| A storage format choice can follow you into every training run.
GM / Cruise's Xin Hu shares its feature store and its … |
@lancedb |
Company |
Original |
2026-10-26 |
244 |
4 |
0 |
2 |
0 |
0 |
| Changed one feature. Reran the whole pipeline. Sound familiar?
@GM's Gokcen Iskender explains how feature-level cachin… |
@lancedb |
Company |
Original |
2026-10-23 |
317 |
1 |
0 |
1 |
0 |
0 |
| Before blaming S3 for slow writes, benchmark your WAL.
We used LAION to benchmark storing multimodal data with a WAL. … |
@lancedb |
Company |
Original |
2026-10-21 |
2,690 |
25 |
2 |
1 |
0 |
28 |
| Congrats @duckdb on 2.0.0 release 👏🦆 |
@lancedb |
Company |
Quote |
2026-10-21 |
543 |
6 |
0 |
0 |
0 |
1 |
| The plot thickens. The table widens.
@Tubi's John Trenkle serves up Cornucopia at #Reverie2026. One row per title, eve… |
@lancedb |
Company |
Original |
2026-10-21 |
213 |
1 |
0 |
1 |
0 |
0 |
| Road logs. Simulation. Training. Evals. The arrows are doing a lot of work.
@XPENG_Global, @AppliedInt, and @LanceDB u… |
@lancedb |
Company |
Original |
2026-10-20 |
304 |
2 |
1 |
0 |
0 |
0 |
| Good morning from Long Horizon! Swing by our booth, take a photo with our shield, and chat about accelerating your trai… |
@lancedb |
Company |
Original |
2026-10-20 |
501 |
9 |
1 |
1 |
1 |
0 |
| Find the rare driving scenarios. Put them to work in training.
@XPENG_Global Bo Tian brings the data infrastructure be… |
@lancedb |
Company |
Original |
2026-10-19 |
3,324 |
3 |
2 |
1 |
2 |
0 |
| Customer Journey Analytics and Brand Concierge pushed @Adobe’s lakehouse into new territory.
Miao Wang shares the move… |
@lancedb |
Company |
Original |
2026-10-16 |
241 |
2 |
0 |
1 |
0 |
0 |
| Optimizers that scale. Models that teach each other. A decade of lessons learned the hard way.
Rohan Anil @_arohan_, G… |
@lancedb |
Company |
Quote |
2026-10-14 |
445 |
6 |
0 |
1 |
0 |
0 |
| A new ranking idea has to work across an index of hundreds of billions of pages.
Go inside @ExaAILabs Skeleton with Ja… |
@lancedb |
Company |
Original |
2026-10-14 |
599 |
5 |
0 |
1 |
1 |
0 |
| We welcome @nebiusai as the marquee sponsor of #Reverie2026!
Nebius, the AI cloud company, helps teams build and scale… |
@lancedb |
Company |
Original |
2026-10-13 |
271 |
3 |
0 |
1 |
0 |
0 |
| RT @lancedb: Keeping training data on S3 often means maintaining another storage layer just to feed the GPUs.
Join Adh… |
@lancedb |
Company |
Repost |
2026-10-12 |
-- |
0 |
1 |
0 |
0 |
0 |
| Keeping training data on S3 often means maintaining another storage layer just to feed the GPUs.
Join Adharvan Jakkula… |
@lancedb |
Company |
Original |
2026-10-12 |
347 |
6 |
1 |
1 |
0 |
1 |
| Wrap up Long Horizon with LanceDB, @CoreWeave and of course @Encord_Team! We’re taking over the St. Francis Yacht Club … |
@lancedb |
Company |
Original |
2026-10-09 |
258 |
0 |
0 |
1 |
0 |
0 |
| Our good friend Bryan Bischof @BEBischof is our MC for #Reverie2026! 👏🤩
Head of AI at @Theoryvc. One of our favorite p… |
@lancedb |
Company |
Quote |
2026-10-09 |
319 |
3 |
0 |
0 |
0 |
0 |
| 𝗦𝗲𝗽𝘁𝗲𝗺𝗯𝗲𝗿 𝗥𝗲𝗰𝗮𝗽! 🔄 𝗪𝗲 𝗵𝗮𝘃𝗲 𝘀𝗼 𝗺𝘂𝗰𝗵 𝘁𝗼 𝗰𝗼𝘃𝗲𝗿:
🗽 LanceDB is in Times Square, thanks to @msft4startups
🌟 @LeRobotHF now … |
@lancedb |
Company |
Original |
2026-10-08 |
211 |
0 |
0 |
1 |
0 |
0 |
| Your robot nailed the demo. Which failures belong in its next training set?
@NVIDIA’s @mli0603, @LumaLabsAI’s Yichen W… |
@lancedb |
Company |
Original |
2026-10-08 |
195 |
0 |
0 |
0 |
0 |
0 |
| We're so excited to have @arcee_ai's Gerred Dillon @sloppenheimer as our closing Keynote Speaker!
Join him at #Reverie… |
@lancedb |
Company |
Original |
2026-10-07 |
1,259 |
14 |
4 |
1 |
0 |
1 |
| Which training examples are worth the compute?
@RunwayML’s Ethan Rosenthal takes us inside multimodal curation with em… |
@lancedb |
Company |
Original |
2026-10-06 |
426 |
5 |
0 |
2 |
0 |
2 |
| Hear from @AppliedInt’s @_xushiyan speak at #Reverie2026 🎉
Hear how the team goes from driving logs to RL training at … |
@lancedb |
Company |
Original |
2026-10-05 |
395 |
8 |
2 |
1 |
0 |
1 |
| . @DynaRobotics cut training startup from roughly 48 hours to under a minute.
Hear ML Infrastructure Lead @ZhipengYan7… |
@lancedb |
Company |
Original |
2026-10-02 |
480 |
6 |
0 |
1 |
0 |
0 |
| Yichen Wang, Data Infrastructure Lead at @LumaLabsAI, will be speaking at #Reverie2026!
How does raw data become a tra… |
@lancedb |
Company |
Original |
2026-10-01 |
637 |
7 |
0 |
2 |
1 |
0 |
| @MicrosoftAI’s Suqiang (Jack) Song is speaking at #Reverie2026.
Hear how MAI is building the frontier AI data flywheel… |
@lancedb |
Company |
Original |
2026-09-30 |
287 |
4 |
1 |
1 |
0 |
0 |
| We benchmarked Jev against 19 reranker configs across 5 datasets.
A few results:
• HotpotQA Hit@1 improved 63.52% → 72… |
@lancedb |
Company |
Original |
2026-09-29 |
920 |
19 |
4 |
1 |
0 |
7 |
| RT @msft4startups: ICYMI: We spotlighted some incredible startups in Times Square. ✨
Now, get to know the people behin… |
@lancedb |
Company |
Repost |
2026-09-28 |
27 |
0 |
4 |
0 |
0 |
0 |
| RT @ChanChan_Mao: Feature of the Week: Batch Vector Search Now Shares IVF Partition Scans
In a batch, many queries wan… |
@lancedb |
Company |
Repost |
2026-09-28 |
23 |
0 |
2 |
0 |
0 |
0 |
| . @nvidia’s @mli0603 is speaking at Reverie 2026!
Cosmos has grown to roughly a million hours of video. Hear how NVIDI… |
@lancedb |
Company |
Original |
2026-09-28 |
361 |
3 |
0 |
1 |
1 |
1 |
| LanceDB is in Times Square. 🗽
@msft4startups is featuring us as part of its invite-only Pegasus Program.
