Skip to main content

Getting Started


pip install guardrails-ai

Create Input and Output Guards for LLM Validation

  1. Download and configure the Guardrails Hub CLI.

    pip install guardrails-ai
    guardrails configure
  2. Install a guardrail from Guardrails Hub.

    gudardrails hub install hub://guardrails/regex_match
  3. Create a Guard from the installed guardrail.

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

    # Initialize the Guard with
    val = Guard().use(

    guard.parse("Caesar") # Guardrail Passes
    guard.parse("Caesar is a great leader") # Guardrail Fails
  4. Run multiple guardrails within a Guard. First, install the necessary guardrails from Guardrails Hub.

    guardrails hub install hub://guardrails/competitor_check
    guardrails hub install hub://guardrails/toxic_language

    Then, create a Guard from the installed guardrails.

    from guardrails.hub import RegexMatch, ValidLength
    from guardrails import Guard

    guard = Guard().use(
    ValidLength(min=1, max=32)

    guard.parse("Caesar") # Guardrail Passes
    guard.parse("Caesar is a great leader") # Guardrail Fails

Use Guardrails to generate structured data from LLMs

Let's go through an example where we ask an LLM to generate fake pet names. To do this, we'll create a Pydantic BaseModel that represents the structure of the output we want.

from pydantic import BaseModel, Field

class Pet(BaseModel):
pet_type: str = Field(description="Species of pet")
name: str = Field(description="a unique pet name")

Now, create a Guard from the Pet class. The Guard can be used to call the LLM in a manner so that the output is formatted to the Pet class. Under the hood, this is done by either of two methods:

  1. Function calling: For LLMs that support function calling, we generate structured data using the function call syntax.
  2. Prompt optimization: For LLMs that don't support function calling, we add the schema of the expected output to the prompt so that the LLM can generate structured data.
from guardrails import Guard
import openai

prompt = """
What kind of pet should I get and what should I name it?

guard = Guard.from_pydantic(output_class=Pet, prompt=prompt)

validated_output, *rest = guard(,


This prints:

"pet_type": "dog",
"name": "Buddy