Original press release published here.

SAN MATEO, Calif. – January 30, 2024 - Rockset, the leading search and analytics database built for the cloud, today announced native support for hybrid search. Hybrid search involves incorporating vector search and text search as well as metadata filtering, all in a single query. With this release, Rockset paves the way for the next generation of search and AI applications. Users can now leverage hybrid search to combine vector, text, geospatial, and structured search to retrieve and rank the most relevant results.

The rapid development of AI models, including Meta’s Llama-3, OpenAI’s GPT-4, Google’s Gemini, and Databricks’ DBRX, is shepherding in a new era of intelligence. Forward-thinking enterprises are investing in powerful retrieval systems built for AI applications. With new hybrid search capabilities, Rockset accelerates the pace of building and iterating on AI applications, establishing a new standard for vector databases that rapidly adapts indexing, models and ranking.

“All search will soon be hybrid search,” said Venkat Venkataramani, co-founder and CEO of Rockset. “Similarity search has limitations around domain awareness and requires combining vector search results along with text search, geospatial search, and structured search to provide the necessary context. Support for hybrid search requires best-in-class indexing technology designed for fast retrieval. We continuously innovate on our Converged Indexing technology, and we’re thrilled to introduce text search and ranking algorithms for hybrid search.”

Engineers building search and AI applications constantly need to incorporate new signals, models, indexes, and ranking algorithms to improve relevance. Rockset enables users to reindex vectors without impacting live search applications. Users have the flexibility to index any type of data and apply ranking and scoring using SQL. This flexibility enables customers to build and iterate on search and AI applications faster to drive the most relevant experiences. New feature benefits include:

● Ranking algorithms including BM25 and reciprocal rank fusion (RRF) to build hybrid search applications

● Multi-tenant design for retrieval augmented generation (RAG) applications

● New search design that uses compressed bitmaps and covering indexes for faster performance at scale

If you like this article consider subscribing to our bi-monthly newsletter to get information about our portfolio, solutions, and insights delivered to your inbox.