Package index • vetiver

Handling vetiver objects

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

vetiver_model() new_vetiver_model(): Create a vetiver object for deployment of a trained model

vetiver_pin_write() vetiver_pin_read(): Read and write a trained model to a board of models

vetiver_api() vetiver_pr_post() vetiver_pr_docs(): Create a Plumber API to predict with a deployable vetiver_model() object

vetiver_write_plumber(): Write a deployable Plumber file for a vetiver model

vetiver_write_docker(): Write a Dockerfile for a vetiver model

vetiver_prepare_docker(): Generate files necessary to build a Docker container for a vetiver model

vetiver_endpoint(): Create a model API endpoint object for prediction

predict(<vetiver_endpoint>): Post new data to a deployed model API endpoint and return predictions

augment(<vetiver_endpoint>): Post new data to a deployed model API endpoint and augment with predictions

Posit Connect

Deploy your vetiver model to Posit Connect.

vetiver_deploy_rsconnect(): Deploy a vetiver model API to Posit Connect

vetiver_create_rsconnect_bundle(): Create an Posit Connect bundle for a vetiver model API

SageMaker

Deploy your vetiver model to Amazon SageMaker.

vetiver_deploy_sagemaker(): Deploy a vetiver model API to Amazon SageMaker

vetiver_endpoint_sagemaker(): Create a SageMaker model API endpoint object for prediction

predict(<vetiver_endpoint_sagemaker>): Post new data to a deployed SageMaker model endpoint and return predictions

augment(<vetiver_endpoint_sagemaker>): Post new data to a deployed SageMaker model endpoint and augment with predictions

vetiver_sm_build() vetiver_sm_model() vetiver_sm_endpoint(): Deploy a vetiver model API to Amazon SageMaker with modular functions

vetiver_sm_delete(): Delete Amazon SageMaker model, endpoint, and endpoint configuration

Monitoring deployed models

Monitor a deployed vetiver_model() with a dashboard.

vetiver_compute_metrics(): Aggregate model metrics over time for monitoring

vetiver_pin_metrics(): Update model metrics over time for monitoring

vetiver_plot_metrics(): Plot model metrics over time for monitoring

vetiver_dashboard() get_vetiver_dashboard_pins() pin_example_kc_housing_model(): R Markdown format for model monitoring dashboards

Developer functions

These functions are helpful for developers extending vetiver for other types of models.

api_spec() glue_spec_summary(): Update the OpenAPI specification using model metadata

attach_pkgs() load_pkgs(): Fully attach or load packages for making model predictions

handler_startup() handler_predict(): Model handler functions for API endpoint

map_request_body(): Identify data types for each column in an input data prototype

vetiver_create_description() vetiver_prepare_model(): Model constructor methods

vetiver_meta() vetiver_create_meta(): Metadata constructors for vetiver_model() object

vetiver_ptype() vetiver_create_ptype(): Create a vetiver input data prototype

vetiver_type_convert(): Convert new data at prediction time using input data prototype