A big milest… |
@lancedb |
Company |
Original |
2026-09-25 |
4,605 |
29 |
6 |
3 |
2 |
1 |
| RT @loldedxd: stable-worldmodel got into neurips 2026!
it's basically everything we keep rebuilding for world model r… |
@lancedb |
Company |
Repost |
2026-09-25 |
27 |
0 |
32 |
0 |
0 |
0 |
| 1/9 The Reverie Summit 2026 agenda is live!
What does it take to build world models, train robots, and search hundreds… |
@lancedb |
Company |
Original |
2026-09-25 |
1,383 |
18 |
5 |
2 |
2 |
0 |
| We teamed up with 🤗 @huggingface on a new guide to using LanceDB as the data backend for LeRobot.
Train directly from … |
@lancedb |
Company |
Quote |
2026-09-24 |
1,065 |
16 |
2 |
0 |
0 |
3 |
| Vector search that works at 10M vectors shouldn’t need a redesign at 10B.
LanceDB hit 18.05ms p50 / 21.61ms p99 across… |
@lancedb |
Company |
Original |
2026-09-22 |
1,116 |
18 |
3 |
1 |
1 |
14 |
| A great blog written by @loldedxd & @ariG23498 🤗👏 https://t.co/zgLkWrvB8R
funes, by @huggingface, turns past agent ses… |
@lancedb |
Company |
Original |
2026-09-21 |
13,181 |
52 |
5 |
10 |
0 |
36 |
| RT @ariG23498: The best kind of work almost always comes from collaborations!
This time @loldedxd helped me figure out… |
@lancedb |
Company |
Repost |
2026-09-17 |
35 |
0 |
11 |
0 |
0 |
0 |
| We’re starting a new series called Feature of the Week 🎉
This week’s feature by @Yah01_: Index prewarm now reads in pa… |
@lancedb |
Company |
Original |
2026-09-17 |
5,118 |
31 |
13 |
1 |
4 |
8 |
| Raw text → curated data → 2.43B tokens → trained GPT-2 in 25 minutes on 8 H100s.
@loldedxd built the entire pretrainin… |
@lancedb |
Company |
Original |
2026-09-16 |
1,010 |
18 |
4 |
0 |
1 |
11 |
| Your coding agent forgets everything the moment a session ends. Ask it what it decided last week and why, and it has no… |
@lancedb |
Company |
Original |
2026-09-15 |
921 |
11 |
0 |
2 |
1 |
8 |
| Lance is now natively supported in 🤗 @huggingface LeRobot.
Ingest through train directly from S3, GCS, or HF Storage B… |
@lancedb |
Company |
Original |
2026-09-14 |
1,487 |
18 |
6 |
0 |
2 |
1 |
| Physical AI data mining is becoming one of the most important infrastructure problems in robotics and autonomous system… |
@lancedb |
Company |
Original |
2026-09-10 |
384 |
7 |
0 |
0 |
0 |
1 |
| 🌟 Reverie, LanceDB's summit for AI builders, lands Nov 5 in San Francisco with speakers from NVIDIA, Runway, and Luma.
… |
@lancedb |
Company |
Original |
2026-09-09 |
444 |
4 |
1 |
1 |
0 |
1 |
| Early Bird pricing ends tomorrow!
Reverie, the summit for AI builders hosted by LanceDB! On November 5 in San Francisc… |
@lancedb |
Company |
Original |
2026-09-03 |
362 |
2 |
2 |
0 |
1 |
0 |
| We’re looking for the builders behind the world’s most ambitious AI systems to speak at Reverie, on November 5 in San F… |
@lancedb |
Company |
Original |
2026-09-01 |
323 |
2 |
0 |
0 |
0 |
0 |
| Weston Pace (Software Engineer @ LanceDB, Apache Arrow and Substrait PMC) keynotes CDMS 2026 on how composable data sys… |
@lancedb |
Company |
Original |
2026-08-31 |
2,162 |
8 |
2 |
1 |
1 |
1 |
| Last day of #RaySummit2026! If you're working on foundation model training, multimodal data curation, or physical AI, w… |
@lancedb |
Company |
Original |
2026-08-26 |
307 |
2 |
0 |
0 |
0 |
0 |
| LanceDB is at #RaySummit2026 this week!
Distributed compute is the easy part. Keeping embeddings, raw content, and met… |
@lancedb |
Company |
Original |
2026-08-24 |
578 |
7 |
2 |
3 |
0 |
1 |
| That's a wrap on #Actuate26 by @Foxglove! 2 days of talking to robotics engineers, ML researchers, and infra leads abou… |
@lancedb |
Company |
Original |
2026-08-20 |
474 |
4 |
1 |
0 |
1 |
1 |
| Live from #Actuate26 by @Foxglove! Stop by LanceDB Booth #15 to chat with our team about how to turn your raw fleet dat… |
@lancedb |
Company |
Original |
2026-08-18 |
372 |
4 |
0 |
0 |
0 |
0 |
| Data loading for ML is simple in theory: keep the GPU fed.
In practice? I/O, transforms, parallelism, shuffling, cachi… |
@lancedb |
Company |
Original |
2026-08-17 |
4,478 |
27 |
7 |
0 |
1 |
28 |
| See you at #Actuate26 next week! 👋
Stop by Booth #15 to chat with the LanceDB team
🎤 Tues 8/18, 1PM: Join our CTO & C… |
@lancedb |
Company |
Original |
2026-08-14 |
438 |
2 |
1 |
0 |
0 |
0 |
| LanceDB ships as the first-party backend in @nvidia NeMo Retriever - a scalable open library for extracting content and… |
@lancedb |
Company |
Original |
2026-08-13 |
1,075 |
15 |
6 |
0 |
0 |
6 |
| Sim-to-real doesn't get easier with more compute.
At #Actuate26, we're hosting Basecamp with @nebiusai and @antiochrob… |
@lancedb |
Company |
Original |
2026-08-12 |
463 |
4 |
0 |
0 |
0 |
0 |
| Every generative model is a kind of dream, rendered from what it has seen.
Introducing Reverie, LanceDB’s summit on th… |
@lancedb |
Company |
Original |
2026-08-11 |
3,312 |
15 |
4 |
1 |
3 |
2 |
| The round table just got bigger, welcome aboard 🎉
New Lancers have joined the guild, from engineering to marketing to … |
@lancedb |
Company |
Original |
2026-08-10 |
476 |
3 |
0 |
1 |
0 |
1 |
| Great Pyrenees or snowdrift?
Your multimodal pipeline should know the difference without becoming an orchestration nig… |
@lancedb |
Company |
Original |
2026-08-06 |
372 |
4 |
0 |
0 |
0 |
0 |
| Describe a clip, show a similar image, or feed it an existing video and get back the matching footage.
Text-to-video, … |
@lancedb |
Company |
Original |
2026-08-05 |
803 |
8 |
1 |
1 |
0 |
5 |
| LanceDB is headed to #Actuate26 by @foxglove in 15 days 🤖
Robotics teams generate huge volumes of video, LiDAR, sensor… |
@lancedb |
Company |
Original |
2026-08-04 |
635 |
8 |
1 |
0 |
0 |
0 |
| .@joaomdmoura and @crewAIInc rebuilt agent memory on @LanceDB.
