Different techniques are needed to max out modern NVMe SSDs.
@westonpace.bsky.social LanceDB blog is so good if you want the industrial version: lancedb.com/blog/one-mil...
Viktor Leis's LeanStore paper is great if you want the academic version: vldb.org/pvldb/vol16/...
@westonpace.bsky.social LanceDB blog is so good if you want the industrial version: lancedb.com/blog/one-mil...
Viktor Leis's LeanStore paper is great if you want the academic version: vldb.org/pvldb/vol16/...
The Quest for One Million IOPS: Benchmarking Storage at LanceDB
Learn how LanceDB benchmarks storage and how we achieved one million disk reads per second.
lancedb.com
February 7, 2026 at 11:59 AM
Different techniques are needed to max out modern NVMe SSDs.
@westonpace.bsky.social LanceDB blog is so good if you want the industrial version: lancedb.com/blog/one-mil...
Viktor Leis's LeanStore paper is great if you want the academic version: vldb.org/pvldb/vol16/...
@westonpace.bsky.social LanceDB blog is so good if you want the industrial version: lancedb.com/blog/one-mil...
Viktor Leis's LeanStore paper is great if you want the academic version: vldb.org/pvldb/vol16/...
There are so many vector databases out there... so many.
I kind of like LanceDB. It takes up no resources when idle and is really fast. What else does one need?
github.com/lancedb/lanc...
I kind of like LanceDB. It takes up no resources when idle and is really fast. What else does one need?
github.com/lancedb/lanc...
GitHub - lancedb/lancedb: Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps! - lancedb/lancedb
github.com
November 21, 2024 at 7:10 PM
There are so many vector databases out there... so many.
I kind of like LanceDB. It takes up no resources when idle and is really fast. What else does one need?
github.com/lancedb/lanc...
I kind of like LanceDB. It takes up no resources when idle and is really fast. What else does one need?
github.com/lancedb/lanc...
How LanceDB handles backpressure : Columnar File Readers in Depth blog.lancedb.com/col...
October 28, 2024 at 6:17 PM
How LanceDB handles backpressure : Columnar File Readers in Depth blog.lancedb.com/col...
MLOps/LLMOps/AgentOps 勉強会でLanceDBについて紹介しました！
speakerdeck.com/mocobeta/lan...
speakerdeck.com/mocobeta/lan...
LanceDB入門
第67回 MLOps/LLMOps/AgentOps 勉強会 (https://mlops.connpass.com/event/401457/) の発表資料です。
speakerdeck.com
August 11, 2026 at 12:43 PM
MLOps/LLMOps/AgentOps 勉強会でLanceDBについて紹介しました！
speakerdeck.com/mocobeta/lan...
speakerdeck.com/mocobeta/lan...
New @talkpython.fm episode: Multimodal data with LanceDB with Change She and host @mkennedy.codes #Python
talkpython.fm/episodes/sho...
talkpython.fm/episodes/sho...
Multimodal data with LanceDB
LanceDB is a developer-friendly, open source database for AI. It's used by well-known companies such as Midjourney and Character.ai. We have Chang She, the CEO and cofounder of LanceDB on to give us a...
talkpython.fm
December 12, 2024 at 9:32 PM
New @talkpython.fm episode: Multimodal data with LanceDB with Change She and host @mkennedy.codes #Python
talkpython.fm/episodes/sho...
talkpython.fm/episodes/sho...
I use Claude to code the scrapers and scripts to manage the data sets. Then I use a qwen3 8b or 4b embed model along with LanceDB for the vector database. I have a rtx 4090, so I can run the embed process at home.
July 23, 2026 at 7:57 PM
I use Claude to code the scrapers and scripts to manage the data sets. Then I use a qwen3 8b or 4b embed model along with LanceDB for the vector database. I have a rtx 4090, so I can run the embed process at home.
Love this list! (esp TigerBeetle, FoundationDB, @duckdb.org).
I'd add other favorites: @pglite.dev from @electric-sql.com, FrostDB from @polarsignals.com, LanceDB
I'd add other favorites: @pglite.dev from @electric-sql.com, FrostDB from @polarsignals.com, LanceDB
Following up from 7 languages, how about 7 databases to explore in 2025? Some crowd favourites and some more niche entries are covered here:
7 Databases in 7 Weeks for 2025
7 databases to explore over in 2025.
matt.blwt.io
December 6, 2024 at 7:01 PM
Love this list! (esp TigerBeetle, FoundationDB, @duckdb.org).
I'd add other favorites: @pglite.dev from @electric-sql.com, FrostDB from @polarsignals.com, LanceDB
I'd add other favorites: @pglite.dev from @electric-sql.com, FrostDB from @polarsignals.com, LanceDB
Nothing more satisfying than hitting those big round number goals: lancedb.com/blog/one-mil...
The Quest for One Million IOPS: Benchmarking Storage at LanceDB
Learn how LanceDB benchmarks storage and how we achieved one million disk reads per second.
lancedb.com
January 29, 2026 at 6:48 PM
Nothing more satisfying than hitting those big round number goals: lancedb.com/blog/one-mil...
github.com/lancedb/lanc... my first PR to LanceDB was merged! :)
feat: add hybrid search example in Rust by mocobeta · Pull Request #2579 · lancedb/lancedb
Hello!
