Guardrails AI ORG

Adding guardrails to large language models.

A Javascript wrapper for guardrails-ai

No description.

FastAPI server for hosting Guardrails AI in your own environment.

Guardrails AI: PII Filter - Validates that any text does not contain any PII

A test validator repo that includes just the regex validator

A bare minimum deployment of guardrails as a service.

A Guardrails AI input validator that detects if the user is trying to jailbreak an LLM using unusual prompting techniques that involve jailbreaking and tricking the LLM

A Guardrials Hub validator used to detect if prompt injection is present

Guardrails AI: Provenance LLM - Validates that the LLM-generated text is supported by the provided contexts.

Prototype Jailbreak Detection Guard

Adding guardrails to large language models.

No description.

Guardrails AI: Profanity free - Validates that a translated text does not contain profanity language.

No description.

Guardrails AI: Toxic language - Validates that the generated text is toxic

A Guardrails AI validator that detects inappropriate/ Not Safe For Work (NSFW) text during validation

OpenAPI Specifications and scripts for generating SDKs for the various Guardrails services

A Guardrails Validator that allows you to ban certain keywords using fuzzy matching

Guardrails AI: Provenance Embeddings - Validates that LLM-generated text matches some source text based on distance in embedding space

Validator for GuardrailsHub to check if a text is related with a topic.

A Neural Framework for MT Evaluation

Guardrails AI: Similar to Document - Validates that a value is similar to the document

Guardrails AI: QA Relevance LLM eval - Validates that an answer is relevant to the question asked by asking the LLM to self evaluate

Guardrails AI: Lower case validator - Validates that a value is lower case

Guardrails AI: Redundant sentences - Removes redundant sentences from a string

No description.

Guardrails AI: Valid SQL - Validates that there are no SQL syntactic bugs in the generated code.

Guardrails AI: Excludes SQL predicates - Validates that the SQL query does not contain certain predicates

Adding guardrails to large language models.

📖 Generate markdown API documentation from Google-style Python docstring. The lazy alternative to Sphinx.

A Guardrails AI validator that checks whether an LLM-generated response contains gibberish

No description.

Guardrails AI: Valid JSON - Validates that a value is parseable as valid JSON.

A Guardrails AI validator that validates LLM responses by grading + evaluating them against a given set of criteria / metrics

Guardrails AI: Saliency check - Checks that the summary covers the list of topics present in the document

A Guardrails AI validator that validates LLM responses by re-prompting the LLM to self-evaluate

Guardrails AI: Detect Secrets - Validates whether the generated code snippet contains any secrets.

Guardrails AI: Competitor Check - Validates that LLM-generated text is not naming any competitors from a given list

A Guardrail Validator for RAG retrieved context Usefulness and Relevance

A Bulletproof Way to Generate Structured JSON from Language Models

No description.

No description.

Guardrails AI: Valid choices - validates that a value is within the acceptable choices

Guardrails AI: Valid url - Validates that a value is a valid URL

Guardrails AI: Valid range - validates that a value is within a range

A Guardrails AI validator that validates whether a given address is valid

Guardrails AI: Upper case - Validates that a value is upper case

Guardrails AI: Ends with validator - Validates that a list or a string ends with a given value

Guardrails AI: One Line validator - Validates that a value is a single line, based on whether or not the output has a newline character

Guardrails AI: Reading time validator - Validates that the a string can be read in less than a certain amount of time.

Guardrails AI: Two words validator - Validates that a value is two words

Guardrails AI: Endpoint is Reachable - Validates that a value is a reachable URL

No description.

No description.

Guardrails AI: Extracted Summary Sentences Match - Validates that the extracted summary sentences match the original text by performing a cosine similarity in the embedding space

Validate that the generated text does not contain a drug name

Guardrails AI: Valid length - Validates that the length of value is within the expected range

No description.

No description.

Shared interfaces defined in JSON Schema.

No description.

No description.

Data structures used in the Guardrails Hub

Monorepo for updated guardrails-ai open source libraries.

No description.

A validator that checks for system prompt leakage in LLM output.

Client side example using Guardrails AI in a Dockerized application

A Guardrails AI validator that detects hallucinations using Wikipedia as the source of truth

No description.

A validator which ensures that a generated output answers the prompt given.

Telemetry instrumentation for the snowglobe client using OpenInference semantics.

Uses an LLM to determine whether text is toxic.

No description.

No description.

No description.

Fork of BrainLogic AI's validator

No description.

Scans LLM outputs for code, code fragments, and keys

Check if the generated text contains a price quote in the given currency

No description.

No description.

No description.

No description.

No description.

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

No description.

A validator that checks if a generated output includes a url.

No description.

No description.

No description.

A url summarizer, made safe with Guardrails

No description.

SQL validator

Check the presence of PHI in a given text

Valid Python Guardrails AI validator - Validates that there are no Python syntactic bugs in the generated code.