Install the SDK

The AI Guard SDK is a Python package that you import into your AI application. It provides classification, redaction, and streaming capabilities.

Requirements

Python 3.13 or higher
pip package manager

Installation Methods

Install from PyPI (Recommended)

pip install "ai-guard-sdk @ git+https://github.com/onetrust-oss/ai-guard-sdk.git"

Install from Source

If you need to install from the source repository:

git clone <repo-url>
cd ai-guard
python -m venv .venv
source .venv/bin/activate
pip install .

📘
Source Repository
The AI Guard SDK source is also available on GitHub.

Verify Installation

After installation, verify the SDK is available:

python -c "from ai_guard import AIGuardClient; print('AI Guard SDK installed successfully')"

Quick Start

Here is a minimal example to verify end-to-end connectivity with your AI Guard service:

from ai_guard import AIGuardClient
from ai_guard.api import (
    AIPlatform,
    ClassificationRequest,
    ClassifierDescriptionDefault,
)

# Initialize the client
client = AIGuardClient(
    "https://ai-guard.example.com:4443",
    token="your-api-key",
    agent_id="my-agent",
    platform=AIPlatform.AMAZON_BEDROCK,
)

# Classify sample text
request = ClassificationRequest(
    context={"actor": "user"},
    classifier_description=ClassifierDescriptionDefault(),
    text="Call me at 321-507-0525",
)

response = client.classify(request)

for match in response.matches:
    print(f"{match.classifier}: '{match.text}' (confidence: {match.confidence})")
# Expected output:
# US_PHONE_NUMBER: '321-507-0525' (confidence: 100)

If you see classification results, your installation and connectivity are working correctly.

Dependencies

The SDK installs the following dependencies automatically:

Package	Version	Purpose
`cryptography`	≥ 43.0.0	TLS certificate pinning support
`python-dotenv`	≥ 1.0.0	Environment variable management
`requests`	≥ 2.25.0	HTTP client for service communication

Virtual Environment (Recommended)

We recommend using a Python virtual environment to isolate AI Guard SDK dependencies:

# Create a virtual environment
python -m venv .venv

# Activate it
source .venv/bin/activate    # macOS/Linux
.venv\Scripts\activate       # Windows

# Install the SDK
pip install ai-guard-sdk

What's Next?

Initialize the Client — Configure the SDK and connect to your AI Guard service
Classify Text — Start classifying text for sensitive data
Redact Sensitive Data — Apply redaction policies to classification results

Updated about 4 hours ago