Introducing Confident Monitor
Confident AI
Docs
Pricing
Products
LLM Evaluation
LLM Evaluation

Benchmark LLM systems with research-backed metrics.

LLM Observability
LLM Observability

Trace, monitor, and alert on production LLM systems.

AI Red Teaming
AI Red Teaming

Stress-test LLM apps against adversarial attacks.

AI Governance
AI Governance

Enforce AI standards and controls across teams.

Contact salesSign Up
Contact salesSign Up

Contextual Precision

Contextual Precision is a single-turn metric used to evaluate a RAG retriever

Overview

The contextual precision metric is a single-turn RAG metric that uses LLM-as-a-judge to evaluate how well your retriever ranks the retrieved context based on the input query.

Required Parameters

These are the parameters you must supply in your test case to run evaluations for contextual precision metric:

inputstringRequired

The input query you supply to your RAG application.

expected_outputstringRequired

The expected output your RAG application has to generate for a given input.

retrieval_contextlist of stringRequired

The retrieved context your retriever outputs for a given input sorted by their rank.

How Is It Calculated?

The contextual precision metric evaluates each retrieved node using an LLM to check if it is correctly ranked for relevance to the input. It then calculates the final score using the following equation:


Contextual Precision=1Num of Relevant Nodes∑k=1n(Num of Relevant Nodes Upto position kk×rk)\text{Contextual Precision} = \frac{1}{\text{Num of Relevant Nodes}}\sum_{k=1}^{n}(\frac{\text{Num of Relevant Nodes Upto position k}}{k} \times r_k)

A high contextual precison score indicates that all the retrieved nodes are in the order of their relevance to the input.

Usage

To run the contextual precision metric on Confident AI, add it to a single-turn metric collection. This will allow you to use contextual precision metric for:

  • Single-turn E2E testing
  • Single-turn component-level testing
  • Online and offline evals for traces and spans

Last updated on

Built byConfident AI