Run an ML model on a dataset file

POST 
/datasets/:id/files/models/:modelid/run

Invokes an ML model run for a selected file (or file set) on the dataset. Caller must have access to the model and owner/editor on the dataset (else AUTH-1002). For OutputType DatasetData, TargetDatasetId is required and must be an active dataset the caller can write to. Body FileName may be a single path or list depending on DatasetProcessingMode. On success starts the invoke-model step function and returns Message "success" with ModelRunId and FileName. Not idempotent: each call creates a new ModelRunId.

Request

Responses

200

Model run accepted. Message is "success". Body also includes ModelRunId (new UUID) and FileName from the request.

Response Headers

Access-Control-Allow-Origin
Access-Control-Allow-Methods
Access-Control-Allow-Headers

400

Validation or authorization failure. Body is {"Message": " - "}. Codes: IPV-1004 (file missing, schema/filetype mismatch, missing TargetDatasetId), IPV-1002, AUTH-1002, DS-1019 / DS-1002 (source or target dataset).

Response Headers

Access-Control-Allow-Origin
Access-Control-Allow-Methods
Access-Control-Allow-Headers

500

Backend/generic failure. Body is {"Message": " - "} (e.g. DS-1003, GE-1008).

Response Headers

Access-Control-Allow-Origin
Access-Control-Allow-Methods
Access-Control-Allow-Headers