LanceDB
Summary
What it is
A vector database that stores data in the Lance columnar format directly on object storage. Designed for serverless vector search without a separate index server.
Where it fits
LanceDB is the S3-native option for vector search. Unlike Milvus or Pinecone, LanceDB stores both raw data and vector indexes as files on S3 — aligning with the separation of storage and compute principle and eliminating a separate infrastructure layer.
Misconceptions / Traps
- Serverless on S3 means higher query latency than in-memory vector databases. LanceDB trades latency for simplicity and cost.
- LanceDB uses the Lance format, not Parquet. Data must be converted or ingested into Lance format for vector search.
Key Connections
indexesMinIO, AWS S3 — builds vector indexes over S3-stored dataimplementsHybrid S3 + Vector Index — the canonical implementation of this patternscoped_toVector Indexing on Object Storage, S3
Definition
What it is
A vector database that stores data in the Lance columnar format directly on object storage. Designed for serverless vector search without requiring a separate vector index server.
Why it exists
Traditional vector databases require dedicated infrastructure. LanceDB stores both raw data and vector indexes as files on S3, aligning with the separation of storage and compute principle and avoiding a separate operational layer for vector search.
Primary use cases
Semantic search over S3-stored documents, retrieval-augmented generation (RAG) with S3-backed corpora, serverless vector search.
Relationships
Outbound Relationships
scoped_toimplementsResources
Official LanceDB documentation covering this serverless vector database built on the Lance columnar format, designed for S3-native storage.
Primary LanceDB repository including the Rust/Python/JS SDKs for embedded vector search with S3 and object store backends.
The Lance columnar format repository — the underlying storage format designed for efficient reads from S3 and cloud object stores.
LanceDB's storage configuration guide documents S3 bucket setup, credential management, and object store backend configuration.