> ## Documentation Index
> Fetch the complete documentation index at: https://gtm-resouces.getmaxim.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# How can I Evaluate My RAG Application?

> RAG (Retrieval-Augmented Generation) evaluation measures the quality of both the retrieved context and the generated output in a RAG system. It uses metrics like answer correctness, relevance, semantic similarity, context recall, and faithfulness to assess how well the system retrieves and uses information to generate responses.

## Maxim AI's RAG Application Evaluation Capabilities

Maxim AI provides comprehensive tools for RAG application evaluation:

* **Automated Testing Infrastructure**: Run systematic tests measuring metrics across all evaluation dimensions
* **Real-Time Monitoring**: Track performance on production traffic with comprehensive dashboards
* **Component-Level Analysis**: Separately evaluate retrieval and generation to pinpoint issues
* **A/B Testing Framework**: Compare different RAG configurations with controlled rollouts
* **Custom Evaluation Metrics**: Define application-specific success criteria beyond standard metrics
* **Hallucination Detection**: Automatically identify and flag responses containing unsupported claims
* **Cost Analytics**: Track and optimize operational costs with detailed breakdowns
* **User Feedback Integration**: Collect and analyze user feedback to complement automated metrics
* **Alerting**: Get notified when key metrics degrade or anomalous patterns emerge
* **Root Cause Analysis**: Investigate failures systematically to understand performance issues