Teradata Package for Generative AI | 20.00.00.03 - Teradata Package for Generative AI - Teradata VantageCloud Lake

Lake - Analyze Your Data with ClearScape Analytics™

Deployment
VantageCloud
Edition
Lake
Product
Teradata VantageCloud Lake
Release Number
Published
February 2025
ft:locale
en-US
ft:lastEdition
2026-02-20
dita:mapPath
tcl1683670667798.ditamap
dita:ditavalPath
pny1626732985837.ditaval
dita:id
tcl1683670667798

Teradata Package for Generative AI provides a comprehensive set of APIs tailored for various text analytics applications, empowering you to efficiently process and analyze text data from diverse sources like emails, academic papers, social media posts, and product reviews. This enables you to gain insights with precision and depth that rival or surpass human analysis.

Use Teradata Package for Generative AI to conduct text analytics tasks with data on Vantage and large language models from:
  • AWS Bedrock
  • Azure AI
  • Google Gemini
  • Hugging Face
  • NVIDIA NIM

The Teradata Enterprise Vector Store is engineered to efficiently store, index, and search high-dimensional vector embeddings. The teradatagenai package offers Python APIs that simplify access to and management of the vector store, allowing users to build their own natural language applications using Vantage as the foundational compute and storage engine.

teradatagenai Package

The teradatagenai package operates on the client system and is tailored to provide a diverse set of text analytics capabilities that run on Vantage, including:
  • KeyPhrase Extraction
  • Entity Recognition
  • PII (Personally Identifiable Information) Entity Recognition
  • PII (Personally Identifiable Information) Masking
  • Language Detection
  • Language Translation
  • Text Summarization
  • Sentiment Analysis
  • Text Classification
  • Embedding Generation
  • Asking LLM

These functions use the capabilities of models provided by AWS Bedrock, Azure AI, Google Gemini, Hugging Face, and NVIDIA NIM. The outcomes are capable of interacting with Vantage to deliver consistent results. Additionally, it provides access to the Enterprise Vector Store, which is specifically designed for the efficient storage, indexing, and searching of high-dimensional vector embeddings.