eval

Evaluate your LLM Model outputs

Overview

This project leverages deepeval, an LLM output evaluation framework to function.

Features

Installation

1. Install Deepeval

deepeval documentation

pip install -u deepeval
deepeval login --confident-api-key <YOUR_DEEPEVAL_KEY>

Dependencies

Make sure you have OPENAI API KEY set

export OPENAI_API_KEY=<YOUR_OPEN_AI_KEY>

Usage

how to run deepeval evaluation

deepeval test run <PROGRAM.py>

How it works

TBD

Notes