LanceDB
@lancedb
The multimodal lakehouse for AI, accelerating large-scale data curation and feature engineering so teams can build better models faster.
66 Following 4.7K Followers
We benchmarked Jev against 19 reranker configs across 5 datasets.
A few results:
• HotpotQA Hit@1 improved 63.52% → 72.87% vs. no reranking
• A better relevance prompt pushed it to 85.24%
• 92.59% Hit@10 on GooAQ
@ifoundanifty + @loldedxd dig in:
Show more
ICYMI: We spotlighted some incredible startups in Times Square. ✨
Now, get to know the people behind them.
Hear from @lancedb’s Christie Schaefer and @FerrumHealth’s Richard Sörberg and Austin Deer about their companies, what they’re building and the problems they’re working to solve.
Learn more about Microsoft for Startups here:
#MicrosoftForStartups# #Startups# #AI# #Tech#
Show more
Feature of the Week: Batch Vector Search Now Shares IVF Partition Scans
In a batch, many queries want the same IVF partitions, but Lance was re-reading them per query. Now it loads each partition once and scores every query that wants it.
Same answers, ~2.5x faster 🚀
@lancedb
Show more
LanceDB is in Times Square. 🗽
@msft4startups is featuring us as part of its invite-only Pegasus Program.
A big milestone as we keep building the new foundation for AI data.
#MicrosoftForStartups# #BuiltWithMfS#
Show more
stable-worldmodel got into neurips 2026!
it's basically everything we keep rebuilding for world model research (data loading, baselines, planning, evals) in one place so nobody has to do it again
Show more
We teamed up with 🤗 @huggingface on a new guide to using LanceDB as the data backend for LeRobot.
Train directly from object storage, use vector + full-text search for curation and mining, and avoid stitching together separate systems as robotics datasets scale.
Show more
LeRobot now natively supports @lancedb datasets, with fast training and global shuffling directly from HF Storage Buckets - no need to download the dataset first 🚀
From vector & full-text search to curation & mining, discover what you can unlock with LanceDB + LeRobot 👇
Show more
Vector search that works at 10M vectors shouldn’t need a redesign at 10B.
LanceDB hit 18.05ms p50 / 21.61ms p99 across 10B vectors, while scaling indexing and letting each query tune precision.
New deep dive from @Yah01_
Show more
A great blog written by @loldedxd & @ariG23498 🤗👏
funes, by @huggingface, turns past agent sessions into memory your agents can actually use.
It indexes Claude Code, Codex, pi, and Hermes traces into one local Lance dataset, then gives the agent 'recall' and 'get' tools.
The next time a task depends on old reasoning, the agent can pull the original passage back. No LLM summarizing your traces at ingest.
Show more
We’re starting a new series called Feature of the Week 🎉
This week’s feature by @Yah01_: Index prewarm now reads in parallel bytes windows. Loading a billion-vector index into memory used to take 95 minutes, now it takes 3.
Show more
Lance is now natively supported in 🤗 @huggingface LeRobot.
Ingest through train directly from S3, GCS, or HF Storage Buckets with the same LeRobotDataset API and true global shuffle. No need to download the full robotics dataset first.
Big thanks to @Caro_Nahkriin and @lhoestq for working with us to get this merged!
Show more
Weston Pace (Software Engineer @ LanceDB, Apache Arrow and Substrait PMC) keynotes CDMS 2026 on how composable data systems hold up when the users are agents and, increasingly, so are the contributors.
Sept 4, Boston, co-located with VLDB 2026
Show more
