Type Alias MlAPI

Activates the deployed model on this deployment's default alias. The response reports which model was targeted and whether its state actually changed via the qlik-model-id and qlik-state-change response headers. If the model was already active, the request still succeeds but qlik-state-change is NO_CHANGE.

Add deployed models for this deployment

Cancels jobs for an experiment version or batch prediction.

Clears the cache for ml api requests.

Create a deployment

Creates an alias for a deployment.

Create a prediction configuration

Create an experiment

Creates an experiment version. Poll this version and check its status field to determine when models are finished training.

Starts creating profile insights for an experiment dataset. This is an asynchronous operation. A 202 Accepted response indicates that the process has started successfully. Use the link in the response to check the status.

Deactivates the deployed model on this deployment's default alias. The response reports which model was targeted and whether its state actually changed via the qlik-model-id and qlik-state-change response headers. If the model was already inactive, the request still succeeds but qlik-state-change is NO_CHANGE.

Delete a deployment

Delete an alias from a deployment.

Delete a batch prediction

Deletes the schedule from a batch prediction.

Delete an experiment

Delete an experiment version

Get a deployment

Retrieves an alias that exists on the deployment.

Retrieves a list of aliases based on filter parameters for a deployment.

Retrieve a batch prediction

List batch prediction configurations

Retrieves the schedule for a batch prediction.

List deployments

Get an experiment

Get a model

List models

Retrieves a list of experiments based on provided filter and sort parameters.

Get an experiment version

List experiment versions

Retrieves profile insights for the specified dataset. If you received a 202 Accepted response from POST /ml/profile-insights, poll this endpoint until a 200 OK response with ready status is returned.

Retrieves profile insights for the specified dataset. If you received a 202 Accepted response from POST /ml/profile-insights, poll this endpoint until a 200 OK response with ready status is returned.

Update a deployment

Updates an alias for a deployment.

Updates a batch prediction

Update an experiment

Update an experiment version

Run a batch prediction

Returns model recommendations for a specified experiment, including the best-performing, fastest, and most accurate models based on evaluation metrics.

Remove deployed models from this deployment

Generate predictions in a synchronous request/response

Generate predictions in a synchronous request/response

Adds a schedule to a batch prediction.

Updates the schedule for a batch prediction.