Guardrails Hub | Guardrails AI

This site is not available on Mobile. Please return on a desktop browser.

Visit our main site at guardrailsai.com

Loading ...

Use Cases

🤖 CHATBOTS

📞 CUSTOMER SUPPORT

🔗 STRUCTURED DATA

📚 RAG

📋 SUMMARIZATION

🧑‍💻 CODEGEN

🔠 TEXT2SQL

Risk Category

🧐 ETIQUETTE

🚫 BRAND RISK

📰 FACTUALITY

📝 FORMATTING

❌ INVALID CODE

🔓 JAILBREAKING

💣 CODE EXPLOITS

🔓 DATA LEAKAGE

Infrastructure Requirements

🤖 ML

🧠 LLM

🈚 NA

📜 RULE

Content Type

🧵 STRING

🔲 OBJECT

📃 LIST

💯 INTEGER

🔢 FLOAT

🗃️ SQL

💻 CODE

📄 CSV

🐍 PYTHON

Certification

🏅 GUARDRAILS CERTIFIED

Language

🇬🇧 EN

Validators

Validators are basic Guardrails components that are used to validate an aspect of an LLM workflow. Validators can be used a to prevent end-users from seeing the results of faulty or unsafe LLM responses.

Showing 64 of 64 validators

Arize Dataset Embeddings

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

🚫 BRAND RISK

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

🚫 BRAND RISK

Bert Toxic Language Validator

Validates that the input string does not contain toxic language based on a BERT model.

🚫 BRAND RISK

Bespoke MiniCheck

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

🚫 BRAND RISK

📰 FACTUALITY

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

🚫 BRAND RISK

Competitor Check

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

🚫 BRAND RISK

Correct Language

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.

Cucumber Expression Match

Validates that the input string matches a specified cucumber expression.

🚫 BRAND RISK

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

🔓 DATA LEAKAGE

Extracted Summary Sentences Match

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

📰 FACTUALITY

🚫 BRAND RISK

Extractive Summary

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

📰 FACTUALITY

A Guardrails AI validator to detect gibberish text.

🚫 BRAND RISK

📰 FACTUALITY

High Quality Translation

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

📰 FACTUALITY

LLM RAG Evaluator

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

📰 FACTUALITY

🚫 BRAND RISK

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

🚫 BRAND RISK

A Guardrails AI validator to detect NSFW text

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

🚫 BRAND RISK

Provenance Embeddings

Compares embeddings of generated and source texts to calculate provenance.

📰 FACTUALITY

🚫 BRAND RISK

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

📰 FACTUALITY

🚫 BRAND RISK

QA Relevance LLM Eval

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

🔓 JAILBREAKING

🚫 BRAND RISK

Relevancy Evaluator

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

🚫 BRAND RISK

Restrict to Topic

Determines if the text pertains to a specified topic.

🔓 JAILBREAKING

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

📰 FACTUALITY

Secrets Present

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

🔓 DATA LEAKAGE

Similar To Document

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

📰 FACTUALITY

Similar To Previous Values

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

📰 FACTUALITY

Validates that the input string does not contain negative statements about Sky Electric.

🚫 BRAND RISK

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

Wiki Provenance

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

📰 FACTUALITY

Contains String

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

📝 FORMATTING

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

📝 FORMATTING

❌ INVALID CODE

Endpoint Is Reachable

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

💣 CODE EXPLOITS

❌ INVALID CODE

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

📝 FORMATTING

Exclude SQL Predicates

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.

🔓 DATA LEAKAGE

💣 CODE EXPLOITS

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

Grounded AI Hallucination

A Grounded AI validator that detects hallucinated text

📰 FACTUALITY

Ensure content contains a url.

💣 CODE EXPLOITS

🔓 JAILBREAKING

Grade the generated response based on provided criteria.

📰 FACTUALITY

Passes when totally lowercase.

📝 FORMATTING

Validates that the generated text does not contain any drug names

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

📝 FORMATTING

Politeness Check

Ensure generated output is polite.

Validates that the generated text contains a price quote

🚫 BRAND RISK

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

🚫 BRAND RISK

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

📝 FORMATTING

Redundant Sentences

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.

📝 FORMATTING

Response Evaluator

Evaluate generated output using a provided question.

📰 FACTUALITY

Responsiveness Check

Ensure generated output is polite.

📰 FACTUALITY

Sensitive Topic

A Guardrails AI validator that detects sensitive topics in text.

Sql Column Presence

Checks that schema columns are present in a SQL query.

💣 CODE EXPLOITS

❌ INVALID CODE

Passes when value is *exactly* two words.

📝 FORMATTING

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

🔓 JAILBREAKING

Passes when totally uppercase.

📝 FORMATTING

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

📝 FORMATTING

📰 FACTUALITY

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

📝 FORMATTING

Ensure content is parseable as valid JSON.

📝 FORMATTING

❌ INVALID CODE

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

📝 FORMATTING

Valid OpenAPI Specification

Ensures that a generated output is a valid OpenAPI Specification.

❌ INVALID CODE

📝 FORMATTING

Validates whether the given Python code is syntactically correct.

❌ INVALID CODE

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

📝 FORMATTING

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

❌ INVALID CODE

📝 FORMATTING

Validates that text is a syntactically-valid URL

📝 FORMATTING

Web Sanitization

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

💣 CODE EXPLOITS

© 2024 Guardrails AI