I'm new to lancedb and interested in the Rust SDK.
I couldn't find a good hybrid search example in Rust, so I created one.
Usage
$ cargo run --quiet --example hybrid_search --feature...
github.com
August 13, 2025 at 12:01 PM
github.com/lancedb/lanc... my first PR to LanceDB was merged! :)
LanceDBの小ネタ書きました / LanceDBのPythonSDKで全文検索，ベクトル検索，ハイブリッド検索をする
blog.mocobeta.dev/posts/202508...
blog.mocobeta.dev/posts/202508...
LanceDBのPythonSDKで全文検索，ベクトル検索，ハイブリッド検索をする | Keep Coding by @mocobeta
blog.mocobeta.dev
August 8, 2025 at 11:50 AM
LanceDBの小ネタ書きました / LanceDBのPythonSDKで全文検索，ベクトル検索，ハイブリッド検索をする
blog.mocobeta.dev/posts/202508...
blog.mocobeta.dev/posts/202508...
And it's a wrap! I got something done for once! github.com/tigrisdata-c...
February 7, 2025 at 9:04 PM
And it's a wrap! I got something done for once! github.com/tigrisdata-c...
I have been working on a talk about the future of table formats, specifically what is needed for AI workloads, and I found Weston's blogs on LanceDB well written and super helpful: lancedb.com/blog/designi...
Designing a Table Format for ML Workloads
Explore designing a table format for ML workloads with practical insights and expert guidance from the LanceDB team.
lancedb.com
January 26, 2026 at 11:51 AM
I have been working on a talk about the future of table formats, specifically what is needed for AI workloads, and I found Weston's blogs on LanceDB well written and super helpful: lancedb.com/blog/designi...
Has anyone worked with lancedb? It looks powerful and simple for vector storage: github.com/lancedb/lanc...
GitHub - lancedb/lancedb: Developer-friendly, embedded retrieval engine for multimodal AI. Search More; Manage Less.
Developer-friendly, embedded retrieval engine for multimodal AI. Search More; Manage Less. - lancedb/lancedb
github.com
May 26, 2025 at 7:29 PM
Has anyone worked with lancedb? It looks powerful and simple for vector storage: github.com/lancedb/lanc...
Trying out #lancedb for storing/retrieving vector data.
1.44 GB 😧 for an simplistic example from their docs: docs.rs/lancedb/late...
233 MB for the release build, still an insane size.
Maybe someone should tell them about rust features to get the binary size down!
I will not use #lancedb ...
1.44 GB 😧 for an simplistic example from their docs: docs.rs/lancedb/late...
233 MB for the release build, still an insane size.
Maybe someone should tell them about rust features to get the binary size down!
I will not use #lancedb ...
January 18, 2026 at 5:28 PM
Trying out #lancedb for storing/retrieving vector data.
1.44 GB 😧 for an simplistic example from their docs: docs.rs/lancedb/late...
233 MB for the release build, still an insane size.
Maybe someone should tell them about rust features to get the binary size down!
I will not use #lancedb ...
1.44 GB 😧 for an simplistic example from their docs: docs.rs/lancedb/late...
233 MB for the release build, still an insane size.
Maybe someone should tell them about rust features to get the binary size down!
I will not use #lancedb ...
LanceDBのRust APIで全文検索，ベクトル検索，ハイブリッド検索をする | Keep Coding by @mocobeta
blog.mocobeta.dev
August 9, 2025 at 7:46 AM
A while back the DuckDB Labs team started a collaboration with LanceDB to bring you an extension that interacts with the Lance lakehouse format from DuckDB. In this post we take the extension for a test drive! duckdb.org/2026/05/21/t...
Test-Driving the Lance Lakehouse Format in DuckDB
Lance is an open lakehouse format with a design geared toward AI workloads. LanceDB and DuckDB Labs have partnered to bring you fast vector and hybrid search directly from DuckDB SQL, without leaving ...
duckdb.org
May 21, 2026 at 10:10 AM
A while back the DuckDB Labs team started a collaboration with LanceDB to bring you an extension that interacts with the Lance lakehouse format from DuckDB. In this post we take the extension for a test drive! duckdb.org/2026/05/21/t...
lancedb / lance: Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with m ... ★5158 https://github.com/lancedb/lance
lancedb / lance
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..
github.com
August 5, 2025 at 1:05 PM
lancedb / lance: Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with m ... ★5158 https://github.com/lancedb/lance
lancedb / lance: Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with m ... ★5333 https://github.com/lancedb/lance
lancedb / lance
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..
github.com
September 11, 2025 at 4:21 PM
lancedb / lance: Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with m ... ★5333 https://github.com/lancedb/lance
pgvectorとLanceDBの性能比較と考察。やはりPythonのGILの影響が大きいなあ。
implicit-none.com/ja/pgvector-...
