Validates that user-generated input does not match the dataset of jailbreak embeddings from Arize AI.

Validates that the output does not contain banned words, using fuzzy search.

Validates that the LLM-generated text is supported by the provided context using BespokeLabs.AI's MiniCheck API.

Validates that the text is free from biases related to age, gender, sex, ethnicity, religion, etc.

Flags mentions of competitors. Fixes responses by filtering out competitor names.

Validate that an LLM-generated text is in the expected language. If the text is not in the expected language, the validator will attempt to translate it to the expected language.

Validates that the input string matches a specified cucumber expression.

Detects personally identifiable information (PII) in text, using Microsoft Presidio.

This validator checks if the extracted summary sentences match the original document.

Uses fuzzy matching to detect if some text is a summary of a document.

A Guardrails AI validator to detect gibberish text.

A validator that checks if a translation is of high quality.

A llama based validator which checks whether a given prompt is safe/unsafe by specifying a set of policies and lists the violating policies when applicable.

This validator uses an LLM Judge to decide whether the LLM response is acceptable in a RAG application.

Validates logical consistency and detects logical fallacies in the model output. Attempts to correct logical fallacies if found.

A Guardrails AI validator to detect NSFW text

Checks for profanity in text, using the alt-profanity-check library.

Compares embeddings of generated and source texts to calculate provenance.

A validator for ensuring the factuality and reducing brand risk in generated content.

Makes a second request to the LLM, asking it if its original response was relevant to the prompt.

Validates that the reference text contains information relevant to answering the original question.

Determines if the text pertains to a specified topic.

Checks if a generated summary covers topics present in a source document.

Detects the secrets present in text by matching against common patterns for API keys and other sensitive information.

A Gemma based validator for moderating user prompts to guard against harmful content by specifying a policy.

Checks if some generated text is similar to a provided document.

Checks if a value is similar to a list of previously known correct values.

Identifies and flags toxic language in text to ensure communications remain professional and appropriate.

A Guardrails AI validator that detects and removes hallucinated text based off Wikipedia

A Guardrails AI validator to check if the LLM-generated text contains a substring.

Checks the CSV file for issues, including mismatched column lengths and inconsistent quote delimiters.

Detects attempts to circumvent safeguards in model conditioning.

Checks if an endpoint can be reached by making a request to it.

Check if a string or list ends with a specified string or list.

This rule checks for the use of particular SQL predicates in the query. It is important to exclude SQL predicates from the query to prevent SQL injection attacks.

Validates that an LLM-generated output (in a financial context) maintains a particular tone.

A Grounded AI validator that detects hallucinated text

Detects personally identifiable information (PII) in text.

Ensure content contains a url.

Grade the generated response based on provided criteria.

Passes when totally lowercase.

Validates that the generated text does not contain any drug names

A validator that scores retrieved RAG context for relevance and usefulness to the user query.

This validator checks if the input is a single line of text.

Ensure generated output is polite.

A Guardrails validator that scores prompts for injection attempts via a secondary LLM.

Validates that the generated text contains a price quote

Parses text to find its readability as a US grade level number (0-12).

Ensures that any generated text is less than a maximum expected reading time.

Identifies redundant sentences in text using fuzzy matching.

Ensure content matches a provided regular expression. This can be used to validate content such as email addresses, phone numbers, and more.

Evaluate generated output using a provided question.

Ensure generated output is polite.

A Guardrails AI validator that detects sensitive topics in text.

Checks that schema columns are present in a SQL query.

Detects toxic language in LLM-generated text using an LLM as the detection backbone. Evaluates text across seven toxicity categories: toxicity, severe toxicity, obscene, threat, insult, identity attack, and sexual explicit content.

Passes when value is *exactly* two words.

A Guardrails AI input validator that validates a prompt for unusualness and trickery.

Passes when totally uppercase.

Verifies an LLM-generated address using Google Maps' Address Validation API.

Checks if a given string is a valid choice from a list of choices.

Guardrails validator that checks for HTML parseability.

Ensure content is parseable as valid JSON.

Ensures the length of a string or list falls between a minimum and maximum.

Ensures that a generated output is a valid OpenAPI Specification.

Validates whether the given Python code is syntactically correct.

Assess whether a generated number is between a maximum and minimum value.

Validates whether the given SQL code is syntactically correct using. Optionally accepts a database schema to validate against using SQLAlchemy.

Validates that text is a syntactically-valid URL

Scans LLM outputs for strings that could cause browser script execution downstream.