PyPI Stats

Search

All packages
Top packages

Track packages

meta-evaluator


PyPI page
Home page
Author: aipractice
Summary: Evaluate LLM-as-a-Judge systems by measuring alignment between judge outputs and human annotations
Latest version: 0.3.3
Required dependencies: beartype | boto3 | botocore | google-auth | instructor | litellm | matplotlib | openai | polars | pydantic | python-dotenv | pyyaml | scikit-learn | scipy | tqdm
Optional dependencies: fastapi | mkdocs | mkdocs-material | uvicorn

Downloads last day: 3
Downloads last week: 471
Downloads last month: 768