(alphaspirit.it_/Shutterstock)
Rockset Inc., a real-time analytical database platform, announced native support for hybrid search that combines text search, vector search, and metadata filtering into a single query.
As artificial intelligence technology evolves, systems that support data search and retrieval must also ensure that AI models have access to the data they need to process the information. There is already a proliferation of applications that require access to both keyword and vector searches, as well as robust indexing and ranking mechanisms.
With the introduction of new capabilities, Rockset is pioneering the next generation of search and AI applications. Users can now leverage Rockset hybrid search, which combines text, vectors, geospatial, and structured data, to get the most relevant results.
The rapid development of AI models such as OpenAI's GPT-4, Meta's Llama-3, Google's Gemini, and Databricks' DBRX is ushering in a new era of enhanced AI, and its success depends on powerful data retrieval. and acquisition systems are essential.
Although AI models are improving at an incredible pace, they lack the ability to retain knowledge or have inherent memory capabilities. To overcome these limitations, developers integrate knowledge from multiple sources into AI models. However, multiple disparate systems mean the risk of quality issues, lack of responsiveness, and poor performance.
This is where Rockset's hybrid search comes into play. This simplifies the process of integrating different types of data searches for AI applications. Users can perform keyword searches, perform metadata filtering, or invoke vector searches all at once through a single query.
AI model developers often need to incorporate ranking algorithms, indexes, and signals to improve relevance. Rockset's Hybrid Search allows users to reindex vectors without disrupting the live search application.
Additionally, Rockset's cloud-native database eliminates the need to download, install, and configure software packages. This makes it easy to manage your installation, access your data from anywhere, and easily scale to meet demand.
The new release includes a multi-tenant design for RAG applications, new ranking algorithms such as BM25 and Reciprocal Rank Fusion (RRF), and a new search design that uses compressed bitmaps and cover indexes for massive performance improvements. Masu.
“Soon all search will be hybrid search,” said Venkat Venkataramani, co-founder and CEO of Rockset. “Similarity search has domain-aware limitations and requires a combination of vector search results with text, geospatial, and structured searches to provide the necessary context. Support for hybrid search requires fast We continue to innovate our converged indexing technology and are excited to introduce text search and ranking algorithms for hybrid search. .”
Venkat is Datanami People to watch in 2022founded Rockset in 2016 to meet the growing need for real-time analytics solutions that can process a variety of data. Before starting Rockset, Venkat worked at his Facebook for eight years, building and expanding online data systems.
Last year, Rockset raised $44 million to power its search, analytics, and AI applications. Rockset's total capital raised reached $105 million. As more organizations seek to take advantage of the efficiency and performance of AI hybrid search, expect Venkat and his team at Rockset to be at the forefront of this transformation.
