Columnar File Readers in Depth: Column Shredding Record shredding is a classic method used to transpose rows of potentially nested data into a flattened tree of buffers that can be written to
🧠Lance Research Paper,🛡️Newly Knighted Lancelot, ⚙️Practical AI Engineering 📄🌐The Lance Research Paper That's right, we finally published the Lance Research Paper on arXiv. Check out Lance: Efficient Random Access in Columnar
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
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
💼 The Future of AI-Native Development is Local: Inside Continue's LanceDB-Powered Evolution As Continue offers user-controlled IDE extensions, most of the codebase is written in Typescript, and the data is stored locally in the ~/.continue folder. The
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
The Future of Open Source Table Formats: Apache Iceberg and Lance As the scale of data continues to grow, open-source table formats have become essential for efficient data lake management. Apache Iceberg has emerged as a
☁️LanceDB Cloud Public Beta, Lance 2.1 , 🎮Game Studio Case Study ☁️ LanceDB Cloud Public Beta The wait is over! LanceDB Cloud is now in Public Beta! No more wait list; just sign-up, get an API key,
💼AnythingLLM's Competitive Edge: LanceDB for Seamless RAG and Agent Workflows AnythingLLM chose LanceDB as their vector database backbone to create a frictionless experience for developers and end-users alike. By leveraging LanceDB's serverless, setup-free
Lance File 2.1: Smaller and Simpler Almost a year ago I announced we were going to be embarking on a journey to build a new 2.0 version of our file
💼 Second Dinner's Secret Weapon: LanceDB-Powered RAG for Faster, Smarter Game Development 💡This is a case study contributed by the Second Dinner team and the LanceDB team. Second Dinner teamed up with LanceDB Cloud’s serverless architecture
RAG with GRPO Fine-Tuned Reasoning Model 💡This is a community post by Mahesh Deshwal Group Relative Policy Optimization is the series of RL techniques for LLMs to guide them to specific
Table Format for ML Workload, LanceDB x Microsoft at Iceberg Summit 🔥 New Blog: Designing a Table Format for ML Workloads Zero-copy schema evolution, indices for everything, and parallelized operations - all designed for modern ML. We
