{"library":"arize-phoenix-evals","type":"library","category":null,"description":"Phoenix Evals provides lightweight, composable building blocks for writing and running evaluations on LLM applications. It offers tools for determining relevance, toxicity, hallucination detection, and more. The library is actively developed, with version 3.0.0 being the current release, and features frequent updates as part of the broader Arize Phoenix ecosystem.","language":"python","status":"active","version":"3.0.0","tags":["LLM","evaluations","MLOps","AI/ML","observability"],"last_verified":"Fri May 22","install":[{"cmd":"pip install arize-phoenix-evals","imports":["from phoenix.evals import create_classifier","from phoenix.evals.llm import LLM","from phoenix.evals import evaluate_dataframe"]},{"cmd":"pip install 'arize-phoenix-evals>=2.0.0' openai","imports":[]}],"homepage":"https://phoenix.arize.com","github":"https://github.com/Arize-ai/phoenix","docs":"https://arize.com/docs/phoenix/","changelog":null,"pypi":"https://pypi.org/project/arize-phoenix-evals/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":100,"avg_install_s":11.6,"avg_import_s":1.88,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/arize-phoenix-evals/compatibility"}}