VAST Data  today announced VAST InsightEngine with NVIDIA, the world’s first solution to securely ingest, process, and retrieve all enterprise data (files, objects, tables, and streams) in real time. As the first application workflow to run on the VAST Data Platform, VAST InsightEngine with NVIDIA accelerates business insights by capturing, embedding, and retrieving real-time data flows, making enterprise data instantly usable for AI-driven decision making.

With the increasing deployment of inference using real-time retrieval-augmented generation (RAG)-enhanced LLMs, organisations face significant, complex data infrastructure challenges in scaling AI to effectively process and extract insights from massive datasets. While hundreds of companies focus on training LLMs, tens of thousands will deploy RAG. This creates new requirements for infrastructure that can classify and search on unstructured and structured datasets as well as new semantic approaches, such as vector and knowledge graphs, with the need for unprecedented speed, scale, simplicity and security. VAST InsightEngine with NVIDIA introduces the first unified system that can handle all of the data functions natively to simplify and deliver real-time AI-powered insights at scale.

The VAST InsightEngine with NVIDIA operates NVIDIA NIM™ microservices, part of the NVIDIA AI Enterprise platform, natively within the VAST Data Platform, embedding the semantic meaning of incoming data using advanced models powered by NVIDIA accelerated computing. The vector and graph embeddings are then stored in the VAST DataBase within milliseconds after the data is captured to ensure that any new file, object, table or streaming data is instantly ready for advanced AI retrieval and inference operations.

“With the VAST Data Platform’s unique architecture, embedded with NVIDIA NIM, we’re making it simple for organisations to extract insights from their data in real-time,” said Jeff Denworth, Co-Founder at VAST Data. “By unifying all elements of the AI retrieval pipeline into an enterprise data foundation, VAST Data InsightEngine with NVIDIA is the industry’s first solution to provide a universal view into all of an enterprise’s structured and unstructured data to achieve advanced AI-enabled decision-making.”

“Generative AI with RAG capabilities has transformed how enterprises can use their data,” said Justin Boitano, Vice President, Enterprise AI at NVIDIA. “Integrating NVIDIA NIM into VAST InsightEngine with NVIDIA helps enterprises more securely and efficiently access data at any scale to quickly convert it into actionable insights.”

VAST InsightEngine with NVIDIA features powerful innovations that set it apart from existing RAG solutions in the market:

• Integration with NVIDIA NIMs: By tapping into NVIDIA NIM microservices integrated within the VAST Data Platform, organisations can embed the semantic meaning from incoming data using models that run on NVIDIA accelerated computing. The embeddings are stored in the VAST DataBase within milliseconds, accelerating insights and simplifying data pipeline operations by automating data workflows.
• Real-Time Data Processing: InsightEngine utilises VAST’s DataEngine to trigger the NVIDIA NIM embedding agent as soon as new data is written to the system, allowing for real-time creation of vector embeddings or graph relationships from unstructured data, and bypassing traditional batch processing delays – enabling near-instant availability for AI tasks. As a result, newly ingested data is immediately searchable and ready for AI operations.
• World’s Most Scalable Semantic Database: Built on the revolutionary VAST DASE architecture, the platform supports the storage of trillions of embeddings, real-time data ingestion and real-time similarity search across massive vector spaces and knowledge graphs. Engineered to handle exabytes of both structured and unstructured enterprise datasets within a unified namespace, the VAST DataBase’s unparalleled scale ensures that enterprises can maintain a seamless, up-to-date representation of their data, without compromising on performance or security.
• Unified Data Architecture: InsightEngine coordinates application workflows that integrate the data storage, processing, and retrieval of all data types into a single platform, where all data indexing happens at the data source. This architecture eliminates the need for separate data lakes and external SaaS platforms, reducing the costs and complexity associated with data management and extract, transform, and load (ETL) processes.
• Data Consistency and Security: The platform ensures that any file system or object storage data update is atomically synced with the vector database and its indices, offering comprehensive, secure data access management and global data provenance to ensure data consistency across multi-tenant environments.

The VAST InsightEngine with NVIDIA represents a significant advancement in real-time AI capabilities within the enterprise environment by automating AI application workflows throughout the data pipeline. Built on the powerful VAST Data Platform, this innovation will help transform the landscape of enterprise AI by seamlessly integrating massive-scale data processing, high-speed vector search, and robust security.

VAST InsightEngine with NVIDIA will be generally available in early 2025. To learn more about VAST InsightEngine and VAST’s collaboration with NVIDIA, visit: https://www.vastdata.com/platform/insightengine-with-nvidia.