🧠Lance Research Paper,🛡️Newly Knighted Lancelot, ⚙️Practical AI Engineering

📄🌐The Lance Research Paper

🔍Columnar File Readers in Depth: Compression and Transparency

A new drop in the Columnar File Reader Deep Dive series. Now read on!

Columnar File Readers in Depth: Compression Transparency

Conventional wisdom states that compression and random access do not go well together. However, there are many ways you can compress data, and some of them support random access better than others. Figuring out which compression we can use, and when, and why, has been an interesting challenge. As we’ve

LanceDB BlogWeston Pace

🛡️Meet the Newly Knighted Lancelot

Back in January, we announced the inaugural Lancelot Round Table — and today, we’re thrilled to welcome three new noble members to the Roundtable! A huge thank you to each of them for their continued support and contributions to lance and lancedb.

⚔️ Hail to the Knights of the Lancelot Roundtable! 🐎

⚙️ Practical AI Engineering: New How-Tos

We’ve published two new in-depth guides on advanced techniques for optimizing AI search systems with LanceDB. These guides are intended for engineers and researchers looking to refine model performance and build more effective AI-driven applications. With the models and code public in the guides.

A Practical Guide to Training Custom Rerankers

A report on reranking, training, & fine-tuning rerankers for retrieval This report offers practical insights for improving a retriever by reranking results. We’ll tackle the important questions, like: When should you implement a reranker? Should you opt for a pre-trained solution, fine-tune an existing model, or build one from scratch? The

LanceDB BlogAyush Chaurasia

A practical guide to fine-tuning embedding models

This is a follow up to the following report that deals with improving retrievers by training and fine-tuning reranker models A Practical Guide to Training Custom RerankersA report on reranking, training, & fine-tuning rerankers for retrieval This report offers practical insights for improving a retriever by reranking results. We’ll tackle

LanceDB BlogAyush Chaurasia

Real-World Applications

Explore how leading AI startups are applying LanceDB to advance development and deployment, from our latest case studies:

💼 The Future of AI-Native Development is Local: Inside Continue's LanceDB-Powered Evolution

Focused on reshaping the future of AI-native development, Continue chose LanceDB to power its local-first, privacy-centric coding environments. LanceDB enabled instant, high-quality semantic search without sacrificing speed, developer control, or security — key pillars for building next-generation AI development tools.

“Thanks for all the work that you do! When I found LanceDB, it was exactly what we needed, and has played its role perfectly since then:) ”
– Nate Sesti, Cofounder & CTO @Continue

💼AnythingLLM's Competitive Edge: LanceDB for Seamless RAG and Agent Workflows

To build a competitive RAG and agent orchestration platform, AnythingLLM integrated LanceDB as its retrieval engine — achieving faster, more scalable knowledge retrieval across local and cloud sources. LanceDB’s low-latency performance and flexibility helped AnythingLLM deliver a seamless user experience across complex workflows.

With support for Windows ARM, LanceDB is the only VectorDB with seamless experience across platforms and able to run fully on CoPilot AI PCs - something no other vector databases can do at this time. This only affirmed our choice that LanceDB is the best VectorDB provider for on-device AI with AnythingLLM."
- Founder CEO, Timothy Carambat @ AnythingLLM, Mintplex Labs

LanceDB Enterprise Product News

Community Contributions

Events Recap

Open Source Releases Spotlight