Version, Share, Deploy, and Monitor Models
Update the OpenAPI specification using model metadata
Fully attach or load packages for making model predictions
Post new data to a deployed model API endpoint and augment with predic...
Post new data to a deployed SageMaker model endpoint and augment with ...
Model handler functions for API endpoint
Identify data types for each column in an input data prototype
Post new data to a deployed model API endpoint and return predictions
Post new data to a deployed SageMaker model endpoint and return predic...
Objects exported from other packages
vetiver: Version, Share, Deploy, and Monitor Models
Create a Plumber API to predict with a deployable vetiver_model() ob...
Aggregate model metrics over time for monitoring
Model constructor methods
Metadata constructors for vetiver_model() object
Create a vetiver input data prototype
Create an Posit Connect bundle for a vetiver model API
R Markdown format for model monitoring dashboards
Deploy a vetiver model API to Posit Connect
Deploy a vetiver model API to Amazon SageMaker
Create a model API endpoint object for prediction
Create a SageMaker model API endpoint object for prediction
Create a vetiver object for deployment of a trained model
Update model metrics over time for monitoring
Read and write a trained model to a board of models
Plot model metrics over time for monitoring
Create a Plumber API to predict with a deployable vetiver_model() ob...
Generate files necessary to build a Docker container for a vetiver mod...
Use extra files required for deployment
Deploy a vetiver model API to Amazon SageMaker with modular functions
Delete Amazon SageMaker model, endpoint, and endpoint configuration
Convert new data at prediction time using input data prototype
Write a Dockerfile for a vetiver model
Write a deployable Plumber file for a vetiver model
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.
Useful links