H2OPredict Syntax Elements | Vantage BYOM - 3.0 - ONNXPredict Syntax Elements - Teradata Vantage

Teradata Vantageā„¢ - Bring Your Own Model User Guide

Teradata Vantage
Release Number
May 2022
Last Update
Content Type
User Guide
Publication ID
English (United States)
Specify one or more column names to add to the output table in a comma-separated list. Use an asterisk (*) to specify all columns.
[Optional] Specify one or more associations of input table columns to ONNX model inputs in a comma-separated list.
Multiple columns can map to a single ONNX model input tensor.
Table columns can be specified using column names or numerical positional indexes corresponding to columns.
[Optional] When set to true, the parameter does not run scoring, but shows the currently defined fields fully expanded. If ModelInputFieldsMap is not specified, the expected default mapping based on the ONNX inputs defined in the model is shown.
Example: If ModelinputFieldsMap is x=[1:4] and ShowModelInputFieldsMap is set to true, the output is returned as a varchar column:


One row is produced for each AMP, but you can use TOP 1 in your SELECT statement to receive only one row back.The columns that are normally returned when scoring are still returned in the call, but are nulled out.
[Optional] Specify the output fields to add as individual columns instead of the entire JSON output.
[Optional] Valid values are: 'current_cached_model', '*', 'true', 't', 'yes', '1', 'false', 'f', 'no', 'n', or '0'. All of these values are equivalent as this argument applies only to the model specified in the model ON clause, which is assumed to be in the cache.
Important: Do not use the OverwriteCachedModel argument except when you are trying to replace a previously cached model. This applies to any model type (PMML, H2O Open Source, DAI, and ONNX). Using the argument in other cases, including in concurrent queries or multiple times within a short period of time, may lead to an OOM error from garbage collection not being fast enough.
If a model loaded into the memory of the node fits in the cache, it stays in the cache until being evicted to make space for another model that needs to be loaded. Therefore, a model can remain in the cache after the query that loaded it completes. Other queries that use the same model can use it, saving the cost of reloading it into memory.
You want to overwrite a cached model only when it has been updated, to make sure that the Predict function uses the updated model instead of the cached model.
Default behavior: The function does not overwrite cached models.