Memory now uses scope, recency, importance, contradicti… |
@lancedb |
Company |
Original |
2026-08-03 |
1,057 |
12 |
4 |
1 |
0 |
6 |
| Check out our open source repo for large scale multimodal training examples with LanceDB!
3 examples published so far:… |
@lancedb |
Company |
Original |
2026-07-30 |
967 |
10 |
1 |
0 |
0 |
5 |
| A dataset dump gets you raw files, embedding and indexing still yours to build.
EuroSAT in Lance format on @huggingfac… |
@lancedb |
Company |
Original |
2026-07-29 |
984 |
15 |
3 |
1 |
0 |
2 |
| 0.53 → 0.66 accuracy
0.66 → 0.80 recall@5
That's swapping keyword search for vector search in the new @LanceDB memory … |
@lancedb |
Company |
Original |
2026-07-28 |
769 |
14 |
1 |
2 |
0 |
2 |
| 7 days for model training down to 1. 95% GPU utilization. 100K+ QPS.
@ByteDanceOSS's Volcano Engine rebuilt its AI sta… |
@lancedb |
Company |
Original |
2026-07-27 |
708 |
7 |
0 |
0 |
0 |
2 |
| LeRobot's X-VLA soft-fold dataset in Lance format: 1,542 episodes, three camera streams, 2.85M frames.
Every MP4 segme… |
@lancedb |
Company |
Original |
2026-07-22 |
576 |
9 |
0 |
1 |
0 |
5 |
| Top-k OR queries in Lance's full-text search just got 3x faster 🔥
0.103s → 0.034s at k10
0.198s → 0.063s at k100 on a … |
@lancedb |
Company |
Original |
2026-07-21 |
632 |
8 |
1 |
1 |
0 |
3 |
| Point a VLM at scanned documents and it works... until the corpus hits a few million pages.
Then every query is a mult… |
@lancedb |
Company |
Original |
2026-07-20 |
949 |
10 |
3 |
4 |
0 |
7 |
| RaBitQ in Lance skips the raw vector refine step.
5-bit codes hit 96.2% recall@10 at 2.6x lower p99 latency than an u… |
@lancedb |
Company |
Original |
2026-07-16 |
740 |
8 |
1 |
0 |
0 |
2 |
| Lance now opens a 65K column table in 17 milliseconds. It used to take 17s. That's 1,032x faster 🚀
Wide tables are no … |
@lancedb |
Company |
Original |
2026-07-15 |
8,795 |
32 |
2 |
1 |
2 |
5 |
| @Ceph has never had native nearest neighbor search, so RAG meant bolting on a vector database and running two systems.
… |
@lancedb |
Company |
Original |
2026-07-14 |
420 |
9 |
0 |
0 |
0 |
3 |
| 🌟 June's highlight: Lance averaged 140ms commit latency across a 10,000-commit S3 benchmark, versus 534ms for Delta Lak… |
@lancedb |
Company |
Original |
2026-07-09 |
746 |
8 |
1 |
1 |
1 |
0 |
| And that's a wrap on World's Fair in SF 🎉
Thanks to everyone who stopped by the booth to say hi and dive into LanceDB… |
@lancedb |
Company |
Original |
2026-07-07 |
5,200 |
17 |
2 |
3 |
0 |
0 |
| How do you trace one number in a 200 page ESG report back to the exact page it came from? We dug into that with the @ll… |
@lancedb |
Company |
Original |
2026-07-06 |
1,663 |
4 |
3 |
1 |
0 |
7 |
| LibriSpeech in Lance format on @huggingface.
One table holds FLAC audio, transcripts, speaker metadata, and transcrip… |
@lancedb |
Company |
Original |
2026-07-01 |
809 |
17 |
4 |
0 |
0 |
6 |
| Qwen2.5-VL-3B QLoRA fine-tuning on TextVQA: the vision tower is frozen during training but most pipelines still run it … |
@lancedb |
Company |
Original |
2026-06-30 |
763 |
10 |
3 |
1 |
0 |
5 |
| 1/3 At @aiDotEngineer World's Fair this week. Booth B1, come say hi, grab swag, or get your hardest data stack question… |
@lancedb |
Company |
Original |
2026-06-29 |
396 |
4 |
0 |
1 |
0 |
1 |
| 1/ Lance is now a native @prestodb connector.
Run distributed SQL across Lance tables and join them against Hive, Ice… |
@lancedb |
Company |
Original |
2026-06-25 |
800 |
14 |
2 |
1 |
0 |
4 |
| Take a break from @aiDotEngineer World's Fair next week to cheer on Team USA at the World Cup with us, @ExaAILabs, @Ext… |
@lancedb |
Company |
Original |
2026-06-24 |
680 |
9 |
3 |
0 |
0 |
0 |
| Updating a label on a row that contains a 50MB video shouldn't require Spark to read that video.
Lance Blob V2 in Lanc… |
@lancedb |
Company |
Original |
2026-06-24 |
656 |
13 |
1 |
0 |
0 |
4 |
| At @aiDotEngineer World's Fair next week? Come join us Tuesday night 🏓
We're co-hosting an evening at SPIN with @Theor… |
@lancedb |
Company |
Original |
2026-06-23 |
6,210 |
19 |
4 |
0 |
0 |
5 |
| ⚡️ RaBitQ multi-bit reranking in Lance is ~12% faster at 1536d, same recall.
The old path rebuilt a 1.5 MiB lookup tab… |
@lancedb |
Company |
Original |
2026-06-22 |
1,573 |
23 |
2 |
0 |
0 |
11 |
| "𝘈𝘨𝘦𝘯𝘵𝘴 𝘢𝘳𝘦 𝘬𝘪𝘯𝘥 𝘰𝘧 𝘭𝘪𝘬𝘦 𝘢𝘯 𝘪𝘥𝘦𝘢𝘭 𝘨𝘢𝘴. 𝘐𝘧 𝘺𝘰𝘶 𝘮𝘢𝘬𝘦 𝘪𝘵 𝘦𝘢𝘴𝘺 𝘧𝘰𝘳 𝘵𝘩𝘦𝘮, 𝘵𝘩𝘦𝘺 𝘸𝘪𝘭𝘭 𝘦𝘹𝘱𝘢𝘯𝘥 𝘵𝘰 𝘧𝘪𝘭𝘭 𝘸𝘩𝘢𝘵𝘦𝘷𝘦𝘳 𝘤𝘰𝘮𝘱𝘶𝘵𝘦, 𝘥𝘢𝘵𝘢, 𝘢… |
@lancedb |
Company |
Original |
2026-06-19 |
1,034 |
3 |
2 |
0 |
0 |
3 |
| Lance IVF_RQ search now has an 𝐚𝐩𝐩𝐫𝐨𝐱_𝐦𝐨𝐝𝐞 parameter. Same index, no rebuild required.
→ 𝐟𝐚𝐬𝐭: 1-bit scoring, lower la… |
@lancedb |
Company |
Original |
2026-06-18 |
431 |
11 |
2 |
0 |
0 |
0 |
| AI Engineer World's Fair, June 29 – July 2 in San Francisco.
GPU job dies at 90%. 19 copies of the same dataset, nobod… |
@lancedb |
Company |
Original |
2026-06-17 |
1,968 |
15 |
2 |
1 |
0 |
2 |
| More and more frontier labs and agentic frameworks are choosing LanceDB: a table that's durable 𝘢𝘯𝘥 performant on any s… |
@lancedb |
Company |
Original |
2026-06-15 |
1,348 |
21 |
4 |
0 |
1 |
8 |
| Most feature engineering pipelines rewrite the full table for every new column.
