intel/enterprise-rag-out-guard repository overview

⁠Intel® AI for Enterprise RAG Output Guardrail Service

Part of the Intel® AI for Enterprise RAG ecosystem.

⁠🔍 Overview

The Intel® AI for Enterprise RAG Output Guardrail service provides content filtering and privacy-related capabilities for LLM-generated responses in the Enterprise RAG system. This microservice ensures all output content adheres to content policies, preventing potentially harmful, inappropriate, or inaccurate responses from reaching end users.

This microservice implements LLM Guard⁠ Output Scanners, including:

• BanSubstrings⁠
• BanTopics⁠
• Bias⁠
• Code⁠
• Deanonymize⁠
• JSON⁠
• MaliciousURLs⁠
• NoRefusal⁠
• NoRefusalLight⁠
• ReadingTime⁠
• FactualConsistency⁠
• Regex⁠
• Relevance⁠
• Sensitive⁠
• Sentiment⁠
• Toxicity⁠
• URLReachability⁠

⁠Features

• Real-time filtering of LLM outputs before reaching end users
• Allows to upholds organizational policy compliance

⁠🔗 Related Components

This service integrates with other Intel® AI for Enterprise RAG components:

• Pairs with the Intel® AI for Enterprise RAG Input Guardrail for complete input/output protection
• Guards Intel® AI for Enterprise RAG LLM service against providing inappropriate responses

⁠License

Intel® AI for Enterprise RAG is licensed under the Apache License, Version 2.0.

Copyright © 2024–2026 Intel Corporation. All rights reserved.