Generate drift and quality reports for ML and LLM pipelines with Evidently

Produce repeatable drift and quality reports after data, model, or prompt changes so regressions are visible before rollout.

Prerequisites

Python 3.9+, pip, datasets or eval outputs for comparison

Installation

Use the upstream install or setup path that matches your environment:

• pip install evidently
• conda install -c conda-forge evidently
• uv run --with evidently evidently ui --demo-projects all
• pip install virtualenv

Requirements and caveats from upstream:

• Evidently is an open-source Python library to evaluate, test, and monitor ML and LLM systems—from experiments to production.
• 🛠️ Python interface for custom metrics.
• View interactive Reports in Python or export as JSON, Python dictionary, HTML, or view in monitoring UI.

Basic usage or getting-started notes:

• ||

• ||

• To install Evidently using the Conda installer, run:

• Source: https://github.com/evidentlyai/evidently

• Extracted from upstream docs: https://raw.githubusercontent.com/evidentlyai/evidently/HEAD/README.md

Documentation

• https://docs.evidentlyai.com/

Source

• Agent Skill Exchange