The Peltarion deployment solution provides the means to quickly test out model prototypes all the way directly in your services. It also provides the stability and scalability you need for a system that will be deployed for longer periods of time with a reliable model for server-to-server integration.
To provide an easy way to make the deep learning models you’ve built on the Peltarion Platform accessible for integration in your services is a key component in making AI operational.
A deployed model will be accessible through a REST API for forward pass queries, either single lookups or in batches.
The Deployment view makes it possible to quickly see which models that are deployed and when they were deployed. A green checkmark indicates that the experiment is deployed and the date is shown in the Deployment info section.
The API is called by sending an HTTP POST to the endpoint shown in the interface. The request body needs to be multipart-form encoded or json.
You can control whether a deployment is enabled for requests and then disable it whenever needed, just toggle the Enable switch.
A deployment can be re-enabled and disabled several times and can be deleted when it’s not relevant anymore. Note that you have to disable the deployment before you can delete it
Both single requests, as well as batch requests, can be sent to the API. Note that if the input batch request contains faulty input samples, the whole response will fail.
A deployment token is required to authenticate the calls. The token is valid from the moment a new deployment is created. The deploy to API is not responding with predictions when the deployment is disabled.