Aporia

# Aporia ## Docs - [Introduction](https://gr-docs.aporia.com/get-started/introduction.md): Aporia Guardrails mitigates LLM hallucinations, inappropriate responses, prompt injection attacks, and other unintended behaviors in **real-time**. - [Quickstart](https://gr-docs.aporia.com/get-started/quickstart.md): Add Aporia Guardrails to your LLM-based app in under 5 minutes by following this quickstart tutorial. - [Why Guardrails?](https://gr-docs.aporia.com/get-started/why-guardrails.md): Guardrails is a must-have for any enterprise-grade non-creative Generative AI app. Learn how Aporia can help you mitigate hallucinations and potential brand damage. - [Projects overview](https://gr-docs.aporia.com/fundamentals/projects.md): To integrate Aporia Guardrails, you need to create a Project, which groups the configurations of multiple policies. Learn how to set up projects with this guide. - [Extractions](https://gr-docs.aporia.com/fundamentals/extractions.md): Extractions are specific parts of the prompt or response that you define, such as a **question**, **answer**, or **context**. These help Aporia know exactly what to check when running policies on your prompts or responses. - [Overview](https://gr-docs.aporia.com/fundamentals/integration/integration-overview.md): This guide provides an overview and comparison between the different integration methods provided by Aporia Guardrails. - [OpenAI Proxy](https://gr-docs.aporia.com/fundamentals/integration/openai-proxy.md) - [REST API](https://gr-docs.aporia.com/fundamentals/integration/rest-api.md) - [Customization](https://gr-docs.aporia.com/fundamentals/customization.md): Aporia Guardrails is highly customizable, and we continuously add more customization options. Learn how to customize guardrails for your needs. - [Streaming support](https://gr-docs.aporia.com/fundamentals/streaming.md): Aporia Guardrails provides guardrails for both prompt-level and response-level streaming, which is critical for building reliable chatbot experiences. - [Overview](https://gr-docs.aporia.com/fundamentals/ai-gateways/overview.md): By integrating Aporia with your AI Gateway, every new LLM-based application gets out-of-the-box guardrails. Teams can then add custom policies for their project. - [LiteLLM integration](https://gr-docs.aporia.com/fundamentals/ai-gateways/litellm.md) - [Portkey integration](https://gr-docs.aporia.com/fundamentals/ai-gateways/portkey.md) - [Cloudflare AI Gateway](https://gr-docs.aporia.com/fundamentals/ai-gateways/cloudflare.md) - [Team Management](https://gr-docs.aporia.com/fundamentals/team-management.md): Learn how to manage team members on Aporia, and how to assign roles to each member with role-based access control (RBAC). - [AGT Test](https://gr-docs.aporia.com/policies/agt-test.md): A dummy policy to help you test and verify that Guardrails are activated. - [Toxicity](https://gr-docs.aporia.com/policies/toxicity.md): Detect user messages and assistant responses that contain toxic content. - [RAG Hallucination](https://gr-docs.aporia.com/policies/rag-hallucination.md): Detects any response that carries a high risk of hallucinations due to inability to deduce the answer from the provided context. Useful for maintaining the integrity and factual correctness of the information when you only want to use knowledge from your RAG. - [Restricted Phrases](https://gr-docs.aporia.com/policies/restricted-phrases.md): Ensures that the LLM does not use specified prohibited terms and phrases. - [Prompt Injection](https://gr-docs.aporia.com/policies/prompt-injection.md): Detects any user attempt of prompt injection or jailbreak. - [Allowed Topics](https://gr-docs.aporia.com/policies/allowed-topics.md): Checks user messages and assistant responses to ensure they adhere to specific and defined topics. - [Restricted Topics](https://gr-docs.aporia.com/policies/restricted-topics.md): Detects any user message or assistant response that contains discussion on one of the restricted topics ment […gekürzt]