☁️ 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, and start building AI with LanceDB Cloud - Serverless Retrieval for Multimodal AI!
Good Reads
👀Lance 2.1 Preview
If you think Lance Format 2.0 was magic, wait till you see Lance 2.1(beta). We are achieving faster full scans than Parquet and gained support for storing large binary data like audio, image, and video.
🎮Second Dinner’s Secret Weapon: LanceDB-Powered RAG for Faster, Smarter Game Development
What if you could go from months of development to hours? That’s exactly what award winning game studio Second Dinner achieved with LanceDB Cloud:
- ✅ Prototyping new features in hours (instead of months)
- ✅ 100x faster QA with a simple API call
- ✅ AI-driven workflows 3 to 5x more cost-effective than alternatives
“LanceDB isn’t just a tool—it’s our cheat code.” – Xiaoyang Yang, VP of AI, Data, Security at Second Dinner
LanceDB Enterprise Product News
🔥 New LanceDB Enterprise & LanceDB Cloud Features
- Enhanced Full-Text Search (FTS): Fuzzy Search & Boosting Now Available
- New SDK APIs:
explain_plan,analyze_plan,restore: - Scalar Indexing for UUID of FixedSizeBinary type
- Support S3-compatible object store
🧮Updated LanceDB Cloud Pricing Calculator
Our updated pricing ensures a fair, scalable, and value-aligned cost structure:
- Storage: Now includes attributes in data storage size.
- Writes: $6 per million 1536D vectors written.
- Queries: Charged based on the data read and returned per query:
- Read size: $0.25/TB
- Return size: $0.1/GB
- Minimum read size per query: 64MB
Community Contributions
Upcoming Events
On April 17th, LanceDB is co-hosting an in-person meetup with Anyscale, learn how to build scalable, performant LLM APIs using Ray + LanceDB
Open Source Releases Spotlight
- TypeScript SDK:
- Binary vector support: LanceDB’s TypeScript SDK now natively supports binary vector indexing and querying with production-grade efficiency.
- Accepts Arrow data type in
alterColumns.
- Python users can utilize the PyArrow schema to add a new column to the table schema.
- Allow streaming larger-than-memory writes when adding data to a table.
