exclude_sql_predicates: A Python repository from jonasferoz

Overview

Developed by	Guardrails AI
Date of development	Feb 15th
Validator type	text2sql
Blog	-
License	Apache 2
Input/Output	Output

Description

This validator confirms that all SQL predicates generated by the LLM are valid and allowed.

Requirements

Dependencies: sqlglot

Installation

guardrails hub install hub://guardrails/exclude_sql_predicates

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 import Guard
from guardrails.hub import ExcludeSqlPredicates

# Setup Guard
guard = Guard().use(ExcludeSqlPredicates, predicates=["Drop"], on_fail="exception")

response = guard.validate("select * from employees;")  # Validator passes

try:
    response = guard.validate("drop table departments;")  # Validator fails
except Exception as e:
    print(e)

Output:

Validation failed for field with errors: SQL query contains predicate Drop

API Reference

__init__(self, on_fail="noop")

Initializes a new instance of the Validator class.

Parameters:

predicates (list[str]): The list of SQL predicates to avoid.
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.