{"id":5526,"date":"2025-05-17T07:09:56","date_gmt":"2025-05-16T23:09:56","guid":{"rendered":"https:\/\/cicserver.com\/vast-data-adds-vector-search-and-deepens-google-cloud-ties-blocks-and-files\/"},"modified":"2025-05-17T07:09:56","modified_gmt":"2025-05-16T23:09:56","slug":"vast-data-adds-vector-search-and-deepens-google-cloud-ties-blocks-and-files","status":"publish","type":"post","link":"https:\/\/cicserver.com\/de\/vast-data-adds-vector-search-and-deepens-google-cloud-ties-blocks-and-files\/","title":{"rendered":"VAST Data adds vector search and deepens Google Cloud ties \u2013 Blocks and Files"},"content":{"rendered":"


\n<\/p>\n

\n <\/p>\n
\"\"<\/a><\/div>\n

<\/p>\n

VAST Data<\/a> has added vector search to its database and integrated its software more deeply into Google\u2019s cloud.<\/p>\n

The database is part of its software stack layered on top of its DASE (Disaggregated Shared Everything) storage foundation along with the Data Catalog, DataSpace, unstructured DataStore and DataEngine (InsightEngine). Generative AI large language models (LLMs) manipulate and process data indirectly, using hashed representations \u2013 vector embeddings or just vectors \u2013 of multiple dimensions of an item. An intermediate abstraction of word in text documents is a token. These are vectorized and a document item\u2019s vectors are stored in a multi-dimensional space with the LLM searching for vectors as it computes steps in its generation of a response to user requests. This is called semantic searching.<\/p>\n

A VAST Data blog<\/a> by Product Marketing Manager Colleen Quinn says: \u201cVector search is no longer just a lookup tool; it\u2019s becoming the foundation for real-time memory, context retrieval, and reasoning in AI agents.\u201d<\/p>\n

Vectors are stored by specialized vector database suppliers \u2013 think Pinecone<\/a>, Weaviate<\/a> and Zilliz<\/a> \u2013 and are also being added as a data type by existing database suppliers. Quinn says that the VAST Vector Search engine \u201cpowers real-time retrieval, transactional integrity, and cross-modal governance in one platform without creating new silos.\u201d\u00a0<\/p>\n

In the VAST world, there is a single query engine, which can handle SQL and vector and hybrid queries. It queries VAST\u2019s unstructured DataStore and the DataBase, where vectors are now a standard data type. Quinn says: \u201cVector embeddings are stored directly inside the VAST DataBase, alongside traditional metadata and full unstructured content to enable hybrid queries across modalities, without orchestration layers or external indexes.\u201d<\/p>\n

\u201cThis native integration enables agentic systems to retrieve memory, reason over metadata, and act \u2013 all without ETL pipelines, external indexes, or orchestration layers.\u201d<\/p>\n

\u201cThe system uses sorted projections, precomputed materializations, and CPU fallback paths to maintain sub-second performance \u2013 even at trillion-vector scale. And because all indexes live with the data, every compute node can access them directly, enabling real-time search across all modalities \u2013 text, images, audio, and more \u2013 without system sprawl or delay.\u201d<\/p>\n

\u201cAt query time, VAST compares the input vector to all stored vectors in parallel. This process uses compact, columnar data chunks to prune irrelevant blocks early and accelerate retrieval.\u201d<\/p>\n

\u201cFuture capabilities will expand beyond vector search, enabling new forms of hybrid reasoning, structured querying, and intelligent data pipelines.\u201d Think multi-modal pipelines and intelligent data preparation.<\/p>\n

Google Cloud<\/h3>\n

Building on its April 2024 announcement<\/a> that it had ported its Data Platform software to Google\u2019s cloud, enabling users to spin up VAST clusters there, VAST has now gone further. It says its Data Platform \u201cis fully integrated into Google Cloud \u2013 offering a unified foundation for training, retrieval-augmented generation (RAG), inference, and analytics pipelines that span across cloud, edge, and on-premises environments.\u201d<\/p>\n

Renen Hallak, VAST founder and CEO, spoke of a \u201cleap forward,\u201d stating: \u201cBy combining the elasticity and reach of Google Cloud with the intelligence and simplicity of the VAST Data Platform, we\u2019re giving developers and researchers the tools they need to move faster, build smarter, and scale without limits.\u201d<\/p>\n

The additional VAST facilities now available on GCP include:<\/p>\n