---
title: Why evaluate your RAG application?
description: The guide will outline both common issues, as well as recommendations to avoid these pitfalls.
cards:
- id: 0
  image:
    src: /img/rag-evaluation-guide/integrations/maximize-search.svg
    alt: Maximize search
  description: Lack of Precision
- id: 1
  image:
    src: /img/rag-evaluation-guide/integrations/enrich-context.svg
    alt: Enrich context
  description: Poor recall
- id: 2
  image:
    src: /img/rag-evaluation-guide/integrations/avoid-hallucinations.svg
    alt: Avoid hallucinations
  description: “Lost in the middle”
frameworksTitle: Recommended evaluation frameworks
frameworksDescription: In the guide, we explore three popular frameworks that can help simplify your evaluation process.
frameworksCards:
- id: 0
  image:
    src: /img/rag-evaluation-guide/integrations/ragas.svg
    alt: Ragas logo
  description: Ragas is an open-source framework for evaluating retrieval augmented generation systems.
- id: 1
  image:
    src: /img/rag-evaluation-guide/integrations/quotient.svg
    alt: Quotient AI logo
  description: Quotient AI is a platform that focuses on building and deploying RAG systems.
- id: 2
  image:
    src: /img/rag-evaluation-guide/integrations/arize.svg
    alt: Arize logo
  description: Arize Phoenix is a tool designed for monitoring and observability in AI systems, including RAG pipelines.
sitemapExclude: true
---