In Lance, adding a column writes only… |
@lancedb |
Company |
Original |
2026-06-11 |
861 |
16 |
3 |
0 |
0 |
8 |
| 1/ Two LanceDB sessions at @databricks #DataAISummit next week in SF (June 15-18) https://t.co/jzfm0w6iGt |
@lancedb |
Company |
Original |
2026-06-10 |
1,284 |
9 |
0 |
1 |
1 |
2 |
| Prashanth Rao @tech_optimist and Sarwar Bhuiyan are running a workshop at TMLS on June 19.
𝗘𝗻𝗵𝗮𝗻𝗰𝗶𝗻𝗴 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗗𝗮𝘁𝗮 𝗣𝗶𝗽… |
@lancedb |
Company |
Original |
2026-06-08 |
984 |
4 |
1 |
1 |
1 |
2 |
| 1/ May's highlight: stable-worldmodel paper published, standardizing world model pipelines on Lance, with Lance-backed … |
@lancedb |
Company |
Original |
2026-06-05 |
1,446 |
12 |
3 |
2 |
0 |
8 |
| 1/ 3-4x faster data loading on Push-T vs HDF5 or video formats at a fraction of the disk size. stable-worldmodel uses L… |
@lancedb |
Company |
Original |
2026-06-04 |
723 |
8 |
3 |
1 |
0 |
1 |
| Lei Xu is speaking at #SnowflakeSummit this Thursday alongside Vishwa Lakkundi (Sr. Manager, Snowflake) for 𝗔𝗽𝗮𝗰𝗵𝗲 𝗣𝗼𝗹𝗮… |
@lancedb |
Company |
Original |
2026-06-02 |
959 |
8 |
1 |
1 |
1 |
0 |
| Cosmos 3 by @nvidia released today — a frontier omnimodal world model for Physical AI.
For the data infrastructure beh… |
@lancedb |
Company |
Original |
2026-06-01 |
3,498 |
20 |
5 |
2 |
1 |
9 |
| 1/ Most curation pipelines have no shared version history. Six months later, nobody knows which rows trained that model… |
@lancedb |
Company |
Original |
2026-06-01 |
691 |
9 |
1 |
1 |
0 |
5 |
| 1/ World model research is fragmented: every paper reimplements its own data pipeline, baselines, and eval harness. Com… |
@lancedb |
Company |
Original |
2026-05-27 |
18,723 |
61 |
13 |
1 |
4 |
39 |
| 1/ Three systems to query your own images: object store for bytes, vector DB for embeddings, SQL warehouse for metadata… |
@lancedb |
Company |
Original |
2026-05-26 |
1,313 |
21 |
1 |
1 |
0 |
9 |
| 1/ LanceDB is in the @msft4startups spotlight at Microsoft Build 2026. Come find us in San Francisco.
We build the mul… |
@lancedb |
Company |
Original |
2026-05-25 |
899 |
11 |
3 |
1 |
0 |
2 |
| 1/ @DuckDB 🤝 LanceDB.
Cold indexed vector search: 12 ms.
Cold hybrid search: 17 ms.
On a single table with CLIP em… |
@lancedb |
Company |
Original |
2026-05-21 |
2,101 |
27 |
6 |
1 |
0 |
14 |
| 1/ TOMORROW NIGHT in Menlo Park: LanceDB, @dlthub, and @DataHubCloud in the same room. Ingestion, retrieval, lineage — … |
@lancedb |
Company |
Original |
2026-05-20 |
832 |
9 |
2 |
2 |
1 |
2 |
| 1/ With LeRobot v3's default layout, exploring a dataset before training means pulling more data than you need.
𝗹𝗲𝗿𝗼𝗯… |
@lancedb |
Company |
Original |
2026-05-19 |
1,322 |
16 |
3 |
1 |
0 |
6 |
| What happens when a duck in a shield walks onto a yacht?
We're still not entirely sure — but it involved @lancedb, @mo… |
@lancedb |
Company |
Original |
2026-05-18 |
567 |
11 |
0 |
0 |
0 |
0 |
| Lance for robotics 🤝🤗 |
@lancedb |
Company |
Quote |
2026-05-15 |
859 |
5 |
0 |
0 |
0 |
1 |
| 1/ Hannes Mühleisen announced Quack — @duckdb's new client-server protocol — at Day 1 of @AICouncilConf. Lance works wi… |
@lancedb |
Company |
Original |
2026-05-14 |
6,525 |
35 |
5 |
2 |
3 |
9 |
| 1/ Past 1B vectors, three things break: index won't fit on one node, centroid scans go linear, RaBitQ rotation costs O(… |
@lancedb |
Company |
Original |
2026-05-13 |
2,007 |
8 |
1 |
1 |
1 |
4 |
| Vector search gets expensive because the index has to live in RAM — bigger dataset, bigger instance.
LanceDB stores t… |
@lancedb |
Company |
Original |
2026-05-12 |
1,393 |
20 |
2 |
0 |
0 |
15 |
| 1/ @AICouncilConf starts tomorrow 🚀 Find us at the LanceDB booth — especially if you're training multimodal models at s… |
@lancedb |
Company |
Original |
2026-05-11 |
519 |
12 |
1 |
1 |
0 |
2 |
| Hear ye, hear ye — the LanceDB team rides forth to @AICouncilConf in SF next week ⚔️🏰
Seek us at our booth within the… |
@lancedb |
Company |
Original |
2026-05-08 |
2,334 |
11 |
2 |
3 |
2 |
2 |
| Apache DataFusion meetup in San Francisco is back!
@tech_optimist, AI Engineer at LanceDB will be diving into the the … |
@lancedb |
Company |
Original |
2026-05-07 |
1,099 |
11 |
1 |
0 |
1 |
0 |
| Modern problems = modern solutions!
Hear from the engineers at LanceDB, @dlthub, and @DataHubCloud building the ingest… |
@lancedb |
Company |
Original |
2026-05-06 |
298 |
6 |
0 |
0 |
0 |
2 |
| Model quality is a numbers game. Checkpoint overhead shouldn't be the thing that limits how many experiments you run.
… |
@lancedb |
Company |
Original |
2026-05-05 |
381 |
5 |
0 |
0 |
0 |
1 |
| 1/ For 20 years: metadata in the DB, pointer to the file, sync them later. That pattern held for BI. It doesn't hold wh… |
@lancedb |
Company |
Original |
2026-05-05 |
524 |
1 |
0 |
1 |
0 |
2 |
| @changhiskhan on stage at AI Agent Conference in NYC! https://t.co/QErHI3DOFa |
@lancedb |
Company |
Original |
2026-05-04 |
222 |
6 |
0 |
1 |
0 |
0 |
| Last call for Agent Builders Night 🚀
Take the night off from AI Agent Conference and join LanceDB, @braintrust, @modal… |
@lancedb |
Company |
Original |
2026-05-04 |
4,446 |
3 |
0 |
0 |
1 |
2 |
| Boats are better than ballrooms for talking data infrastructure.
On May 13th, we are co-hosting a private evening on t… |
@lancedb |
Company |
Original |
2026-05-01 |
1,007 |
9 |
3 |
0 |
0 |
1 |
| 1/ Multimodal RAG agents typically need 3 hops to reason over media: vector search → graph traversal → blob fetch.
