Install the NeMo Guardrails Library#

Follow these steps to install the NeMo Guardrails library.

Prerequisites#

Verify your system meets the following requirements before installation.

Requirement	Details
Operating System	Windows, Linux, MacOS
Python	3.10, 3.11, 3.12, or 3.13
Hardware	1 CPU with 4GB RAM. The NeMo Guardrails library runs on CPU. External models may require GPUs, which may be deployed separately to the library

Quick Start#

Use the following steps to install the NeMo Guardrails library in a virtual environment.

Create and activate a virtual environment:

Linux/macOS

python3 -m venv .venv
source .venv/bin/activate

Windows (Git Bash)

python -m venv .venv
source .venv/Scripts/activate

Install the NeMo Guardrails library with support for NVIDIA-hosted models. Set NVIDIA_API_KEY to your personal API key generated on build.nvidia.com.
```
pip install "nemoguardrails[nvidia]"
```
Set up an environment variable for your NVIDIA API key.
```
export NVIDIA_API_KEY="your-nvidia-api-key"
```
This is required to access NVIDIA-hosted models on build.nvidia.com. The tutorials and example configurations (examples/configs) in this library include configurations that use NVIDIA-hosted models.

Alternative Installation Methods#

Install the NeMo Guardrails library from source using pip or Poetry. Choose this method if you want to contribute to the library or use the latest development version.

pip

git clone https://github.com/NVIDIA-NeMo/Guardrails.git nemoguardrails
cd nemoguardrails
python -m venv .venv
source .venv/bin/activate
pip install -e .

Poetry

git clone https://github.com/NVIDIA-NeMo/Guardrails.git nemoguardrails
cd nemoguardrails
python -m venv .venv
source .venv/bin/activate
poetry install --extras "nvidia"

When using Poetry, prefix CLI commands with poetry run:

poetry run nemoguardrails server --config examples/configs

Extra Dependencies#

You can install the NeMo Guardrails library with optional extra packages to add useful functionalities. The table below shows a comprehensive list.

Extra	Description
`nvidia`	NVIDIA-hosted model integration through build.nvidia.com
`openai`	OpenAI-hosted model integration
`sdd`	Sensitive data detection using Presidio
`eval`	Evaluation tools for testing guardrails
`tracing`	OpenTelemetry tracing support
`gcp`	Google Cloud Platform language services
`jailbreak`	YARA-based jailbreak detection heuristics
`multilingual`	Language detection for multilingual content
`all`	All optional packages

Some features such as AlignScore have additional requirements. See the feature documentation for details.

Docker#

You can run the NeMo Guardrails library in a Docker container. For containerized deployment, see NeMo Guardrails with Docker.

Troubleshooting Installation Issues#

Use the following information to resolve common installation issues.

C++ Runtime Errors#

The library uses annoy, which requires a C++ compiler. If installation fails:

Linux/macOS

apt-get install gcc g++ python3-dev

Windows

Install Microsoft C++ Build Tools (version 14.0 or greater).