Teradata Partner API

The Partner API is composed of two separate components.  The first component is an in-database function (a Table Operator named API_Request) that enables Vantage users to predict (score) machine learning models that are built on 3rd party partner platforms against Vantage data through a Vantage query.  For example, the release 1.4.0 release supports AWS SageMaker, Azure Machine Learning (and OpenAI), Google Vertex AI, and OpenAI model endpoints, with data passed from Vantage to these external platforms using a web services call, and the results are returned to the Vantage end user as results from the query.

The second component is a Python library (named tdapiclient), which is a companion package of the Teradata Package for Python (teradataml), Teradata's Python package for client-side processing.  The tdapiclient Python packages allows AWS SageMaker, AzureML and/of Google VertexAI users of Vantage to call each CSP’s Python library interfaces to train and predict using data in Teradata Vantage tables.  tdapiclient also transparently converts and copies the Teradata DataFrame to S3, AzureBlob Storage or Google Cloud Storage for training as part of the fit() method which can invoke any of the API’s offered by the CSP.  For inference, it will use the data directly from Vantage input tables or queries via API_Request.  Test inferences on small amounts of data can also be done directly through the client library.  The tdapiclient also wraps the required BYOM calls to productionize the scoring process. 

** Note that for OpenAI and Azure OpenAI, only the API_Request static API is available in tdapiclient. 

Download tdapiclient from: 

https://pypi.org/project/tdapiclient/

For more information, see the Partner API Integration Guide on docs.teradata.com.