@t… |
@lancedb |
Company |
Original |
2026-04-30 |
845 |
5 |
0 |
1 |
1 |
2 |
| 1/ Scaling vector search to 10B vectors has three distinct bottlenecks: linear centroid scans, O(d²) RaBitQ rotation at… |
@lancedb |
Company |
Original |
2026-04-30 |
822 |
9 |
1 |
1 |
1 |
4 |
| OpenXData by @Onehousehq is live tomorrow!
Join @changhiskhan's session to learn how LanceDB's unified multimodal lake… |
@lancedb |
Company |
Original |
2026-04-28 |
329 |
3 |
2 |
2 |
0 |
0 |
| 1/ Chang She (@changhiskhan) is speaking at @AICouncilConf!
Why trillion-row multimodal tables break every data system… |
@lancedb |
Company |
Original |
2026-04-27 |
991 |
9 |
2 |
1 |
0 |
2 |
| Adding a column to a 10M row dataset: 𝗟𝗮𝗻𝗰𝗲 - 𝟭𝟯𝗺𝘀 ⚔️ Parquet - 520 seconds. Lance writes new columns as separate files… |
@lancedb |
Company |
Original |
2026-04-16 |
4,550 |
35 |
5 |
4 |
0 |
15 |
| 1/ Autonomous driving data pipelines have a specific failure mode: annotation adds a column, LMDB rewrites the whole da… |
@lancedb |
Company |
Original |
2026-04-15 |
495 |
2 |
0 |
1 |
0 |
0 |
| “𝗟𝗲𝘀𝘀 𝗧𝗼𝗸𝗶𝗼 𝗶𝘀 𝗠𝗼𝗿𝗲 𝗧𝗼𝗸𝗶𝗼: 𝗦𝘁𝗿𝗮𝘁𝗲𝗴𝗶𝗲𝘀 𝗳𝗼𝗿 𝗔𝗰𝗰𝗲𝗹𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗮 𝗥𝘂𝘀𝘁 𝗡𝗮𝘁𝗶𝘃𝗲 𝗦𝗲𝗮𝗿𝗰𝗵 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲” @ TokioConf 2026 – April 20 in P… |
@lancedb |
Company |
Original |
2026-04-14 |
1,797 |
7 |
0 |
1 |
1 |
5 |
| 1/4 At ~100M cells, “download → load → analyze” breaks.
Querying a subset means terabytes moved, duplicated datasets, … |
@lancedb |
Company |
Original |
2026-04-13 |
760 |
8 |
3 |
1 |
0 |
4 |
| 1/7 LanceDB March Newsletter is out — focused on performance + scale 🔥
Here’s what shipped ↓ https://t.co/HjOwOOAhOq |
@lancedb |
Company |
Original |
2026-04-10 |
634 |
5 |
0 |
1 |
0 |
1 |
| 𝘿𝙤 𝙮𝙤𝙪 𝙧𝙚𝙖𝙡𝙡𝙮 𝙣𝙚𝙚𝙙 𝙑𝙖𝙧𝙞𝙖𝙣𝙩 𝙛𝙤𝙧 𝙮𝙤𝙪𝙧 𝘼𝙄 𝙙𝙖𝙩𝙖?
We benchmarked Lance JSONB vs Parquet Variant on real-world JSON workload… |
@lancedb |
Company |
Original |
2026-04-09 |
1,323 |
6 |
0 |
1 |
1 |
0 |
| 1/4 If your agent fails on PDFs with tables or charts, it’s usually not the model.
It’s the data pipeline. 🧵
We worke… |
@lancedb |
Company |
Original |
2026-04-08 |
442 |
7 |
3 |
1 |
0 |
3 |
| 1/3 If your dataset doubles, your storage cost shouldn’t.
And your GPUs shouldn’t slow down reading it.
Most formats … |
@lancedb |
Company |
Original |
2026-04-07 |
480 |
7 |
0 |
2 |
0 |
3 |
| Only 2 weeks away from Data Engineering Open Forum 2026 in SF on April 16!
Join us for "Powering Netflix's Multimodal … |
@lancedb |
Company |
Original |
2026-04-02 |
407 |
6 |
2 |
1 |
0 |
1 |
| TONIGHT! Join us, @anyscalecompute, and @ExaAILabs as we dive into Exa's web-scale AI search stack, powered by Lance an… |
@lancedb |
Company |
Original |
2026-03-31 |
1,100 |
7 |
0 |
0 |
1 |
3 |
| Just merged into Lance: a completely new FTS index layout
🚀 9.35x faster index builds (34s → 3.6s)
🚀 8.87x smaller i… |
@lancedb |
Company |
Original |
2026-03-30 |
2,501 |
40 |
7 |
1 |
0 |
15 |
| 1/4 If your agent memory requires multiple tool calls to retrieve context, recall quality drops.
We benchmarked 3 @Ope… |
@lancedb |
Company |
Original |
2026-03-26 |
2,169 |
18 |
2 |
2 |
1 |
5 |
| 1/5 Multimodal datasets break most blob storage strategies.
Why?
Because production workloads hit three constraints a… |
@lancedb |
Company |
Original |
2026-03-25 |
619 |
6 |
1 |
1 |
0 |
0 |
| 1/3 Upload a Lance dataset to 🤗 @huggingface in 3 steps:
1. Convert raw data (JSON, images) into a Lance table
2. Add … |
@lancedb |
Company |
Original |
2026-03-24 |
1,440 |
15 |
5 |
1 |
1 |
4 |
| Excited to announce that Lance is now a 𝗰𝗼𝗿𝗲 𝗲𝘅𝘁𝗲𝗻𝘀𝗶𝗼𝗻 of @duckdb! 🦆🚀
The Lance core extension allows DuckDB users to … |
@lancedb |
Company |
Original |
2026-03-23 |
13,586 |
179 |
21 |
3 |
5 |
82 |
| 1/3 What does it take to run search over billions of documents *and* keep it continuously updated?
Join LanceDB, @anys… |
@lancedb |
Company |
Original |
2026-03-19 |
2,025 |
9 |
0 |
1 |
1 |
2 |
| 1/3 LanceDB, @openclaw, and Seed 2.0 let you go from a few screenshots to a working frontend without writing specs.
Th… |
@lancedb |
Company |
Original |
2026-03-18 |
498 |
8 |
1 |
2 |
0 |
2 |
| Join us March 26 in SF for a panel with leaders building the next generation of AI-native developer tools:
@changhiskha… |
@lancedb |
Company |
Original |
2026-03-17 |
432 |
6 |
0 |
1 |
0 |
0 |
| Did you spot Lance & LanceDB in Jensen Huang's keynote at @nvidia GTC today? 👀
Jensen highlighted one of the bigge… |
@lancedb |
Company |
Original |
2026-03-17 |
1,817 |
39 |
3 |
2 |
0 |
13 |
| 1/3 @OpenClaw agents persist memory across sessions.
Preferences, facts, and prior decisions can be written during one… |
@lancedb |
Company |
Original |
2026-03-16 |
2,714 |
7 |
2 |
2 |
1 |
3 |
| Taken from last year's team offsite! So it only makes sense that LanceDB is the default memory layer for @openclaw 🦞 ht… |
@lancedb |
Company |
Original |
2026-03-12 |
418 |
8 |
1 |
0 |
0 |
0 |
| Cool to see people building persistent memory for AI agents with LanceDB!
