ONNXSeq2Seq Function | BYOM | Teradata Vantage - ONNXSeq2Seq - Teradata Vantage

Teradata Vantage™ - Bring Your Own Model User Guide

Deployment
VantageCloud
VantageCore
Edition
VMware
Enterprise
IntelliFlex
Lake
Product
Teradata Vantage
Release Number
20.00
Published
February 2026
ft:locale
en-US
ft:lastEdition
2026-02-18
dita:mapPath
fee1607120608274.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
fee1607120608274

ONNXSeq2Seq function uses the open source text sequence models and tokenizers from the Hugging Face AI community converted to ONNX format. The models are trained on vast amounts of text data and learn to predict the next word in a sequence, which allows them to generate coherent and contextually relevant sentences. Both the input and output are always text strings. The function takes table column text data and, using the combination of sequence model and tokenizer to produce human-like text, translates languages and creates summaries of paragraphs.