⚔️ Lancelot Round Table, 100x Reduction in S3 Requests, VoyageAI❤️LanceDB

To inaugurate the new year, we proudly unveiled the first ⚔️Lancelot Round Table in January, celebrating the founding knights who have been instrumental in shaping the future of AI infrastructure since LanceDB's inception. These Lancelot pioneers are driving innovation by implementing and collaborating with lance and lancedb across their organizations, democratizing access to advanced AI tools, empowering innovators worldwide, and expanding the frontiers of data management.

The Lancelot Chronicles: Your Quest in the Realm of Open Source

Answering the Clarion Call In the vast open source realm, where bits and bytes flow like rivers of possibility, a new saga is unfolding. This is not just any tale – it’s the story of lance and lancedb, and you, brave knight, are the protagonist we’ve been waiting for. Open source

LanceDB BlogJasmine Wang

LanceDB Enterprise Product News

🔥 Enterprise customers upgrading to the new reactive indexer in LanceDB Enterprise reported 100x reduction in S3 requests. We engineered LanceDB Enterprise for high-throughput data ingestion and indexing. The system ensures data persistence on durable object storage before confirming any write request.

🌱 New LanceDB Enterprise Changelog - now you can keep a close eye on our enterprise updates. We’ve already made some exciting updates since the New Year! 

• Support hamming distance and binary vector
• GPU indexing support
• Multi-vector index support
• Optimized Build for AWS Graviton 4 and Google Cloud Axion Processors
• Support index over float16 vectors

Partnership Spotlight

🥳 Vector Search with LanceDB using Voyage AI's Text and Multimodal Embeddings.

• You can now directly define a Voyage embedding function and data model, all within LanceDB. Together, this creates a powerful ecosystem for semantic search, enabling developers to build intelligent, context-aware applications with minimal computational overhead.
• Using this new integration makes it incredibly easy to build, experiment, and scale your AI applications to billions of vectors and beyond.

Community Contributions

Open Source Updates

• Upsert with merge insert allows omitting nullable columns.
• Vector search can be applied to binary vectors using hamming distance.
• Can limit vector search results based on maximum distance (distance range).
• Typescript LanceDB supports hybrid search.
• Python LanceDB improved parity between async and sync Table API.