Evidently

Try it in 3 steps

1. 1

   Install Evidently 0.7.23 in a Python 3.10+ virtual environment

   Pin the core package without enabling any external LLM API integrations.

   python3 -m venv evidently-demo && . evidently-demo/bin/activate && pip install 'evidently==0.7.23'Copy
2. 2

   Create a local Data Drift Report

   Use only local DataFrames to exercise the Report API.

   printf 'import pandas as pd\nfrom evidently import Report\nfrom evidently.presets import DataDriftPreset\nref=pd.DataFrame({"x":[1,2,3,4,5]})\ncur=pd.DataFrame({"x":[1,2,3,5,8]})\nr=Report([DataDriftPreset()]).run(cur, ref)\nprint(type(r).__name__)\n' > evidently-demo/demo.pyCopy
3. 3

   Run the offline evaluation

   Confirm that a report result is produced without calling an external service or model.

   . evidently-demo/bin/activate && python evidently-demo/demo.pyCopy

Built with

• Jupyter Notebook

Categories and tags

GitHub data

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Explore next

• Fluent Bit8,130 Stars

  1 shared tag(s) · 2 shared category(s)

  collect, transform, buffer, and route logs, metrics, and traces

  C
• LangWatch4,911 Stars

  1 shared tag(s) · 2 shared category(s)

  run LLM tracing, evaluations, and agent testing in one production platform

  TypeScript
• Transformers166,909 Stars

  2 shared tag(s) · 1 shared category(s)

  Load, run, and train text, vision, audio, and multimodal models through shared AutoClass and Pipeline APIs

  Python
• Prometheus66,346 Stars

  2 shared tag(s) · 1 shared category(s)

  monitor and alert on time-series metrics with PromQL and pull-based collection

  Go
• Kibana21,304 Stars

  2 shared tag(s) · 1 shared category(s)

  the interface for querying, visualizing, and operating Elasticsearch data

  TypeScript
• Keep12,374 Stars

  2 shared tag(s) · 1 shared category(s)

  centralize monitoring alerts and connect correlation, enrichment, and response workflows

  Python