Teradata Launches Enterprise Vector Retailer

Mar 3, 2025 | SAN DIEGO

Designed for cost-effective, sub-second response instances in any respect information volumes, the brand new providing can clear up multi-dimensional, complicated issues by combining structured and unstructured information

Enterprise Vector Retailer will use NVIDIA NeMo Retriever microservices for accelerated compute, optimized RAG

Teradata (NYSE: TDC) at present introduced Teradata Enterprise Vector Retailer, an in-database answer that brings the velocity, energy and multi-dimensional scale of Teradata’s hybrid cloud platform to vector information administration, a vital ingredient for Trusted AI, with future enlargement to incorporate integration of NVIDIA NeMo Retriever microservices, a part of the NVIDIA AI Enterprise software program platform. That includes the flexibility to course of billions of vectors and combine them into pre-existing enterprise programs, with response instances as fast as within the tens of milliseconds, Enterprise Vector Retailer is designed to cost-effectively ship the sophistication required for getting actual worth out of complicated, multifaceted enterprise challenges.

The providing creates a single, trusted repository for all information and builds on the sturdy assist Teradata gives at present for retrieval-augmented era (RAG), whereas working in direction of dynamic agentic AI use circumstances, akin to “augmented name middle” (see instance under).

Vector shops are foundational for any group seeking to leverage agentic AI, however most vector shops require trade-offs that make it prohibitively onerous or costly to make use of in fixing probably the most difficult (and doubtlessly probably the most profitable) enterprise issues. They are often quick, however just for small information units. Or they will handle vector volumes, however not on the velocity that agentic AI use circumstances require. The true magic occurs when organizations can apply each lightning-fast velocity and large compute to unstructured datasets that maintain actual worth when mixed with mission-critical structured information.

“Vector shops are on the root of how we bind reality to generative AI fashions and agentic AI. They’re important to any information administration apply, however their affect is restricted when they’re sluggish or siloed,” mentioned Louis Landry, Teradata’s CTO. “Teradata’s long-standing experience in excessive concurrency and linear scale, in addition to the crucial capacity to harmonize information and assist RAG, means Teradata Enterprise Vector Retailer  delivers on the dynamic, trusted basis massive organizations want for agentic AI.”

Teradata’s Enterprise Vector Retailer is designed to be a performant approach to allow use circumstances that require vector capabilities and RAG purposes. With cost-efficient scaling and close to seamless integration built-in, Enterprise Vector Retailer is predicted to assist enterprises maximize worth and perception from unstructured information whereas decreasing spend. Given Teradata’s benefit in hybrid, Enterprise Vector Retailer is a pure selection for organizations that need to scale flexibly throughout cloud and on-premises environments, constructing in direction of an agentic AI future whereas benefiting from present infrastructure.

By managing unstructured information in multi-modal codecs — textual content, video, photographs, PDFs, and extra — Teradata’s Enterprise Vector Retailer unifies structured and unstructured information for holistic evaluation. It additionally:

• Engages with the complete lifecycle of vector information administration, from embedding era and indexing to metadata administration and clever search 
• Processes this work throughout the present Teradata system, which thrives in versatile deployment choices together with cloud, on-premises, or hybrid 
• Helps industry-leading frameworks like LangChain and RAG, together with the excellent information administration and governance practices wanted for Trusted AI  
• Provides deliberate temporal vector embedding capabilities, which is designed to spice up belief and explainability by monitoring modifications to information over time, enhancing accuracy and choice making. 

A scalable, in-database vector answer constructed with NVIDIA AI

Teradata Enterprise Vector Retailer is predicted to combine NVIDIA NeMo Retriever to supply a number one info retrieval answer with excessive accuracy and information privateness, enabling enterprises to generate enterprise insights in real-time. Builders can fine-tune NeMo Retriever microservices together with neighborhood or customized fashions to construct scalable doc ingestion and RAG purposes which may be linked to proprietary information wherever it resides. NVIDIA NeMo Retriever extraction is designed to allow prospects to make use of info and insights from unstructured information sources akin to PDFs, enabling builders to construct RAG-based purposes which leverage real-time data appended with info from throughout the company IT property.

“Information is important to correct inference for AI purposes,” mentioned Pat Lee, Vice President of Strategic Enterprise Partnerships at NVIDIA. “Teradata Enterprise Vector Retailer, built-in with NVIDIA AI Enterprise and NVIDIA NeMo Retriever, can unlock the institutional data saved in PDFs and different unstructured paperwork to energy clever AI brokers.”

Use Case: Augmented Name Heart

The augmented name middle use case demonstrates how the Teradata Enterprise Vector Retailer makes use of agentic AI and RAG to rework customer support to be sooner, extra environment friendly and tailor-made to every buyer’s wants. AI brokers additionally allow upsell and cross-sell alternatives throughout buyer interactions.

For instance, an insurance coverage firm shops contracts for its tens of millions of consumers in PDF format in an object retailer. It additionally makes use of a hybrid information platform for mission-critical buyer 360 information. When a buyer calls in, a multi-agent system makes use of lightning-fast entry (as little as tens of milliseconds) to harmonized information to supply exact, context-aware solutions to every particular person buyer. 

• “Howdy, how can I make it easier to at present?”
  

  • “Buyer Interplay” Agent communicates in actual time with the client utilizing a pure language interface which is powered by widespread LLMs working as NVIDIA NIM on NVIDIA accelerated compute. 

• “I’m touring to Malaysia. Does my insurance coverage cowl medical bills? Ought to I add something?”

  • “Contract Analyzer” Agent shortly retrieves protection particulars from the PDF copy of the contract utilizing RAG with Enterprise Vector Retailer, which has extracted the data from PDFs and saved as embeddings utilizing NVIDIA NeMo Retriever in Teradata Enterprise Vector Retailer.
  • “Insurance coverage Advisor” Agent makes use of reasoning and choice making to suggest including dental protection throughout the journey, utilizing a propensity-to-buy mannequin and Teradata’s trusted predictive and explainable AI capabilities.

• “Okay, let’s add dental please.”

  • “Actions” Agent makes use of operational analytics and buyer 360 (structured) information in Teradata’s hybrid atmosphere to create a contract for buyer signature.

Availability

Teradata Enterprise Vector Retailer is now obtainable in personal preview, with common availability anticipated in July.