This @OpenClaw tutorial by @tonbistudio show… |
@lancedb |
Company |
Original |
2026-03-12 |
513 |
5 |
0 |
2 |
0 |
2 |
| @dlthub and @huggingface 🤗 just shipped a clean way to ingest Hugging Face datasets into LanceDB 🚀
Query datasets over… |
@lancedb |
Company |
Original |
2026-03-11 |
898 |
23 |
6 |
2 |
0 |
10 |
| 1/6 Lance Blob V2 introduces multi-semantic blob storage under a single column type.
Instead of forcing all binary dat… |
@lancedb |
Company |
Original |
2026-03-11 |
1,333 |
17 |
4 |
3 |
1 |
8 |
| 1/3 Lance file format 2.2 is here 🎉
This release adds several format-level capabilities for working with complex ML da… |
@lancedb |
Company |
Original |
2026-03-09 |
1,958 |
18 |
3 |
2 |
0 |
5 |
| 1/8 This month in the Lance ecosystem, we made it easier to publish, experiment, and search on the same dataset!
Highl… |
@lancedb |
Company |
Original |
2026-03-05 |
515 |
4 |
0 |
1 |
0 |
2 |
| Your dataset contains images with GPS coordinates.
You want to run queries like:
“Find images taken within 1 km of th… |
@lancedb |
Company |
Original |
2026-03-04 |
1,079 |
13 |
3 |
1 |
0 |
7 |
| 1/4 If you’re building long-term memory for agents, vector search alone is not enough.
memory-lancedb-pro by @AISuperD… |
@lancedb |
Company |
Original |
2026-03-03 |
2,097 |
16 |
2 |
3 |
1 |
11 |
| 1/3 Geospatial support just landed in Lance.
And no new storage format work was required.
Because Lance is Arrow-nati… |
@lancedb |
Company |
Original |
2026-02-25 |
745 |
18 |
5 |
1 |
0 |
4 |
| Our next Lance Community Sync is this Thursday 2/26 at 9am PT!
Everyone is welcome to join. Subscribe to the Lance For… |
@lancedb |
Company |
Original |
2026-02-24 |
392 |
4 |
2 |
0 |
0 |
0 |
| 1/4 3.5B vectors. 0 database servers.
@metagenomi’s enzyme discovery stack runs ANN on LanceDB, directly from S3 with … |
@lancedb |
Company |
Original |
2026-02-24 |
1,291 |
17 |
0 |
2 |
0 |
12 |
| 1/3 @nowledgelabs redesigned its search stack and chose @lancedb as its dedicated text + vector engine.
Here’s what ch… |
@lancedb |
Company |
Original |
2026-02-23 |
12,708 |
17 |
5 |
1 |
6 |
13 |
| Attending PyAI Conference on March 10 in San Francisco? Check out Chang’s session - 𝟭𝟬 𝗧𝗵𝗶𝗻𝗴𝘀 𝗜 𝗛𝗮𝘁𝗲 𝗔𝗯𝗼𝘂𝘁 𝗙𝗲𝗮𝘁𝘂𝗿𝗲 𝗘𝗻𝗴𝗶… |
@lancedb |
Company |
Original |
2026-02-19 |
330 |
3 |
0 |
1 |
0 |
0 |
| “Almost every AI problem can be boiled down to a search problem.”
@changhiskhan (CEO, LanceDB) joined @BEBischof (Hea… |
@lancedb |
Company |
Original |
2026-02-18 |
1,355 |
17 |
2 |
0 |
0 |
6 |
| 1/3 In Lance, we unify branching and shallow cloning using multi-base.
Instead of choosing between shared-metadata bra… |
@lancedb |
Company |
Original |
2026-02-17 |
650 |
7 |
0 |
2 |
1 |
1 |
| 1/4 Branching for ML data shouldn’t slow down production.
Iceberg branching → shared metadata bottlenecks.
Delta shall… |
@lancedb |
Company |
Original |
2026-02-16 |
542 |
7 |
2 |
1 |
0 |
2 |
| 1/6 Here’s a quick example of how to read @huggingface datasets via LanceDB.
Start with opening a LanceDB connection … |
@lancedb |
Company |
Original |
2026-02-12 |
270 |
5 |
2 |
1 |
0 |
0 |
| 1/6 LAION-1M in Lance format packages images, CLIP embeddings, and metadata into a single, queryable table on the 🤗 @h… |
@lancedb |
Company |
Original |
2026-02-11 |
455 |
9 |
0 |
1 |
0 |
1 |
| 1/6 FineWeb-Edu in Lance format brings scan, retrieval, and dataset evolution together for text at billion-row scale.
… |
@lancedb |
Company |
Original |
2026-02-10 |
573 |
5 |
1 |
1 |
0 |
2 |
| 1/6 OpenVid-1M in Lance format shows what’s possible when videos, metadata, embeddings, and indexes live in the same da… |
@lancedb |
Company |
Original |
2026-02-09 |
11,801 |
38 |
10 |
3 |
2 |
21 |
| 𝗨𝘀𝗲 𝗟𝗮𝗻𝗰𝗲𝗗𝗕 𝗮𝘀 𝗮 𝗺𝗲𝗺𝗼𝗿𝘆 𝘀𝘁𝗼𝗿𝗲 𝗳𝗼𝗿 𝘆𝗼𝘂𝗿 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗶𝗻 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 🦞
Simply set `plugins.slots.memory = "memory-lancedb”` in… |
@lancedb |
Company |
Original |
2026-02-06 |
881 |
6 |
2 |
2 |
1 |
1 |
| 1/5 Large multimodal datasets change constantly. Rewriting them shouldn’t be expensive.
On the 🤗 @huggingface Hub, Lan… |
@lancedb |
Company |
Original |
2026-02-05 |
238 |
5 |
1 |
1 |
0 |
0 |
| 1/5 Large multimodal blobs don’t have to break dataset workflows.
Images and videos are often treated as external file… |
@lancedb |
Company |
Original |
2026-02-04 |
2,564 |
21 |
9 |
2 |
1 |
3 |
| 1/6 Why store your datasets in Lance format on @huggingface Hub?
With native Lance support on the 🤗 Hub, you can pub… |
@lancedb |
Company |
Original |
2026-02-03 |
1,049 |
14 |
4 |
1 |
1 |
3 |
| 1/3 Lance ❤️ @huggingface 🤗
We’re excited to announce native support for Lance on the Hugging Face Hub!
You can now … |
@lancedb |
Company |
Original |
2026-02-02 |
14,309 |
50 |
13 |
6 |
4 |
11 |
| The @openclaw community is cooking with @lancedb! A couple of weeks ago, a "memory (LanceDB)" plugin for agents was rel… |
@lancedb |
Company |
Original |
2026-01-30 |
1,347 |
10 |
1 |
2 |
1 |
8 |
| 𝗖𝗼𝗺𝗯𝗶𝗻𝗶𝗻𝗴 𝗮 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲𝗿 𝗿𝗲𝘄𝗼𝗿𝗸 𝘄𝗶𝘁𝗵 𝗶𝗼_𝘂𝗿𝗶𝗻𝗴, 𝘄𝗲 𝘄𝗲𝗿𝗲 𝗮𝗯𝗹𝗲 𝘁𝗼 𝗮𝗰𝗵𝗶𝗲𝘃𝗲 𝟭,𝟱𝟬𝟬,𝟬𝟬𝟬 𝗜𝗢𝗣𝗦 𝘄𝗶𝘁𝗵 𝗟𝗮𝗻𝗰𝗲
In this blog, Weston Pac… |
@lancedb |
Company |
Original |
2026-01-29 |
352 |
5 |
3 |
1 |
0 |
3 |
| Our next Lance Community Sync is this Thursday 1/29 at 9am PT!
