InputGuardrail

org.llm4s.agent.guardrails.InputGuardrail

trait InputGuardrail extends Guardrail[String]

Validates user input before agent processing.

Input guardrails run BEFORE the LLM is called, validating:

Attributes

Graph
Supertypes: trait Guardrail[String]

class Object

trait Matchable

class Any
Known subtypes: class LengthCheck

class PIIDetector

class PIIMasker

class ProfanityFilter

class PromptInjectionDetector

class RegexValidator

class TopicBoundaryGuardrail
Show all

Optional: Transform the input after validation. Default is identity (no transformation).

Compose this guardrail with another sequentially.

The second guardrail runs only if this one passes.

Optional description of what this guardrail validates.

Name of this guardrail for logging and error messages.

Validate a value.

This is a PURE FUNCTION - no side effects allowed. Same input always produces same output.

In this article

Generated with