OSS Alternative - Discover Top Open Source Alternatives to Popular Software

evidentlyai/evidently

An open-source Python library for evaluating, testing, and monitoring ML and LLM systems from experiments to production, supporting tabular and text data with 100+ built-in metrics.

Core Features

Comprehensive evaluation, testing, and monitoring for ML and LLM systems.

Supports diverse data types (tabular, text) and tasks (predictive, generative AI).

Offers 100+ built-in metrics, including data drift, model quality, and LLM judges.

Provides interactive Reports, Test Suites for CI/CD, and a Monitoring Dashboard.

Modular Python library with an open architecture for custom metrics and integration.

Quick Start

pip install evidently

Detailed Introduction

Evidently is an open-source Python library that serves as a robust observability framework for machine learning and large language model systems. It empowers data scientists and MLOps engineers to evaluate, test, and continuously monitor their AI models from development to production. By supporting both tabular and text data, including generative AI applications like RAG, Evidently addresses critical challenges such as data drift, model performance degradation, and LLM quality. With over 100 built-in metrics, interactive reports, and a monitoring dashboard, it provides essential tools for ensuring the reliability, fairness, and performance of AI-powered solutions. Its modular design allows for flexible integration into existing MLOps pipelines.