# any-guardrail Documentation > Complete documentation for any-guardrail - A Python library providing a single interface to different llm providers. This file contains all documentation pages concatenated for easy consumption by AI systems. --- ## index.md

Project logo

`any-guardrail` is a Python library providing a single interface to different guardrails. ### Getting Started Refer to the [Quickstart](#./quickstart.md) for instructions on installation and usage. ### Guardrails Refer to [Guardrails](#./api/guardrails/index.md) for the parameters for each guardrail. Refer to [AnyGuardrail](#./api/any_guardrail.md) for how to use the `AnyGuardrail` object. ## For AI Systems This documentation is available in two AI-friendly formats: - **[llms.txt](https://mozilla-ai.github.io/any-guardrail/llms.txt)** - A structured overview with curated links to key documentation sections - **[llms-full.txt](https://mozilla-ai.github.io/any-guardrail/llms-full.txt)** - Complete documentation content concatenated into a single file --- ## quickstart.md ### Requirements - Python 3.11 or newer ### Installation You can install the bare bones library as follows (only [`any_guardrails.guardrails.any_llm.AnyLlm`] will be available): ```bash pip install any-guardrail ``` Or you can install it with the required dependencies for different guardrails: ```bash pip install any-guardrail[huggingface] ``` Refer to [pyproject.toml](https://github.com/mozilla-ai/any-guardrail/blob/main/pyproject.toml) for a list of the options available. ### Basic Usage `AnyGuardrail` provides a seamless interface for interacting with the guardrail models. It allows you to see a list of all the supported guardrails, and to instantiate each supported guardrails. Here is a full example: ```python from any_guardrail import AnyGuardrail, GuardrailName, GuardrailOutput guardrail = AnyGuardrail.create(GuardrailName.DEEPSET) result: GuardrailOutput = guardrail.validate("All smiles from me!") assert result.valid ``` ### Troubleshooting Some of the models on HuggingFace require extra permissions to use. To do this, you'll need to create a HuggingFace profile and manually go through the permissions. Then, you'll need to download the HuggingFace Hub and login. One way to do this is: ```bash pip install --upgrade huggingface_hub hf auth login ``` More information can be found here: [HuggingFace Hub](https://huggingface.co/docs/huggingface_hub/en/quick-start#login-command) --- ## api/guardrails/any_llm.md ::: any_guardrail.guardrails.any_llm.any_llm --- ## api/guardrails/deepset.md ::: any_guardrail.guardrails.deepset.deepset --- ## api/guardrails/duo_guard.md ::: any_guardrail.guardrails.duo_guard.duo_guard --- ## api/guardrails/flowjudge.md ::: any_guardrail.guardrails.flowjudge.flowjudge --- ## api/guardrails/glider.md ::: any_guardrail.guardrails.glider.glider --- ## api/guardrails/harm_guard.md ::: any_guardrail.guardrails.harm_guard.harm_guard --- ## api/guardrails/injec_guard.md ::: any_guardrail.guardrails.injec_guard.injec_guard --- ## api/guardrails/jasper.md ::: any_guardrail.guardrails.jasper.jasper --- ## api/guardrails/off_topic.md ::: any_guardrail.guardrails.off_topic --- ## api/guardrails/pangolin.md ::: any_guardrail.guardrails.pangolin.pangolin --- ## api/guardrails/protectai.md ::: any_guardrail.guardrails.protectai.protectai --- ## api/guardrails/sentinel.md ::: any_guardrail.guardrails.sentinel.sentinel --- ## api/guardrails/shield_gemma.md ::: any_guardrail.guardrails.shield_gemma.shield_gemma --- ## api/any_guardrail.md ## AnyGuardrail ::: any_guardrail.api.AnyGuardrail --- ## api/guardrails/index.md ## Guardrails This section documents the available guardrails and their parameters. Select a guardrail to view its API details. ---