Deployment
A Deployment represents an instantiation of a machine learning model that is hosted on physical hardware. It serves as a reference to the actual deployment taking place on the underlying infrastructure. Deployments always include a model, and can optionally also host an explainer, transformer, or both. Each Deployment is equipped with an endpoint, enabling communication with the model to retrieve predictions and explanations.
Every Deployment has an owner, who assumes responsibility for its management. Initially, the user creating the deployment automatically becomes its owner.
Interact with a Deployment using the Deployment API, Python Client, or UI.
📄️ Create a Deployment
Creating Deployments is a straightforward process that can be completed in a few simple steps, using the Deployment API, Python Client, or UI.
📄️ Monitor a Deployment
Deeploy intercepts logs (e.g., inferencing logs) and stores and shows key event information so you can monitor your Deployments directly within Deeploy. There are two categories of monitoring:
📄️ Interact with a Deployment
After creating a Deployment, you can easily test it on the Interact tab.
📄️ Integrate a Deployment
This article described how to seamlessly integrate your Deployment with other (business) applications. The integration process involves two steps:
📄️ Deployment Events
On the Events tab, you'll find an overview of events such as Deployment updates and created tokens. Use the filters to easily find specific events.
📄️ Compliance Insights
Track and document a Deployment's compliance to responsible AI standards using the Compliance insights. Its focus is to document how and why decisions for the model are made. Completing the compliance insights is fully optional, but advisible when dealing with high risk applications.
🗃️ Advanced
3 items