Serving and cost

servectl

Serve a model over HTTP in one command, with metrics.

Install

pip install servectl

Once published to PyPI. Also available now from GitHub:

pip install git+https://github.com/jmweb-org/servectl

What it does

You have a model on disk and want to try it behind an HTTP endpoint without writing an app each time. servectl loads the artifact and serves it: a typed /predict, a /health check and Prometheus metrics ready to scrape.

Features

—Loads scikit-learn-style joblib/pickle artifacts.
—/predict and /predict_proba with validation.
—/health and /metrics in Prometheus format.
—Clean 400 responses on bad input.

View the code on GitHub →

Other tools

dsdiff

A git-style diff between two datasets, with distribution drift.

splitcheck

Detect rows leaking between train, validation and test splits.

pii-sweep

Scan datasets for PII before sharing them.