--- title: Evaluate RAG with Human Feedback type: templates category: LLM Evaluations cat: llm-evaluations order: 965 is_new: t meta_description: Evaluate the contextual relevancy of retrieved documents and rate the LLM response. date: 2024-07-26 14:49:29 --- When dealing with RAG (Retrieval-Augmented Generation) pipeline, your goal is not only evaluating a single LLM response, but also incorporating various assessments of the retrieved documents like contextual and answer relevancy and faithfulness. In this example, you will create a labeling interface that aims to evaluate: - Contextual relevancy of the retrieved documents - Answer relevancy - Answer faithfulness For a tutorial on how to use this template with the Label Studio SDK, see [Evaluate LLM Responses](https://api.labelstud.io/tutorials/tutorials/evaluate-llm-responses). ## Configure the labeling interface [Create a project](/guide/setup_project) with the following labeling configuration: ```xml
``` This configuration includes the following elements: * `` - All labeling configurations must include a base `View` tag. In this configuration, the `View` tag is used to configure the display of blocks, similar to the div tag in HTML. It helps in organizing the layout of the labeling interface. * `