🔥 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 explain the why & how behind the Lance table format in our latest engineering blog.
LanceDB Enterprise Product News
🔥 Multivector Search is now live:
Documents can be stored as contextualized vector lists. Fast multi-vector queries are supported at scale, powered by our XTR optimization.
🌱 LanceDB Cloud UI has a new look
Search by Project/Table in Cloud UI: allow users to quickly locate the desired project/table.
Explore Your Data at a Glance: preview sample data from any table with a single click.
Drop_index added to SDK: users can remove unused or outdated indexes from your tables.
Community Contributions
Upcoming Events
🥳 Microsoft Research Gray Systems Lab is partnering with LanceDB on this exploratory project to explore how to enhance Apache Iceberg's performance by leveraging next-generation file formats like Vortex and Lance. These formats are designed to meet the demands of modern AI/ML workloads and GPU-accelerated analytics, offering advantages such as random data access, support for wide tables, vector encodings, and optimized I/O for cloud environments. We will be presenting at the upcoming Iceberg Summit on April 8th in SF.
Open Source Releases Spotlight
- Python async API now has Table.search() method just like synchronous API.
- Safer handling of secrets in Python and Node embeddings APIs.
- Support XTR based multivector retrieval
- Support Conditional Put on S3
- Support schema evolution in Java SDK
