rag/fact_checking/config.yml`:

```yaml theme={null}
rails:
  config:
    fact_checking:
      parameters:
        endpoint: "http://localhost:5123/alignscore_base"

  output:
    flows:
      - alignscore check facts
```

## Complete Example

Here's a comprehensive configuration example combining multiple features:

```yaml theme={null}
instructions:
  - type: general
    content: |
      Below is a conversation between a bot and a user. The bot is talkative and
      quirky. If the bot does not know the answer to a question, it truthfully says it does not know.

sample_conversation: |
  user "Hello there!"
    express greeting
  bot express greeting
    "Hello! How can I assist you today?"

models:
  - type: main
    engine: openai
    model: gpt-3.5-turbo-instruct
    parameters:
      temperature: 0.7
      max_tokens: 256

rails:
  input:
    flows:
      - check jailbreak
      - mask sensitive data on input

  output:
    flows:
      - self check facts
      - self check hallucination

  config:
    sensitive_data_detection:
      input:
        entities:
          - PERSON
          - EMAIL_ADDRESS
```

## Loading Configuration

<Tabs>
  <Tab title="Python API">
    ```python theme={null}
    from nemoguardrails import RailsConfig, LLMRails

    # Load from directory
    config = RailsConfig.from_path("./config")
    rails = LLMRails(config)

    # Use the rails
    response = rails.generate(
        messages=[{"role": "user", "content": "Hello!"}]
    )
    ```
  </Tab>

  <Tab title="Server">
    ```bash theme={null}
    # Start server with config directory
    nemoguardrails server --config ./configs
    ```

    Then make requests:

    ```bash theme={null}
    curl -X POST http://localhost:8000/v1/chat/completions \
      -H "Content-Type: application/json" \
      -d '{
        "config_id": "sample",
        "messages": [{"role": "user", "content": "Hello!"}]
      }'
    ```
  </Tab>
</Tabs>

## Next Steps

<CardGroup cols={2}>
  <Card title="Rails Definition" icon="shield" href="/configuration/rails-definition">
    Learn how to define custom rails in .co files
  </Card>

  <Card title="LLM Configuration" icon="brain" href="/configuration/llm-configuration">
    Explore LLM provider configuration options
  </Card>
</CardGroup>