Deployment is a critical component for gaining real value from a model, yet unfortunately it’s also where a lot of models get stuck. DataRobot offers a comprehensive set of solutions around model deployment as well as model monitoring, management, and governance through MLOps. These solutions work well with the different personas involved in MLOps and are agnostic to your current platform and choice of model-development environment.
With MLOPs you can deploy models using various solutions:
Easily deploy and interact with a DataRobot-built model using the REST API.
Deploy a model built with tools like Python or R using DataRobot Custom Inference Models.
Export a DataRobot-built model as a container.
Export a DataRobot-built model as scoring code.
Deploy a remote agent for an external model.
And you can monitor, manage, and govern all of these models in one place:
Monitor any of these models for service health, data drift, and accuracy.
Set up custom Notifications that tell you when your deployment needs your attention.
Manage and Replace your models easily while keeping a documented record of every change that occurs.
Establish Governance roles and processes for each deployment.
To get the big picture of MLOps, see these resources which show the entire product from end-to-end:
Then you have the model you want, you just need to deploy it. You can do this all through one system, regardless of how you created the model.DataRobot gives you three options for deployment: using REST APIs, using Custom Inference Models, or using Portable Prediction Servers (PPSs) with MLOps agents.
Monitoring All Your Models with DataRobot Agents—Do you have machine learning models that are running outside of DataRobot? Is your organization using a set of diverse tools and platforms to deploy models, despite what IT wants? This session introduces DataRobot's MLOps agent framework which allows anyone to monitor models deployed externally, to DataRobot MLOps platform.