llm-guard 0.3.0

LLM-Guard is a comprehensive tool designed to fortify the security of Large Language Models (LLMs). By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM-Guard ensures that your interactions with LLMs remain safe and secure.

LLM Guard - The Security Toolkit for LLM Interactions

LLM Guard by Laiyer.ai is a comprehensive tool designed to fortify the security of Large Language Models (LLMs).

Documentation | Demo

Production Support / Help for companies

We're eager to provide personalized assistance when deploying your LLM Guard to a production environment.

• Send Email ✉️

What is LLM Guard?

By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM-Guard ensures that your interactions with LLMs remain safe and secure.

Installation

Begin your journey with LLM Guard by downloading the package:

pip install llm-guard

And then download a preferred spaCy model for Anonymize scanner. By default, you can use:

pip install https://huggingface.co/beki/en_spacy_pii_fast/resolve/main/en_spacy_pii_fast-any-py3-none-any.whl

Getting Started

Important Notes:

• LLM Guard is designed for easy integration and deployment in production environments. While it's ready to use out-of-the-box, please be informed that we're constantly improving and updating the repository.
• Base functionality requires a limited number of libraries. As you explore more advanced features, necessary libraries will be automatically installed.
• Ensure you're using Python version 3.8.1 or higher. Confirm with: python --version.
• Library installation issues? Consider upgrading pip: python -m pip install --upgrade pip.

Examples:

• Get started with ChatGPT and LLM Guard.

Supported scanners

Prompt scanners

• Anonymize
• BanSubstrings
• BanTopics
• Code
• Language
• PromptInjection
• Regex
• Secrets
• Sentiment
• TokenLimit
• Toxicity

Output scanners

• BanSubstrings
• BanTopics
• Bias
• Code
• Deanonymize
• JSON
• Language
• LanguageSame
• MaliciousURLs
• NoRefusal
• Refutation
• Regex
• Relevance
• Sensitive
• Sentiment
• Toxicity

Roadmap

You can find our roadmap here. Please don't hesitate to contribute or create issues, it helps us improve LLM Guard!

Contributing

Got ideas, feedback, or wish to contribute? We'd love to hear from you! Email us.

For detailed guidelines on contributions, kindly refer to our contribution guide.