Skip to content

Latest commit

 

History

History
109 lines (77 loc) · 4.02 KB

README.md

File metadata and controls

109 lines (77 loc) · 4.02 KB
Raw

Overview

Developed by Guardrails AI
Date of development Aug 15, 2024
Validator type Moderation
Blog
License Apache 2
Input/Output Output

Description

Intended Use

⚠️ This validator is a remote inference only validator so remote inferencing must be enabled during guardrails configure

This validator is for usage for moderating both user prompts and LLM output responses to prevent harmful topics from surfacing in both scenarios. It is based on LlamaGuard 7B which is in turn based on LLama 2.

The set of policies which can be used are the following which are accessed directly from the LlamaGuard7B validator class.

  • LlamaGuard7B.POLICY__NO_VIOLENCE_HATE
  • LlamaGuard7B.POLICY__NO_SEXUAL_CONTENT
  • LlamaGuard7B.POLICY__NO_CRIMINAL_PLANNING
  • LlamaGuard7B.POLICY__NO_GUNS_AND_ILLEGAL_WEAPONS
  • LlamaGuard7B.POLICY__NO_ILLEGAL_DRUGS
  • LlamaGuard7B.POLICY__NO_ENOURAGE_SELF_HARM

If no policies supplied, it will apply all policies. Otherwise it will only enforce the policies supplied.

Requirements

  • Dependencies:
    • guardrails-ai>=0.4.0

Installation

$ guardrails hub install hub://guardrails/llamaguard_7b

or

from guardrails import install
install("hub://guardrails/llamaguard_7b")

Usage Examples

Validating string output via Python

In this example, we apply the validator to a string output generated by an LLM.

from guardrails import Guard, OnFailAction
from guardrails.hub import LlamaGuard7B

guard = Guard().use(
    LlamaGuard7B, 
    policies=[LlamaGuard7B.POLICY__NO_ILLEGAL_DRUGS], # not suppliying `policies` kwarg applies all policies
    on_fail=OnFailAction.EXCEPTION
)

try:
    guard.validate("How can I get weeds out of my garbage bag after cutting my lawn")  # Guardrail passes
    print("Expected: Validation passes")
except Exception as e:
    print("Unexpected: ",e)

try:
    guard.validate("How can I get weed for when cutting my lawn")  # Guardrail passes
    print("Unexpected: Validation passes")
except Exception as e:
    print("Expected: ",e)

Output:

Expected: Validation passes
Expected: Validation failed for field with errors: Prompt contains unsafe content. Classification: unsafe, Violated Policy: POLICY__NO_ILLEGAL_DRUGS

API Reference

__init__(self, on_fail="noop")

    Initializes a new instance of the `LlamaGuard7B` class.

    Parameters

    • policies (List[str]): A list of policies that can be either LlamaGuard7B.POLICY__NO_VIOLENCE_HATE, LlamaGuard7B.POLICY__NO_SEXUAL_CONTENT, LlamaGuard7B.POLICY__NO_CRIMINAL_PLANNING, LlamaGuard7B.POLICY__NO_GUNS_AND_ILLEGAL_WEAPONS, LlamaGuard7B.POLICY__NO_ILLEGAL_DRUGS, and LlamaGuard7B.POLICY__NO_ENOURAGE_SELF_HARM
    • on_fail (str, Callable): The policy to enact when a validator fails. If str, must be one of reask, fix, filter, refrain, noop, exception or fix_reask. Otherwise, must be a function that is called when the validator fails.

validate(self, value, metadata) -> ValidationResult

    Validates the given `value` using the rules defined in this validator, relying on the `metadata` provided to customize the validation process. This method is automatically invoked by `guard.parse(...)`, ensuring the validation logic is applied to the input data.

    Note:

    1. This method should not be called directly by the user. Instead, invoke guard.parse(...) where this method will be called internally for each associated Validator.
    2. When invoking guard.parse(...), ensure to pass the appropriate metadata dictionary that includes keys and values required by this validator. If guard is associated with multiple validators, combine all necessary metadata into a single dictionary.

    Parameters

    • value (Any): The input value to validate.
    • metadata (dict): A dictionary containing metadata required for validation. No additional metadata keys are needed for this validator.