Deploy models into REST endpoints
Project description
vetiver 🏺
Vetiver, the oil of tranquility, is used as a stabilizing ingredient in perfumery to preserve more volatile fragrances.
Python parallel to R vetiver package.
Usage
vetiver is used to deploy a trained model to predict from a remote endpoint.
Key features include:
- Simple: designed to fit into a data scientist's natural workflow
- Robust: ability to check input data types to minimize type failures in a model
- Advanced support: easily deploy multiple endpoints to handle pre- and post- processing
- Based on FastAPI, using OpenAPI
Get Started
pip install vetiver
To begin, initialize a VetiverModel with a trained model and an example of data (usually training data) to built a data prototype.
my_model = VetiverModel(model = linear_reg, ptype_data = train_data)
Next, you can build a model-aware API and run it locally.
my_app = VetiverAPI(my_model)
my_app.run()
To view more, see this repo of examples.
License
Contributing
This project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
