OpenAI Embedding API | Azure OpenAI | Teradata API Integration - OpenAI and Azure OpenAI - Teradata Vantage

Teradata Vantageā„¢ - API Integration Guide for Cloud Machine Learning

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
1.4
Published
September 2023
ft:locale
en-US
ft:lastEdition
2023-09-28
dita:mapPath
mgu1643999543506.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
mgu1643999543506

OpenAI's API platform offers multiple APIs to interact with the large language models. The Embedding API is used to measure the relatedness of text strings. These floating-point measurements, or embeddings, can then be used as input to other machine learning models for further data analysis.

Microsoft's Azure OpenAI Service provides REST API access to OpenAI's language models.

The Teradata API Integration enables Teradata customers to obtain OpenAI text embeddings from Teradata Vantage data, using a large language model deployed in Azure OpenAI or a model provided directly from OpenAI. Users can request text embeddings from an OpenAI or Azure OpenAI model using Teradata input tables or queries, and benefit from the integration of embeddings with Teradata in-database analytics functions.

This integration enables end users to solve and address text analysis problems including the following and more:
  • Text Classification
  • Recommendation
  • Information Retrieval
  • Clustering
  • Anomaly detection
  • Text Search
  • Translation

Users can choose from several language models provided by OpenAI that are tailored for the computation of embeddings. Alternatively, embeddings can be requested from an endpoint of a language model deployed in Azure OpenAI.

The Teradata API Integration with OpenAI and Azure OpenAI includes the following:
  • API_Request In-database Function

    This in-database function enables Vantage users to connect with an endpoint for scoring using a Vantage query (SQL).

  • teradataml Extension Library (tdapiclient)

    This client package provides Python interface to execute API_Request in-database function.

API_Request In-database Function

Typical steps to use API_Request in-database function with OpenAI are:
  • Data cleaning, feature engineering inside Teradata database
  • Exporting data for requesting embeddings to OpenAI or Azure OpenAI
  • Performing in-database analytics on the embeddings obtained

teradataml Extension Library ()

The tdapiclient package provides Python interface to execute API_Request in-database function.