Skip to main content

POST /v1/predict

Make predictions using all loaded forecasting models in parallel, useful for ensembling or A/B testing.

Example:

curl --request POST \
  --url http://localhost:8090/v1/predict \
  --data '{
    "predictions": [
        {
            "model_name": "drive_stats_a"
        },
        {
            "model_name": "drive_stats_b"
        }
    ]
}'

Parameters:

  • model_name: References a model name defined in the spicepod.yaml.
{
  "duration_ms": 81,
  "predictions": [
    {
      "status": "Success",
      "model_name": "drive_stats_a",
      "model_version": "1.0",
      "lookback": 30,
      "prediction": [0.45, 0.5, 0.55],
      "duration_ms": 42
    },
    {
      "status": "Success",
      "model_name": "drive_stats_b",
      "model_version": "1.0",
      "lookback": 30,
      "prediction": [0.43, 0.51, 0.53],
      "duration_ms": 42
    }
  ]
}
Limitations
  • Univariate predictions only.
  • Multiple covariates.
  • Covariate and output variate must have a fixed time frequency.
  • No support for discrete or exogenous variables.

GET /v1/models/:name/predict​

Make a prediction using a specific model.

Example:

curl "http://localhost:8090/v1/models/my_model_name/predict"

Parameters:

  • name: References the model name defined in the spicepod.yaml.

Response​

{
    "status": "Success",
    "model_name": "my_model_name",
    "model_version": "1.0",
    "lookback": 30,
    "prediction": [0.45, 0.50, 0.55],
    "duration_ms": 123
}