Some topics we’ll discuss include subproject incubation… |
@lancedb |
Company |
Original |
2026-01-28 |
395 |
6 |
1 |
0 |
0 |
0 |
| Fine-tuning embedding models can improve retrieval quality, but it’s not always the right lever.
This post walks throu… |
@lancedb |
Company |
Original |
2026-01-27 |
512 |
9 |
1 |
0 |
0 |
4 |
| 𝗪𝗵𝗮𝘁 𝗶𝗳 𝘀𝗲𝗮𝗿𝗰𝗵𝗶𝗻𝗴 𝘃𝗶𝗱𝗲𝗼𝘀 𝘄𝗼𝗿𝗸𝗲𝗱 𝘁𝗵𝗲 𝘄𝗮𝘆 𝗵𝘂𝗺𝗮𝗻𝘀 𝘁𝗵𝗶𝗻𝗸?
This demo shows how LanceDB enables multimodal video search:
• N… |
@lancedb |
Company |
Original |
2026-01-26 |
1,119 |
13 |
0 |
0 |
0 |
6 |
| Organizations have a lot of knowledge trapped in slide decks. This blog post by @cocoindex_io demonstrates a 𝗦𝗹𝗶𝗱𝗲𝘀-𝘁𝗼… |
@lancedb |
Company |
Original |
2026-01-23 |
1,033 |
15 |
2 |
3 |
1 |
7 |
| 𝗪𝗵𝗲𝗻 𝗲𝘃𝗲𝗿𝘆 𝘄𝗲𝗯 𝗽𝗮𝗴𝗲 𝗽𝗿𝗼𝗱𝘂𝗰𝗲𝘀 𝗱𝗼𝘇𝗲𝗻𝘀 𝗼𝗳 𝗲𝘃𝗼𝗹𝘃𝗶𝗻𝗴 𝗮𝗿𝘁𝗶𝗳𝗮𝗰𝘁𝘀, @ExaAILabs built exa-d on Lance so they can update individua… |
@lancedb |
Company |
Original |
2026-01-22 |
337 |
6 |
1 |
0 |
0 |
0 |
| 🎤 Prashanth Rao @tech_optimist will be speaking at Data Day Texas on why modern AI and multimodal workloads demand a n… |
@lancedb |
Company |
Original |
2026-01-21 |
1,161 |
6 |
0 |
0 |
1 |
0 |
| Dive deep into the Apache Polaris + Lance integration with the @apachepolaris and Lance communities.
We’ll be walking … |
@lancedb |
Company |
Original |
2026-01-21 |
238 |
4 |
0 |
1 |
0 |
0 |
| The AI infra team at @Uber pushed us to rethink how table formats handle file paths in Lance
At Uber scale, a single o… |
@lancedb |
Company |
Original |
2026-01-20 |
319 |
7 |
1 |
2 |
0 |
0 |
| 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗹𝗮𝗻𝗰𝗲-𝗰𝗼𝗻𝘁𝗲𝘅𝘁, 𝗮 𝘀𝗽𝗲𝗰𝗶𝗮𝗹𝗶𝘇𝗲𝗱 𝗹𝗶𝗯𝗿𝗮𝗿𝘆 𝗳𝗼𝗿 𝗺𝗮𝗻𝗮𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗹𝗶𝗳𝗲𝗰𝘆𝗰𝗹𝗲 𝗼𝗳 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝗰𝗼𝗻𝘁𝗲𝘅𝘁.
@Uber is al… |
@lancedb |
Company |
Original |
2026-01-19 |
1,867 |
15 |
3 |
1 |
1 |
5 |
| 1/6 Agentic search feels magical… until your data changes.
Your retrieval layer silently goes stale, and your agent s… |
@lancedb |
Company |
Original |
2026-01-15 |
465 |
7 |
3 |
1 |
0 |
3 |
| Lance & @apachepolaris are coming together to make the open multimodal lakehouse real 🚀
With this integration, 𝗟𝗮𝗻𝗰𝗲 𝘁… |
@lancedb |
Company |
Original |
2026-01-14 |
237 |
7 |
0 |
1 |
0 |
1 |
| In real AI systems, multimodality shows up across three dimensions:
1. How the data looks
2. How the data is accessed
3… |
@lancedb |
Company |
Original |
2026-01-13 |
210 |
6 |
0 |
1 |
0 |
3 |
| 𝗦𝗤𝗟 𝗳𝗼𝗿 𝗿𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗼𝗻 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗱𝗮𝘁𝗮 𝗷𝘂𝘀𝘁 𝗴𝗼𝘁 𝗮 𝗹𝗼𝘁 𝘀𝗶𝗺𝗽𝗹𝗲𝗿.
DuckDB can now act as a compute engine on top of Lance, a… |
@lancedb |
Company |
Original |
2026-01-12 |
726 |
16 |
3 |
2 |
0 |
4 |
| 🚀 𝗪𝗵𝗮𝘁 𝘁𝗵𝗲 𝗟𝗮𝗻𝗰𝗲 𝘁𝗲𝗮𝗺 𝘀𝗵𝗶𝗽𝗽𝗲𝗱 𝗶𝗻 𝗗𝗲𝗰𝗲𝗺𝗯𝗲𝗿 𝘁𝗼 𝘄𝗿𝗮𝗽 𝘂𝗽 𝟮𝟬𝟮𝟱 https://t.co/S6mOlgtpbj |
@lancedb |
Company |
Original |
2026-01-09 |
709 |
6 |
1 |
1 |
1 |
2 |
| 🚀 𝗟𝗮𝗻𝗰𝗲𝗗𝗕 𝗘𝗻𝘁𝗲𝗿𝗽𝗿𝗶𝘀𝗲 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲 𝗼𝗻 𝘁𝗵𝗲 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 𝗔𝘇𝘂𝗿𝗲 𝗠𝗮𝗿𝗸𝗲𝘁𝗽𝗹𝗮𝗰𝗲
An AI-native multimodal lakehouse for poweri… |
@lancedb |
Company |
Original |
2026-01-08 |
279 |
8 |
0 |
0 |
0 |
1 |
| 1/5 @lancedb 🫶🏻 @duckdb
We’re happy to announce a new Lance extension for DuckDB! You can simply install this extensio… |
@lancedb |
Company |
Original |
2026-01-07 |
2,145 |
16 |
8 |
1 |
1 |
3 |
| Kicking off the new year with our 1st Lance Community Sync next Thursday 1/15 at 9am PT!
