Guardrails Hub | Guardrails AI

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

Visit our main site at guardrailsai.com

Docs Learn more at GuardrailsAI.com

Loading ...

Use Cases

🤖 CHATBOTS

📞 CUSTOMER SUPPORT

🔗 STRUCTURED DATA

📚 RAG

🔗 STRUCTURED DATA

📋 SUMMARIZATION

🧑‍💻 CODEGEN

🔠 TEXT2SQL

Risk Category

🧐 ETIQUETTE

🚫 BRAND RISK

📝 FORMATTING

❌ INVALID CODE

🔓 JAILBREAKING

📰 FACTUALITY

💣 CODE EXPLOITS

🔓 DATA LEAKAGE

Infrastructure Requirements

🤖 ML

🈚 NA

🧠 LLM

📜 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 53 of 53 validators

Competitor Check

Select

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

Correct Language

Select

scb-10x/correct_language

Select

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

Detect Prompt Injection

Select

Finds prompt injection using the Rebuff prompt library.

Extracted Summary Sentences Match

Select

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

Extractive Summary

Select

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

Select

A Guardrails AI validator to detect gibberish text.

High Quality Translation

Select

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

Select

A Guardrails AI validator to detect NSFW text

Select

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

Provenance Embeddings

Select

Compares embeddings of generated and source texts to calculate provenance.

Select

guardrails/provenance_llm

QA Relevance LLM Eval

Select

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

Restrict to Topic

Select

tryolabs/restricttotopic

Select

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

Secrets Present

Select

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

Similar To Document

Select

Checks if some generated text is similar a provided document.

Similar To Previous Values

Select

guardrails/similar_to_previous_values

Select

guardrails/toxic_language

Wiki Provenance

Select

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

Select

hyparam/csv_validator

Endpoint Is Reachable

Select

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

Select

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

Exclude SQL Predicates

Select

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.

Select

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

Select

Ensure content contains a url.

Select

Grade the generated response based on provided criteria.

Select

Passes when totally lowercase.

Select

Validates that the generated text does not contain any drug names

Select

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

Politeness Check

Select

Ensure generated output is polite.

Select

Validates that the generated text contains a price quote

Select

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

Select

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

Redundant Sentences

Select

Identifies redundant sentences in text using fuzzy matching.

Select

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

Response Evaluator

Select

Evaluate generated output using a provided question.

Responsiveness Check

Select

Ensure generated output is polite.

Sensitive Topic

Select

A Guardrails AI validator that detects sensitive topics in text.

Sql Column Presence

Select

numbersstation/sql_column_presence

Select

guardrails/two_words

Select

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

Select

Passes when totally uppercase.

Select

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

Select

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

Select

Ensure content is parseable as valid JSON.

Select

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

Valid OpenAPI Specification

Select

Ensures that a generated output is a valid OpenAPI Specification.

Select

Validates whether the given Python code is syntactically correct.

Select

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

Select

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

Select

Validates that text is a syntactically-valid URL

Web Sanitization

Select

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

© 2024 Guardrails AI