Open source, self-hosted - verified
LanceDB OSS
LanceDB OSS is listed under open source, self-hosted (deployment type: open source self-host). Open source; no price. Stated: hybrid and sparse search and built-in reranking. Read from the vendor's own pages on October 18, 2026.
Read from docs.lancedb.com, raw.githubusercontent.com. Docs - License - Compare every vector database
Status
- Availability label
- Not stated
No release-status label is stated on the pages checked.
How LanceDB OSS charges
Every price LanceDB OSS states, in its own unit, with the quote and where it comes from. Nothing is converted.
Open source; no price.
Free tier and limits
- Free tier
- Not stated
Open-source library; no hosted free tier applies.
- Limits
- Not stated
Not stated on the pages checked.
Search and indexing
- Max dimensions
- Not stated
Not stated on the indexing or vector search pages checked.
- Distance metrics
l2, cosine, dot, hamming
“Euclidean or l2 is the default, and used for general-purpose similarity, cosine for unnormalized embeddings, dot for normalized embeddings (best performance), or hamming for binary vectors.”
docs.lancedb.com - Index types
IVF (with PQ, SQ or RabitQ quantization), IVF_HNSW, FTS (BM25), BTree, Bitmap, LabelList, FM
“IVF (Vector) Large-scale vector search with configurable accuracy/speed trade-offs.”
docs.lancedb.com “IVF_HNSW (Vector) Large-scale vector search requiring both high recall and efficient partitioning.”
docs.lancedb.com - Hybrid and sparse search
Yes: BM25 full-text index combinable with vector search
“FTS (Full-text search) String columns (e.g., title, description, content) requiring keyword-based search with BM25 ranking.”
docs.lancedb.com - Metadata filtering
Yes (scalar indexes for filters)
“Scalar Index: Accelerates filtering and sorting of structured numeric or categorical data”
docs.lancedb.com - Multi-tenancy
- Not stated
Not described on the pages checked.
Built-in embedding and reranking
- Built-in embedding
- Not stated
The docs index (llms.txt) lists "Managing Embeddings", but none of the pages checked describes the embedding feature itself, so no value is given.
- Built-in reranking
Rerankers documented (RRF default for hybrid search, cross-encoder and custom)
“Reranking Search Results: Use a reranker to improve search relevance.”
docs.lancedb.com “Reciprocal Rank Fusion Reranker: Learn about LanceDB's default Reciprocal Rank Fusion (RRF) reranker for hybrid search.”
docs.lancedb.com
Deployment, license and SDKs
- Regions and clouds
- Not stated
Embedded library; regions do not apply.
- BYOC and self-host
Open-source embedded library
“The fastest way to get started is the open-source embedded library, with client SDKs in Python, TypeScript and Rust.”
docs.lancedb.com - License
Apache-2.0
“Apache License Version 2.0, January 2004”
raw.githubusercontent.com - SDKs
Python, TypeScript, Rust
“The fastest way to get started is the open-source embedded library, with client SDKs in Python, TypeScript and Rust.”
docs.lancedb.com
Vendor-stated claims
Performance, scale and SLA figures as LanceDB OSS states them. Not measured.
No performance, scale or SLA figure is recorded from the pages checked.
Research notes
Built on the Lance columnar format (Apache-2.0).
FAQ
How much does LanceDB OSS cost?
Open source; no price.
What is the maximum vector dimension in LanceDB OSS?
Not stated. Not stated on the indexing or vector search pages checked.
Does LanceDB OSS support hybrid search?
Yes: BM25 full-text index combinable with vector search, per the vendor: "FTS (Full-text search) String columns (e.g., title, description, content) requiring keyword-based search with BM25 ranking."
Does LanceDB OSS have built-in embedding or reranking?
Embedding: not stated. The docs index (llms.txt) lists "Managing Embeddings", but none of the pages checked describes the embedding feature itself, so no value is given. Reranking: Rerankers documented (RRF default for hybrid search, cross-encoder and custom).
Sources
- Source: docs.lancedb.com
- Source: docs.lancedb.com/search/vector-search
- Source: docs.lancedb.com/indexing
- Source: docs.lancedb.com/llms.txt
- Source: raw.githubusercontent.com/lancedb/lancedb/main/LICENSE
Last verified from each vendor's own docs, pricing pages, READMEs and license files; every quote was string-matched against the page that day. This is a dated snapshot, not a benchmark: prices are shown in each product's own unit and change without notice, so check the linked source before you commit.
Newsletter
Know when a vector database changes its pricing
One email per week. New model releases, retrieval tooling and pricing changes and what they mean for what you build.