NVIDIA NeMo Guardrails Library

LATEST RELEASE / DEVELOPMENT VERSION: The develop branch tracks the latest top of tree development. The latest released version is 0.23.0.

✨✨✨

📌 The official NeMo Guardrails library documentation is available at docs.nvidia.com/nemo/guardrails.

✨✨✨

NVIDIA NeMo Guardrails library is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational applications. Guardrails (or "rails" for short) are specific ways of controlling the output of a large language model, such as not talking about politics, responding in a particular way to specific user requests, following a predefined dialog path, using a particular language style, extracting structured data, and more.

This paper introduces the NeMo Guardrails library and contains a technical overview of the system and the current evaluation.

Requirements

Python 3.10, 3.11, 3.12 or 3.13.

Installation

To install using pip:

> pip install nemoguardrails

For more detailed instructions, see the Installation Guide.

Overview

The NeMo Guardrails library enables developers building LLM-based applications to add programmable guardrails between the application code and the LLM.

Key benefits of adding programmable guardrails include:

• Building Trustworthy, Safe, and Secure LLM-based Applications: you can define rails to guide and safeguard conversations; you can choose to define the behavior of your LLM-based application on specific topics and prevent it from engaging in discussions on unwanted topics.

• Connecting models, chains, and other services securely: you can connect an LLM to other services (a.k.a. tools) seamlessly and securely.

• Controllable dialog: you can steer the LLM to follow pre-defined conversational paths, allowing you to design the interaction following conversation design best practices and enforce standard operating procedures (e.g., authentication, support).

Protecting against LLM Vulnerabilities

The NeMo Guardrails library provides several mechanisms for protecting an LLM-powered chat application against common LLM vulnerabilities, such as jailbreaks and prompt injections. Below is a sample overview of the protection offered by different guardrails configuration for the example ABC Bot included in this repository. For more details, please refer to the LLM Vulnerability Scanning page.

Use Cases

You can use programmable guardrails in different types of use cases:

1. Question Answering over a set of documents (a.k.a. Retrieval Augmented Generation): Enforce fact-checking and output moderation.
2. Domain-specific Assistants (a.k.a. chatbots): Ensure the assistant stays on topic and follows the designed conversational flows.
3. LLM Endpoints: Add guardrails to your custom LLM for safer customer interaction.
4. LangChain Chains (optional): If you use LangChain for any use case, you can add a guardrails layer around your chains. To enable this integration, set the NEMOGUARDRAILS_LLM_FRAMEWORK=langchain environment variable or call set_default_framework("langchain").

Usage

To add programmable guardrails to your application you can use the Python API or a guardrails server (see the Server Guide for more details). Using the Python API is similar to using the LLM directly. Calling the guardrails layer instead of the LLM requires only minimal changes to the code base, and it involves two simple steps:

1. Loading a guardrails configuration and creating an LLMRails instance.
2. Making the calls to the LLM using the generate/generate_async methods.

from nemoguardrails import LLMRails, RailsConfig

# Load a guardrails configuration from the specified path.
config = RailsConfig.from_path("PATH/TO/CONFIG")
rails = LLMRails(config)

completion = rails.generate(
    messages=[{"role": "user", "content": "Hello world!"}]
)

Sample output:

{"role": "assistant", "content": "Hi! How can I help you?"}

The input and output format for the generate method is similar to the Chat Completions API from OpenAI.

Async API

The NeMo Guardrails library is an async-first toolkit as the core mechanics are implemented using the Python async model. The public methods have both a sync and an async version. For example: LLMRails.generate and LLMRails.generate_async.

Supported LLMs

You can use NeMo Guardrails with multiple LLMs like OpenAI GPT-3.5, GPT-4, LLaMa-2, Falcon, Vicuna, or Mosaic. For more details, check out the Supported LLM Models section in the Configuration Guide.

Types of Guardrails

The NeMo Guardrails library supports five main types of guardrails:

1. Input rails: applied to the input from the user; an input rail can reject the input, stopping any additional processing, or alter the input (e.g., to mask potentially sensitive data, to rephrase).

2. Dialog rails: influence how the LLM is prompted; dialog rails operate on canonical form messages for details see Colang Guide) and determine if an action should be executed, if the LLM should be invoked to generate the next step or a response, if a predefined response should be used instead, etc.

3. Retrieval rails: applied to the retrieved chunks in the case of a RAG (Retrieval Augmented Generation) scenario; a retrieval rail can reject a chunk, preventing it from being used to prompt the LLM, or alter the relevant chunks (e.g., to mask potentially sensitive data).

