Teradata has introduced the Enterprise Vector Store, an in-database solution aimed at enhancing vector data management for Trusted AI applications. This solution is designed to address multi-dimensional, complex problems by effectively combining structured and unstructured data.

The Enterprise Vector Store will leverage NVIDIA NeMo Retriever microservices for accelerated computing and optimized retrieval-augmented generation (RAG). This new offering is built to process large volumes of vector data while maintaining rapid response times, which can be as low as tens of milliseconds.

According to Louis Landry, Teradata’s CTO, “Vector stores are essential to any data management practice, but their impact is limited when they are slow or siloed. Teradata’s expertise in data harmonization enables the Enterprise Vector Store to deliver a necessary foundation for agentic AI in large organizations.”

The new vector solution aims to assist organizations in maximizing value from unstructured data while reducing costs. Additionally, it supports various use cases by managing unstructured data formats such as text, video, and images effectively.

Enterprise Vector Store is currently in private preview, with a general availability anticipated in July. This launch signifies Teradata's ongoing commitment to supporting businesses in their data analytics and AI functionalities.