Skip to content

@guardrails-ai Guardrails AI

Change the repository type filter

All

    Repositories list

    85 repositories

    • guardrails-api

      Public
      Docker compose stub of Guardrails as a Service
      Python
      •
      Other
      •0•5•5•7•Updated Nov 1, 2024Nov 1, 2024

    • guardrails

      Public
      Adding guardrails to large language models.
      aiopenaigpt-3llmfoundation-model
      Python
      •
      Apache License 2.0
      •306•4k•35•5•Updated Nov 1, 2024Nov 1, 2024

    • detect_pii

      Public
      Guardrails AI: PII Filter - Validates that any text does not contain any PII
      Python
      •
      Apache License 2.0
      •1•6•4•2•Updated Oct 31, 2024Oct 31, 2024

    • bias_check

      Public
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Oct 31, 2024Oct 31, 2024

    • politeness_check

      Public
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Oct 30, 2024Oct 30, 2024

    • qa_relevance_llm_eval

      Public
      Guardrails AI: QA Relevance LLM eval - Validates that an answer is relevant to the question asked by asking the LLM to self evaluate
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Oct 30, 2024Oct 30, 2024

    • sensitive_topics

      Public
      Python
      •
      Apache License 2.0
      •1•0•0•2•Updated Oct 30, 2024Oct 30, 2024

    • responsiveness_check

      Public
      A validator which ensures that a generated output answers the prompt given.
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Oct 30, 2024Oct 30, 2024

    • detect-jailbreak

      Public
      Prototype Jailbreak Detection Guard
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Oct 30, 2024Oct 30, 2024

    • cucumber_expression_match

      Public
      Python
      •
      Apache License 2.0
      •0•0•0•1•Updated Oct 29, 2024Oct 29, 2024

    • provenance_llm

      Public
      Guardrails AI: Provenance LLM - Validates that the LLM-generated text is supported by the provided contexts.
      Python
      •
      Apache License 2.0
      •1•0•0•6•Updated Oct 25, 2024Oct 25, 2024

    • french_toxic_language

      Public
      Python
      •
      Apache License 2.0
      •1•0•0•1•Updated Oct 23, 2024Oct 23, 2024

    • restricttotopic

      Public
      Validator for GuardrailsHub to check if a text is related with a topic.
      Python
      •
      Apache License 2.0
      •5•1•0•3•Updated Oct 22, 2024Oct 22, 2024

    • guardrails-api-client

      Public
      OpenAPI Specifications and scripts for generating SDKs for the various Guardrails services
      JavaScript
      •1•1•1•0•Updated Oct 18, 2024Oct 18, 2024

    • interfaces

      Public
      Shared interfaces defined in JSON Schema.
      JavaScript
      •0•0•1•0•Updated Oct 18, 2024Oct 18, 2024

    • NeMo-Guardrails

      Public
      NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
      Python
      •
      Other
      •387•0•0•0•Updated Oct 17, 2024Oct 17, 2024

    • toxic_language

      Public
      Guardrails AI: Toxic language - Validates that the generated text is toxic
      Jupyter Notebook
      •
      Apache License 2.0
      •1•2•4•2•Updated Oct 17, 2024Oct 17, 2024

    • llamaguard-7b

      Public
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Oct 1, 2024Oct 1, 2024

    • competitor_check

      Public
      Guardrails AI: Competitor Check - Validates that LLM-generated text is not naming any competitors from a given list
      Jupyter Notebook
      •
      Apache License 2.0
      •3•1•0•3•Updated Sep 17, 2024Sep 17, 2024

    • nsfw_text

      Public
      A Guardrails AI validator that detects inappropriate/ Not Safe For Work (NSFW) text during validation
      Python
      •
      Apache License 2.0
      •2•1•0•1•Updated Sep 17, 2024Sep 17, 2024

    • high_quality_translation_validator

      Public
      Fork of BrainLogic AI's validator
      Python
      •
      Apache License 2.0
      •4•0•0•0•Updated Sep 16, 2024Sep 16, 2024

    • financial_tone

      Public
      Python
      •
      Apache License 2.0
      •2•0•0•0•Updated Sep 16, 2024Sep 16, 2024

    • web_sanitization

      Public
      Scans LLM outputs for code, code fragments, and keys
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Sep 16, 2024Sep 16, 2024

    • valid_url

      Public
      Guardrails AI: Valid url - Validates that a value is a valid URL
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Sep 16, 2024Sep 16, 2024

    • valid_range

      Public
      Guardrails AI: Valid range - validates that a value is within a range
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Sep 16, 2024Sep 16, 2024

    • valid_json

      Public
      Guardrails AI: Valid JSON - Validates that a value is parseable as valid JSON.
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Sep 16, 2024Sep 16, 2024

    • valid_address

      Public
      A Guardrails AI validator that validates whether a given address is valid
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Sep 16, 2024Sep 16, 2024

    • uppercase

      Public
      Guardrails AI: Upper case - Validates that a value is upper case
      Python
      •
      Apache License 2.0
      •0•1•0•0•Updated Sep 16, 2024Sep 16, 2024

    • unusual_prompt

      Public
      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
      Python
      •
      Apache License 2.0
      •2•3•0•0•Updated Sep 16, 2024Sep 16, 2024

    • response_evaluator

      Public
      A Guardrails AI validator that validates LLM responses by re-prompting the LLM to self-evaluate
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Sep 16, 2024Sep 16, 2024