agentskillexchange Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard
Screen prompts and responses with input and output scanners before an LLM interaction reaches production users or downstream systems.
Prerequisites
Python 3.9+, application or agent code that can wrap LLM input and output handling
Installation
Use the upstream install or setup path that matches your environment:
- pip install llm-guard
Requirements and caveats from upstream:
- Base functionality requires a limited number of libraries. As you explore more advanced features, necessary libraries
- Ensure you're using Python version 3.9 or higher. Confirm with: python --version.
Basic usage or getting-started notes:
Begin your journey with LLM Guard by downloading the package:
sh
Important Notes:
Extracted from upstream docs: https://raw.githubusercontent.com/protectai/llm-guard/HEAD/README.md