[This article was first published on The Jumping Rivers Blog, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)

---

Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.This is part one of a two part series on {vetiver}.

• Part 1: Vetiver: First steps inMLOps
• Part 2: Vetiver: Model Deployment (This post)

IntroductionIn our previous blog, we provided an overview of MLOps and the{vetiver} package, creating anddeploying a simple model locally. In this post, we’ll show you how todeploy a model to production using PositConnect,SageMaker, and Docker.

What is DockerDocker is an open-source platform that allowsdevelopers to build, deploy, and run containers. These containers bundleapplication source code with the operating system libraries anddependencies needed to run that code.

Previously, we discussed deploying a ShinyApplicationusing Docker. Similarly, we can deploy a set of APIs to access ourmodel.

---

Data comes in all shapes and sizes. It can often be difficult to know where to start. Whatever your problem, Jumping Rivers can help.

---

Creating a Docker fileThe {vetiver} package simplifies creating a Dockerfile. We simply run:

vetiver::vetiver\_prepare\_docker( pins::board\_connect(), "colin/k-nn", docker\_args = list(port = 8080)) This command accomplishes several tasks:

• Uses the {renv}package to create a list of R package dependencies required to runyour model.
• Creates a file named plumber.R containing the necessary code todeploy an API, essentially just vetiver_api().
• Generates the Dockerfile.

The Dockerfile includes several components. The first component sets theR version, specifies the package repository, and crucially, installs thenecessary system libraries.

FROM rocker/r-ver:4.4.0ENV RENV\_CONFIG\_REPOS\_OVERRIDE https://packagemanager.rstudio.com/cran/latestRUN apt-get update -qq && apt-get install -y --no-install-recommends \ ... The second component copies the renv.lock file and installs the requiredR packages:

COPY vetiver\_renv.lock renv.lockRUN Rscript -e "install.packages('renv')"RUN Rscript -e "renv::restore()" Finally, we have the plumber/API section

COPY plumber.R /opt/ml/plumber.REXPOSE 8080ENTRYPOINT ["R", "-e", "pr <- plumber::plumb('/opt/ml/plumber.R'); pr$run(host = '0.0.0.0', port = 8080)"] which runs the API on port 8080.

The container is built via

docker build --tag my-first-model . The --tag flag allows you to name your Docker image. You can inspectyour stored Docker images with:

docker image listREPOSITORY TAG IMAGE ID CREATED SIZEmy-first-model latest 792af21c775a About a minute ago 1.33GB To run the image, use

docker run --rm --publish 8080:8080 my-first-model Posit Connect / Sage MakerWe can also trivially publish the model to Posit Connect via

vetiver::vetiver\_deploy\_rsconnect(board = pins::board\_connect(), "colin/k-nn") Similarly, we can publish to SageMaker using the functionvetiver_deploy_sagemaker().

For updates and revisions to this article, see the original post

To leave a comment for the author, please follow the link and comment on their blog: The Jumping Rivers Blog.

---

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.

---

Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.Continue reading: Vetiver: Model Deployment