Vetiver, the oil of tranquility, is used as a stabilizing ingredient in perfumery to preserve more volatile fragrances.

The goal of vetiver is to provide fluent tooling to version, share, deploy, and monitor a trained model. Functions handle both recording and checking the model's input data prototype, and predicting from a remote API endpoint. The vetiver package is extensible, with generics that can support many kinds of models, and available for both Python and R. To learn more about vetiver, see the documentation at https://vetiver.rstudio.com/

You can use vetiver with:

• scikit-learn
• PyTorch

You can install the released version of vetiver from PyPI:

pip install vetiver

And the development version from GitHub with:

python -m pip install git+https://github.com/rstudio/vetiver-python

A VetiverModel() object collects the information needed to store, version, and deploy a trained model.

from vetiver import mock, VetiverModel

X, y = mock.get_mock_data()
model = mock.get_mock_model().fit(X, y)

v = VetiverModel(model, save_ptype=True, ptype_data=X)

You can version and share your VetiverModel() by choosing a pins "board" for it, including a local folder, RStudio Connect, Amazon S3, and more.

from pins import board_temp
from vetiver import vetiver_pin_write

model_board = board_temp(versioned = True, allow_pickle_read = True)
vetiver_pin_write(model_board, v)

You can deploy your pinned VetiverModel() using VetiverAPI(), an extension of FastAPI.

from vetiver import VetiverAPI
app = VetiverAPI(v, check_ptype = True)

To start a server using this object, use app.run(port = 8080) or your port of choice.

This project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.

• For questions and discussions about deploying models, statistical modeling, and machine learning, please post on RStudio Community.

• If you think you have encountered a bug, please submit an issue.