76 projects
guardrails-ai-ends-with
Check if a string or list ends with a specified string or list.
guardrails-ai-two-words
Passes when value is *exactly* two words.
guardrails-ai-endpoint-is-reachable
Checks if an endpoint can be reached by making a request to it.
guardrails-ai-detect-system-prompt-leakage
Detects system prompt leakage using fuzzy string matching (via `rapidfuzz`) to compare the LLM's response against a provided system prompt
guardrails-ai-presidio-gliner-pii
Detects personally identifiable information (PII) in text.
guardrails-ai-profanity-free
Checks for profanity in text, using the alt-profanity-check library.
guardrails-ai-responsiveness-check
Ensure generated output is polite.
guardrails-ai-response-evaluator
Evaluate generated output using a provided question.
guardrails-ai-relevancy-evaluator
Validates that the reference text contains information relevant to answering the original question.
guardrails-ai-valid-address
Verifies an LLM-generated address using Google Maps' Address Validation API.
guardrails-ai-valid-html
Guardrails validator that checks for HTML parseability.
guardrails-ai-regex-match
Ensure content matches a provided regular expression. This can be used to validate content such as email addresses, phone numbers, and more.
guardrails-ai-uppercase
Passes when totally uppercase.
guardrails-ai-redundant-sentences
Identifies redundant sentences in text using fuzzy matching.
guardrails-ai-valid-choices
Checks if a given string is a valid choice from a list of choices.
guardrails-ai-valid-open-api-spec
Ensures that a generated output is a valid OpenAPI Specification.
guardrails-ai-valid-sql
Validates whether the given SQL code is syntactically correct using. Optionally accepts a database schema to validate against using SQLAlchemy.
guardrails-ai-reading-time
Ensures that any generated text is less than a maximum expected reading time.
guardrails-ai-valid-range
Assess whether a generated number is between a maximum and minimum value.
guardrails-ai-valid-url
Validates that text is a syntactically-valid URL
guardrails-ai-detect-pii
Detects personally identifiable information (PII) in text, using Microsoft Presidio.
guardrails-ai-reading-level
Parses text to find its readability as a US grade level number (0-12).
guardrails-ai-web-sanitization
Scans LLM outputs for strings that could cause browser script execution downstream.
guardrails-ai-detect-jailbreak
Detects attempts to circumvent safeguards in model conditioning.
guardrails-ai-qa-relevance-llm-eval
Makes a second request to the LLM, asking it if its original response was relevant to the prompt.
guardrails-ai-cucumber-expression-match
Validates that the input string matches a specified cucumber expression.
guardrails-ai-contains-string
A Guardrails AI validator to check if the LLM-generated text contains a substring.
guardrails-ai-provenance-embeddings
Compares embeddings of generated and source texts to calculate provenance.
guardrails-ai-competitor-check
Flags mentions of competitors. Fixes responses by filtering out competitor names.
guardrails-ai-bias-check
Validates that the text is free from biases related to age, gender, sex, ethnicity, religion, etc.
guardrails-ai-prompt-injection-detector
A Guardrails validator that scores prompts for injection attempts via a secondary LLM.
guardrails-ai-unusual-prompt
A Guardrails AI input validator that validates a prompt for unusualness and trickery.
guardrails-ai-valid-json
Ensure content is parseable as valid JSON.
guardrails-ai-bert-toxic
Validates that the input string does not contain toxic language based on a BERT model.
guardrails-ai-saliency-check
Checks if a generated summary covers topics present in a source document.
guardrails-ai-ban-list
Validates that the output does not contain banned words, using fuzzy search.
guardrails-ai-detect-prompt-injection
Finds prompt injection using the Rebuff prompt library.
guardrails-ai-wiki-provenance
A Guardrails AI validator that detects and removes hallucinated text based off Wikipedia
guardrails-ai-shieldgemma-2b
A Gemma based validator for moderating user prompts to guard against harmful content by specifying a policy.
guardrails-ai-secrets-present
Detects the secrets present in text by matching against common patterns for API keys and other sensitive information.
guardrails-ai-valid-length
Ensures the length of a string or list falls between a minimum and maximum.
guardrails-ai-quotes-price
Validates that the generated text contains a price quote
guardrails-ai-sensitive-topics
A Guardrails AI validator that detects sensitive topics in text.
guardrails-ai-similar-to-document
Checks if some generated text is similar to a provided document.
guardrails-jsonformer
A fork of 1rgs' jsonformer maintained by Guardrails AI
guardrails-ai
Adding guardrails to large language models.
guardrails-ai-sdk
Offical Guardrails AI SDK
snowglobe-telemetry-mlflow
MLflow instrumentation for the snowglobe client
snowglobe
client server for usage with snowglobe experiments
guardrails-ai-types
Offical Guardrails AI Types
snowglobe-telemetry-openinference
OpenInference instrumentation for the snowglobe client
guardrails-ai-logic-check
Validates logical consistency and detects logical fallacies in the model output. Attempts to correct logical fallacies if found.
guardrails-ai-extracted-summary-sentences-match
This validator checks if the extracted summary sentences match the original document.
guardrails-ai-lowercase
Passes when totally lowercase.
guardrails-ai-mentions-drugs
Validates that the generated text does not contain any drug names
snowglobe-sdk
A client library for accessing Snowglobe SDK
guardrails-api
Guardrails API
guardrails-api-client
Guardrails API Client.
guardrails-ai-llm-critic
Grade the generated response based on provided criteria.
guardrails-ai-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.
guardrails-ai-provenance-llm
A validator for ensuring the factuality and reducing brand risk in generated content.
guardrails-hub-types
Guardrails Hub Types.
guardrails-ai-llamaguard-7b
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.
guardrails-ai-gibberish-text
A Guardrails AI validator to detect gibberish text.
guardrails-ai-one-line
This validator checks if the input is a single line of text.
guardrails-ai-provenance-nli
Detects and removes hallucinations from LLM-generated text using an NLI model to validate it against a provided context.
guardrails-ai-similar-to-previous-values
Checks if a value is similar to a list of previously known correct values.
guardrails-ai-internal-domains
Identifies internal domains in a string output.
guardrails-ai-nsfw-text
A Guardrails AI validator to detect NSFW text
guardrails-ai-politeness-check
Ensure generated output is polite.
guardrails-ai-sky-validator
Validates that the input string does not contain negative statements about Sky Electric.
guardrails-ai-toxic-language
Identifies and flags toxic language in text to ensure communications remain professional and appropriate.
guardrails-ai-restrict-to-topic
Checks that a text stays on a set of valid topics and avoids invalid ones.
guardrails-ai-has-url
Ensure content contains a url.
guardrails-ai-toxic-language-llm
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.
guardrails-ai-guardrails-pii
Detects personally identifiable information (PII) in text.
