Hybrid Search

Get the best of both worlds with vector + full-text search

single-store-supports-hybrid-search-enabling-you-to-easily-build-rich-ai-and-analytical-applicationsSingleStore supports hybrid search, enabling you to easily build rich AI and analytical applications.

Vector search

Search for semantically similar vector embeddings and power your generative AI applications. Understand users’ intent behind queries by analyzing semantics, context and relationships between words or concepts.

Full-text search
Retrieve documents or web pages that contain the exact keywords specified in the query. Treat each keyword independently, without considering the relationships between them or the overall context.

vector-search-with-single-storeVector search with SingleStore

Vector search typically involves a three-way tradeoff. With SingleStore, you get to make tradeoffs on your own terms.

Exact-nearest neighbor vector search

  • k-Nearest Neighbor (kNN) algorithms using dot product and Euclidean distance
  • Optimize for recall (accuracy)

Approximate Nearest Neighbor (ANN) vector search

  • Optimize for scale and costs with tunable accuracy
  • Choose IVF-PQ for low index build time and small index size
  • Choose HNSW for excellent recall and performance at high dimensionality (coming soon)
Magnifying Glass Icon

full-text-search-operations-on-large-datasetsFull-text search operations on large datasets

Inverted indexes

An inverted index is a data structure used to store a mapping from content, like words or numbers, to its locations in a database table. This is similar to the index found at the back of a book and is highly efficient for text search operations.

String matching and filtering

The full-text search capability allows for advanced string matching and filtering. This includes the ability to search for phrases, perform wildcard searches and handle different variations of words and characters.


SingleStore full-text search is based on the active, open-source Lucene and benefits from its latest advancements, performance improvements, expanded API support, etc.

Database Icon

fast-enterprise-grade-sql-databaseFast, enterprise-grade SQL database

Unparalleled speed

Fast ingest for vector embeddings and new vectors makes data immediately searchable.

Familiar, powerful SQL interface

With support for filters, aggregates + joins, there’s no need to learn new query languages.

Scalability, performance and reliability

Get the reliability of an enterprise database designed for high performance and scalability. Even as data volumes grow, SingleStore efficiently handles complex text and vector search queries — without significant degradation in performance.

vector-search-with-single-storeVector search with SingleStore


Sentiment analysis on employee survey responses

Siemens is driving sentiment analysis using vector capabilities within SingleStore to analyze and gain deeper insights into the responses from company-wide HR surveys across 200,000 employees worldwide.


Real-time image search and object recognition for search and analytics

nyris.io, a leading AI-based visual search engine for retailers is powering its platform (including catalog search, visual search and analytics) using dot_product vector similarity capabilities in SingleStore.


Catalog, customer 360 and personalization matching job seekers with roles

DirectlyApply, a job discovery platform and vertical search engine that connects job seekers with employers, uses SingleStore to store vector embeddings generated from job titles and run vector similarity search (using dot_product) to match embeddings with job openings and standard ISCO job titles.


AI-driven video monitoring and surveillance for safety and security

Lumana, a SaaS visual intelligence platform for real-time video monitoring and surveillance uses SingleStore's vector functionality to perform image and video matching to monitor occupational safety, surveillance footage and more.