Overview

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

Description

Checks that schema columns are present in a SQL query.

Requirements

Dependencies:
- guardrails-ai>=0.4.0
- sqlglot

Installation

guardrails hub install hub://numbersstation/sql_column_presence

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 SqlColumnPresence

# Setup Guard
guard = Guard().use(SqlColumnPresence, ["name", "breed", "weight"], on_fail="exception")

guard.validate(
    "SELECT name, AVG(weight) FROM animals GROUP BY name"
)  # Validator passes

try:
    guard.validate(
        "SELECT name, color, AVG(weight) FROM animals GROUP BY name, color"
    )  # Validator fails
except Exception as e:
    print(e)

Output:

Validation failed for field with errors: Columns [color] not in [weight, name, breed]

Validating JSON output via Python

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

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

# Initialize Validator
val = SqlColumnPresence(["name", "breed", "weight"])

# Create Pydantic BaseModel
class Report(BaseModel):
		name: str
		query: str = Field(validators=[val])

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

# Run LLM output generating JSON through guard
guard.parse("""
{
	"name": "Canine Lookup",
	"query": "SELECT name, AVG(weight) FROM animals GROUP BY name"
}
""")

API Reference

__init__(self, cols, on_fail="noop")

Parameters

cols (List[str]): The list of valid columns.
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.