implicit-none.com/ja/pgvector-...
pgvector vs LanceDB 実測ベンチマーク｜RAG のベクトル検索はどちらを選ぶか (10万件×1536次元)
pgvector 0.8.6 と LanceDB 0.36 を同一データ (DBpedia OpenAI 埋め込み 10万件×1536次元) で実測比較。投入は LanceDB が 20 倍速、単独クエリも 2 倍速だが、8 並行では pgvector が逆転。フィルタ併用では pgvector の recall がプランナ次第で 0.07 に崩壊する条件と対策 (ANALYZE / iterat...
implicit-none.com
August 12, 2026 at 12:31 AM
pgvectorとLanceDBの性能比較と考察。やはりPythonのGILの影響が大きいなあ。
implicit-none.com/ja/pgvector-...
implicit-none.com/ja/pgvector-...
TIL: 今からRAGを始めるなら，LanceDBがいいんじゃないかなと思った話
blog.mocobeta.dev/posts/202506...
blog.mocobeta.dev/posts/202506...
今からRAGを始めるなら，LanceDBがいいんじゃないかなと思った話 | Keep Coding by @mocobeta
blog.mocobeta.dev
June 29, 2025 at 1:01 PM
TIL: 今からRAGを始めるなら，LanceDBがいいんじゃないかなと思った話
blog.mocobeta.dev/posts/202506...
blog.mocobeta.dev/posts/202506...
lancedb / lance: Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with m ... ★4610 https://github.com/lancedb/lance
lancedb / lance
Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..
github.com
May 13, 2025 at 12:55 PM
lancedb / lance: Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with m ... ★4610 https://github.com/lancedb/lance
📊 #VectorDB #LanceDB v0.4.5 works with @pola.rs DataFrames & LazyFrames for faster vector data handling. Vectorize your CSV fast!
👉 Discuss in Discord: linktr.ee/qdrddr
#AI #LLM #DataFrames
👉 Discuss in Discord: linktr.ee/qdrddr
#AI #LLM #DataFrames
LanceDB + Polars
A (near) perfect match
A spiritual successor to pandas, Polars is a new blazing fast DataFrame library for Python written in Rust. At LanceDB, we hear from many of our users that they process data us...
blog.lancedb.com
August 14, 2025 at 9:13 PM
📊 #VectorDB #LanceDB v0.4.5 works with @pola.rs DataFrames & LazyFrames for faster vector data handling. Vectorize your CSV fast!
👉 Discuss in Discord: linktr.ee/qdrddr
#AI #LLM #DataFrames
👉 Discuss in Discord: linktr.ee/qdrddr
#AI #LLM #DataFrames
I made an example app using my haiku.rag (github.com/ggozad/haiku...), the open-source local RAG library using @pydantic.dev, to create a research assistant.
Video demonstration here: vimeo.com/1128874386
#AI #python #open-source #RAG
Video demonstration here: vimeo.com/1128874386
#AI #python #open-source #RAG
GitHub - ggozad/haiku.rag: Retrieval Augmented Generation based on LanceDB
Retrieval Augmented Generation based on LanceDB. Contribute to ggozad/haiku.rag development by creating an account on GitHub.
github.com
October 20, 2025 at 2:52 PM
I made an example app using my haiku.rag (github.com/ggozad/haiku...), the open-source local RAG library using @pydantic.dev, to create a research assistant.
Video demonstration here: vimeo.com/1128874386
#AI #python #open-source #RAG
Video demonstration here: vimeo.com/1128874386
#AI #python #open-source #RAG
⚡ Scaling #Multimodal AI Lakehouse w/ Lance & LanceDB, Chang She (LanceDB)
⚡ Your Lakehouse Has Everything You Need, Sammy Sidhu (Eventual)
⚡ DuckLake: The SQL-Powered #Lakehouse Format, @hannes.muehleisen.org (DuckDB)
⚡ Composable Open Table Formats, Ion Koutsouris & Robert Pack (Delta Maintainers)
⚡ Your Lakehouse Has Everything You Need, Sammy Sidhu (Eventual)
⚡ DuckLake: The SQL-Powered #Lakehouse Format, @hannes.muehleisen.org (DuckDB)
⚡ Composable Open Table Formats, Ion Koutsouris & Robert Pack (Delta Maintainers)
August 25, 2025 at 10:18 AM
⚡ Scaling #Multimodal AI Lakehouse w/ Lance & LanceDB, Chang She (LanceDB)
⚡ Your Lakehouse Has Everything You Need, Sammy Sidhu (Eventual)
⚡ DuckLake: The SQL-Powered #Lakehouse Format, @hannes.muehleisen.org (DuckDB)
⚡ Composable Open Table Formats, Ion Koutsouris & Robert Pack (Delta Maintainers)
⚡ Your Lakehouse Has Everything You Need, Sammy Sidhu (Eventual)
⚡ DuckLake: The SQL-Powered #Lakehouse Format, @hannes.muehleisen.org (DuckDB)
⚡ Composable Open Table Formats, Ion Koutsouris & Robert Pack (Delta Maintainers)