Overview

Description

Intended Use

This validator ensures that any given output follows a pre-specified regex rule.

Requirements

Dependencies:
- guardrails-ai>=0.4.0
- rstr

Installation

$ guardrails hub install hub://guardrails/regex_match

Usage Examples

Validating string output via Python

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

# Import Guard and Validator
from guardrails.hub import RegexMatch
from guardrails import Guard

# Use the Guard with the validator
guard = Guard().use(
    RegexMatch, regex="Open.*", on_fail="exception"
)

# Test passing response
guard.validate(
    "OpenAI's GPT3.5 model is the latest in the GPT series. It is a powerful language model."
)

try:
    # Test failing response
    guard.validate(
        "MetaAI's Llama2 is the latest in their open-source LLM series. It is a powerful language model."
    )
except Exception as e:
    print(e)

Output:

Validation failed for field with errors: Result must match Open.*

API Reference

__init__(self, regex, match_type=None, on_fail="noop")

Parameters

regex (str): String representing the regex pattern
match_type (Optional[str]): One of search or fullmatch
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

Note:

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.
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.