On-premise support is available for enterprise customers. If you are interested in running Nextmv Platform on-premise, please contact Nextmv.
It is possible to execute runs outside of the Nextmv Cloud environment and just send the results (input and output) back to the platform. This can be useful if you want to do production runs on your own infrastructure while still using the Nextmv Cloud platform for monitoring and collaboration on non-production models.
The general principle is that you can send a result as part of a run request to the Nextmv Cloud API. This result can be a success
or a failure
, and it can include the output of the run or an error message.
External runs can further be attached to an existing batch experiment using the batch_experiment_id
field. They can also trigger shadow tests, but do not work with switchback tests.
Using the HTTP API
As a prerequisite, you will have to know how to make authenticated requests to the Nextmv Cloud API. You can find more information on how to authenticate your requests in the Cloud API section.
In addition, results use upload IDs to reference the output of the run. To learn more about upload IDs, see the large payloads page.
New application run.
Create new application run.
Recording a successful run
To record a successful run, you need to send a POST request to the runs endpoint. The below payload will create a run with a successful status and an execution duration of 1000ms. The run will have the content behind the upload_id
as input and the content behind the output_upload_id
as output.
Recording a failed run
To record a failed run you can set the status
to failed
and include an error or output upload ID. Note that the content might get truncated in case of a failed run.