Everyone is welcome to join.… |
@lancedb |
Company |
Original |
2026-01-06 |
361 |
3 |
1 |
0 |
0 |
2 |
| 1/5 In this blog post, we discuss what we mean by “multimodal” and the different lenses through which it can be viewed.… |
@lancedb |
Company |
Original |
2026-01-06 |
805 |
9 |
4 |
1 |
0 |
1 |
| Happy holidays and happy new year from the LanceDB team ✨
The team grew and the open source community grew even faster… |
@lancedb |
Company |
Original |
2025-12-30 |
2,453 |
25 |
2 |
2 |
0 |
0 |
| Reranking is a late-stage retrieval technique that improves precision without changing your embedding or indexing layer… |
@lancedb |
Company |
Original |
2025-12-29 |
8,463 |
81 |
8 |
2 |
2 |
78 |
| Merry Christmas and happy holidays from the @lancedb team! Lots of new projects are cooking, but one thing is clear: Fr… |
@lancedb |
Company |
Quote |
2025-12-25 |
1,207 |
12 |
1 |
0 |
0 |
1 |
| How do you use Lance tables 𝙞𝙣𝙨𝙞𝙙𝙚 your existing data stack without replacing your catalog or metadata layer?
Lance Na… |
@lancedb |
Company |
Original |
2025-12-22 |
1,288 |
18 |
2 |
0 |
0 |
5 |
| 𝗖𝗼𝗺𝗯𝗶𝗻𝗲 𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗮𝗻𝗱 𝗸𝗲𝘆𝘄𝗼𝗿𝗱 𝘀𝗲𝗮𝗿𝗰𝗵 𝗮𝗰𝗿𝗼𝘀𝘀 𝟰𝟭𝗠+ 𝗪𝗶𝗸𝗶𝗽𝗲𝗱𝗶𝗮 𝗮𝗿𝘁𝗶𝗰𝗹𝗲𝘀
We built WikiSearch, a search engine that stores an… |
@lancedb |
Company |
Original |
2025-12-17 |
5,099 |
85 |
10 |
3 |
0 |
56 |
| Watch ChanChan & Lu’s sessions from KubeCon NA!
🎤 Highly Scalable AI Search Engine and AI Data Lake With Kubernete… |
@lancedb |
Company |
Original |
2025-12-16 |
1,253 |
14 |
2 |
1 |
0 |
1 |
| Lance SDK 1.0.0 is live 🚀
This release reflects how the project is used today. Lance now backs production workloads ac… |
@lancedb |
Company |
Original |
2025-12-15 |
4,776 |
41 |
5 |
0 |
0 |
11 |
| If you missed our sessions from @PyData Seattle, the recordings are live! https://t.co/Lmi3ZVSc2z |
@lancedb |
Company |
Original |
2025-12-11 |
339 |
3 |
0 |
1 |
0 |
1 |
| LanceDB is proud to be a Silver Member of the newly formed Agentic AI Foundation (AAIF) under the Linux Foundation.
AA… |
@lancedb |
Company |
Original |
2025-12-10 |
1,337 |
15 |
4 |
1 |
0 |
3 |
| Iceberg for BI. Lance for AI. Here’s how they fit together 🤝 https://t.co/C0IP6GQW0f |
@lancedb |
Company |
Original |
2025-12-09 |
644 |
4 |
0 |
1 |
0 |
2 |
| From @Netflix's Ray Summit 2025 talk with LanceDB: Pablo Delgado shows how multimodal embeddings organize content into … |
@lancedb |
Company |
Original |
2025-12-08 |
713 |
14 |
4 |
1 |
0 |
8 |
| Check out our talk from @ScaleByTheBay that's up on YouTube now. Hear about the benefits of @lancedb of multimodal data… |
@lancedb |
Company |
Quote |
2025-12-05 |
1,298 |
6 |
0 |
0 |
0 |
1 |
| New community blog post out! Our friends at @getkiln have been cooking up a guide on how to build better RAG systems. L… |
@lancedb |
Company |
Original |
2025-12-02 |
595 |
8 |
4 |
1 |
0 |
0 |
| Check out our latest deep-dive post on the @lancedb blog that compares and contrasts the Lance format with @ApacheIcebe… |
@lancedb |
Company |
Original |
2025-11-26 |
928 |
14 |
2 |
1 |
0 |
4 |
| A few folks from the @lancedb were at this hackathon on building data agents last weekend, and the findings were quite … |
@lancedb |
Company |
Quote |
2025-11-25 |
977 |
8 |
0 |
0 |
0 |
1 |
| Pablo Delgado @pablete from @netflix demonstrates text-to-image search at Ray Summit 2025.
Upload a reference image → … |
@lancedb |
Company |
Original |
2025-11-20 |
355 |
3 |
0 |
1 |
0 |
3 |
| We’re excited to introduce formal governance for the Lance open-source format, giving contributors a structured way to … |
@lancedb |
Company |
Original |
2025-11-18 |
3,362 |
25 |
6 |
1 |
1 |
6 |
| LanceDB is heading to #AWSreinvent!
If you’re building AI systems that need fast hybrid search, scalable feature engi… |
@lancedb |
Company |
Original |
2025-11-17 |
1,366 |
18 |
2 |
1 |
0 |
1 |
| Prashanth Rao @tech_optimist, AI Engineer, is speaking at @ScaleByTheBay next week!
Don’t miss his session - Agents Ne… |
@lancedb |
Company |
Original |
2025-11-13 |
1,579 |
13 |
1 |
1 |
1 |
4 |
| Here's a demo from @Netflix's Pablo Delgado @pablete showcasing text-to-text semantic search at Ray Summit 2025.
Watch… |
@lancedb |
Company |
Original |
2025-11-12 |
2,004 |
19 |
4 |
1 |
1 |
5 |
| Fei-Fei Li’s essay on Spatial Intelligence explores world models that connect perception and action—learning from video… |
@lancedb |
Company |
Original |
2025-11-11 |
1,225 |
11 |
1 |
1 |
0 |
4 |
| Lei Xu, Co-Founder and CTO, will be presenting at next week’s Real Time Data Lakes and AI Meetup in SF! https://t.co/DP… |
@lancedb |
Company |
Original |
2025-11-10 |
980 |
13 |
1 |
1 |
0 |
2 |
| Lei Xu and Pablo Delgado of @netflix took the stage on Wednesday at Ray Summit 2025! https://t.co/IoXPGryCEr |
@lancedb |
Company |
Original |
2025-11-07 |
1,689 |
10 |
1 |
1 |
1 |
1 |
| Lu Qiu and ChanChan Mao are heading to KubeCon + CloudNativeCon in Atlanta, GA!
Don’t miss our 2 sessions this year! h… |
@lancedb |
Company |
Original |
2025-11-05 |
674 |
3 |
1 |
1 |
0 |
0 |
| We’re heading to the Open Lakehouse + AI Mini Summit (Nov 13, Mountain View)!
Join Chang She @changhiskhan for Scaling… |
@lancedb |
Company |
Original |
2025-11-04 |
919 |
14 |
1 |
2 |
0 |
1 |
| 💫 What’s New in the LanceDB Universe (October 2025 Edition)
🫶 Community Spotlight
Huge thanks to contributors from @N… |
@lancedb |
Company |
Original |
2025-11-03 |
614 |
9 |
1 |
1 |
0 |
0 |
| Building and curating large-scale multimodal datasets has long been a complex, resource-heavy challenge. But that’s cha… |
@lancedb |
Company |
Original |
2025-10-30 |
783 |
9 |
3 |
1 |
0 |
1 |
| 1/5 @netflix leverages the Multimodal Lakehouse to power its Media Data Lake — unifying video, audio, subtitles, and me… |
@lancedb |
Company |
Original |
2025-10-29 |
1,419 |
14 |
2 |
2 |
0 |
4 |
| Welcome! Excited for what we will be doing together! |
@lancedb |
Company |
Quote |
2025-10-28 |
1,885 |
7 |
0 |
0 |
0 |
0 |
