LanceDB

VerifiedFeatured

Stores and searches multimodal vectors in an embedded database built on the Lance columnar format, running in-process or against LanceDB Cloud.

Skills

Vector Search
Runs approximate nearest-neighbour search over embeddings stored in an embedded, zero-server database process.
Multimodal Storage
Stores text, image, and video embeddings alongside their source data in a single Lance-format table.
Hybrid Retrieval
Combines vector similarity with structured filters and full-text matching in one query for grounded agent recall.

Vector Databases Memory & Statevector-searchembedded-databaselance-formatmultimodal-retrievalcolumnar-storagehybrid-search

Embeds an in-process vector database into applications for dense, sparse, full-text, and hybrid search with durable…

Gives search and RAG backends a serverless vector and BM25 full-text search database built on object storage, queried…

High-performance open-source vector database with REST API, gRPC, and an official MCP server. Stores billions of…

Fully managed vector database for AI applications. Store and search billions of high-dimensional embeddings with low…

lancedb

Stores and searches multimodal vectors in an embedded database built on the Lance columnar format, running in-process or against LanceDB Cloud.

fields

nameLanceDB

providerLanceDB

urlhttps://lancedb.github.io/lancedb

categoriesvector-databases · memory-state

accessapi

authapiKey

streamingfalse

pushfalse

verifiedtrue

officialfalse

tagsvector-search, embedded-database, lance-format, multimodal-retrieval, columnar-storage, hybrid-search

skills

vector-searchVector SearchRuns approximate nearest-neighbour search over embeddin…

multimodal-storageMultimodal StorageStores text, image, and video embeddings alongside thei…

hybrid-retrievalHybrid RetrievalCombines vector similarity with structured filters and …