4. Execution rails: applied to input/output of the custom actions (a.k.a. tools), that need to be called by the LLM.

5. Output rails: applied to the output generated by the LLM; an output rail can reject the output, preventing it from being returned to the user, or alter it (e.g., removing sensitive data).

Guardrails Configuration

A guardrails configuration defines the LLM(s) to be used and one or more guardrails. A guardrails configuration can include any number of input/dialog/output/retrieval/execution rails. A configuration without any configured rails will essentially forward the requests to the LLM.

The standard structure for a guardrails configuration folder looks like this:

.
├── config
│   ├── actions.py
│   ├── config.py
│   ├── config.yml
│   ├── rails.co
│   ├── ...

The config.yml contains all the general configuration options, such as LLM models, active rails, and custom configuration data". The config.py file contains any custom initialization code and the actions.py contains any custom python actions. For a complete overview, see the Configuration Guide.

Below is an example config.yml:

# config.yml
models:
  - type: main
    engine: openai
    model: gpt-3.5-turbo-instruct

rails:
  # Input rails are invoked when new input from the user is received.
  input:
    flows:
      - check jailbreak
      - mask sensitive data on input

  # Output rails are triggered after a bot message has been generated.
  output:
    flows:
      - self check facts
      - self check hallucination
      - activefence moderation on input

  config:
    # Configure the types of entities that should be masked on user input.
    sensitive_data_detection:
      input:
        entities:
          - PERSON
          - EMAIL_ADDRESS

The .co files included in a guardrails configuration contain the Colang definitions (see the next section for a quick overview of what Colang is) that define various types of rails. Below is an example greeting.co file which defines the dialog rails for greeting the user.

define user express greeting
  "Hello!"
  "Good afternoon!"

define flow
  user express greeting
  bot express greeting
  bot offer to help

define bot express greeting
  "Hello there!"

define bot offer to help
  "How can I help you today?"

Below is an additional example of Colang definitions for a dialog rail against insults:

define user express insult
  "You are stupid"

define flow
  user express insult
  bot express calmly willingness to help

Colang

To configure and implement various types of guardrails, this toolkit introduces Colang, a modeling language specifically created for designing flexible, yet controllable, dialogue flows. Colang has a python-like syntax and is designed to be simple and intuitive, especially for developers.

Two versions of Colang, 1.0 and 2.0, are supported and Colang 1.0 is the default.

For a brief introduction to the Colang 1.0 syntax, see the Colang 1.0 Language Syntax Guide.

To get started with Colang 2.0, see the Colang 2.0 Documentation.

Guardrails Library

NeMo Guardrails comes with a set of built-in guardrails.

The built-in guardrails may or may not be suitable for a given production use case. As always, developers should work with their internal application team to ensure guardrails meets requirements for the relevant industry and use case and address unforeseen product misuse.

The library includes guardrails for LLM self-checking (input/output moderation, fact-checking, hallucination detection), NVIDIA safety models (content safety, topic safety), jailbreak and injection detection, and integrations with community models and third-party APIs. For the complete list, see the Guardrails Library documentation.

CLI

The NeMo Guardrails library also comes with a built-in CLI.

$ nemoguardrails --help

Usage: nemoguardrails [OPTIONS] COMMAND [ARGS]...

actions-server    Start a NeMo Guardrails actions server.
chat              Start an interactive chat session.
evaluate          Run an evaluation task.
server            Start a NeMo Guardrails server.

Guardrails Server

You can use the NeMo Guardrails library CLI to start a guardrails server. The server can load one or more configurations from the specified folder and expose and HTTP API for using them.

nemoguardrails server [--config PATH/TO/CONFIGS] [--port PORT]

For example, to get a chat completion for a sample config, you can use the /v1/chat/completions endpoint:

POST /v1/chat/completions

{
    "config_id": "sample",
    "messages": [{
      "role":"user",
      "content":"Hello! What can you do for me?"
    }]
}

Sample output:

{"role": "assistant", "content": "Hi! How can I help you?"}

Docker

To start a guardrails server, you can also use a Docker container. The NeMo Guardrails library provides a Dockerfile that you can use to build a nemoguardrails image. For further information, see the using Docker section.

Integration with LangChain (Optional)

LangChain integration is opt-in. To enable it, set the NEMOGUARDRAILS_LLM_FRAMEWORK=langchain environment variable or call set_default_framework("langchain"). Then install the LangChain packages your configuration requires. After you enable the integration, you can wrap a guardrails configuration around a LangChain chain (or any Runnable), and you can call a LangChain chain from within a guardrails configuration. For more information, refer to the LangChain Integration Documentation.

Evaluation

Evaluating the safety of a LLM-based conversational application is a complex task and still an open research question. To support proper evaluation, the NeMo Guardrails library provides the following:

1. An evaluation tool, i