ends_with: A Python repository from Guardrails AI

Overview

Developed by	Guardrails AI
Date of development	Feb 15, 2024
Validator type	Format
Blog	-
License	Apache 2
Input/Output	Output

Description

This validator ensures that a generated string ends with an expected text. This validator works on strings or lists.

Installation

$ guardrails hub install hub://guardrails/ends_with

Usage Examples

Validating string output via Python

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

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

# Setup Guard
guard = Guard().use(EndsWith, end="a", on_fail="exception")

response = guard.validate("Llama")  # Validator passes

try:
    response = guard.validate("Mistral")  # Validator fails
except Exception as e:
    print(e)

Output:

Validation failed for field with errors: Mistral must end with a

Validating a list field within a generated JSON

In this example, we apply the validator to a list field of a generated JSON output by an LLM.

# Import Guard and Validator
from pydantic import BaseModel, Field
from guardrails.hub import EndsWith
from guardrails import Guard

# Initialize Validator
val = EndsWith(end="all", on_fail="exception")


class Article(BaseModel):
    """Info about article."""

    title: str = Field(description="Title of the article")
    tags: list[str] = Field(
        description="Tags that describe the article", validators=[val]
    )


# Create a Guard to check for valid Pydantic output
guard = Guard.from_pydantic(output_class=Article)

# Run LLM output generating JSON through guard
guard.parse(
    """
    {
        "title": "The LLM Infra Stack",
        "tags": ["infra", "ai", "quick read", "all"]
    }
    """
)

try:
    # Run LLM output generating JSON through guard
    guard.parse(
        """
        {
            "title": "The LLM Infra Stack",
            "tags": ["infra", "ai", "quick read"]
        }
        """
    )
except Exception as e:
    print(e)

Output:

Validation failed for field with errors: ['infra', 'ai', 'quick read'] must end with all

API Reference

__init__(self, on_fail="noop")

Initializes a new instance of the Validator class.

Parameters:

end (str): The expected end to the string or list. For strings, the input must end with this character. For lists, the last element must be equal to this string value.
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.

__call__(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:

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.