Franck Pachot1d ago
In PostgreSQL managed services on Azure, you can index your embeddings with #pgvector or #DiskANN. I compared and explored DiskANN pre-filtering and cost-based optimization in a new blog post: https://dev.to/franckpachot/vector-search-with-filters-pgvector-vs-diskann-on-horizondb-i2k
Vector Search with Filters: pgvector vs DiskANN on HorizonDB

In a previous post, I explained that using filtering with pgvector can decrease recall in approximate...

DEV Community
N-gated Hacker NewsDec 30
🚀🚀 BREAKING NEWS: A new #Postgres extension claims to boost #performance and scale with #vector #magic 🧙‍♂️✨. Apparently, #DiskANN works alongside #pgvector, because the only thing better than one overhyped feature is two! OSS licensed, because who wouldn't want to spend hours wrestling with open source? 🤦‍♂️
https://github.com/timescale/pgvectorscale #HackerNews #ngated
GitHub - timescale/pgvectorscale: Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.

Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed. - timescale/pgvectorscale

GitHub
Howard Chu @ SymasNov 14, 2025

#DiskANN and #HNSW (Hierarchical Navigable Small World graphs) appear to be trending again. First popped onto my radar 2 years ago, using #LMDB. https://xcancel.com/search?f=tweets&q=%23DiskANN&cursor=DAADDAABCgABGnlm6BXbcfcKAAIY9_luAhchywAIAAIAAAACCAADAAAAAAgABAAAAAAKAAUbmx1GGMAnEAoABhubHUYYv9jwAAA

A lot of the more recent noise seems to be on M$ infrastructure. For those with more money than brains...

Gea-Suan LinAug 5, 2025

https://blog.gslin.org/archives/2025/08/06/12559/%e9%97%9c%e6%96%bc-embedding-%e6%90%9c%e5%b0%8b%e5%95%8f%e9%a1%8c%e7%9a%84%e5%9d%91/

關於 Embedding 搜尋問題的坑

#algorithm #amazon #aws #cloud #disk #diskann #embedding #filtered #filtereddiskann #fresh #freshdiskann #hnsw #microsoft #model #s3 #search #service #turbobuffer #vector

關於 Embedding 搜尋問題的坑

清 RSS feed 裡面翻到「Introducing Amazon S3 Vectors: First cloud storage with native vector support at scale (preview)」這篇，意外的發現 AWS 提供了 embedding 搜尋的產品？ 我很好奇的是，目前大家主力都是 HNSW，這應該還是限制在 in-memory 等級的搜尋 (...

Gea-Suan Lin's BLOG
Gareth Emslie 🇿🇦 🇪🇦 🇨🇭Jun 15, 2024
Azure Cosmos DB has integrated DiskANN technology, enabling high-accuracy and efficient vector search at a massive scale. This enhancement improves efficiency, reduces latency, and offers a cost-effective solution for managing and analyzing large datasets. https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/vector-search-using-95-less-compute-diskann-with-azure-cosmos-db/ba-p/4162956 #AzureCosmosDB #DiskANN #AIApplications #softcorpremium
Vector Search using 95% Less Compute | DiskANN with Azure Cosmos DB

Ensure high-accuracy, efficient vector search with DiskANN and Azure Cosmos DB.

TECHCOMMUNITY.MICROSOFT.COM
keroDec 24, 2023
Just before Christmas I offer you this article on how the Meilisearch team implemented filtered #DiskAnn on arroy and integrated it in the engine 🎁
Wouldn't it be cool to do fast and relevant #hybridSearch?
https://blog.kerollmops.com/meilisearch-expands-search-power-with-arroy-s-filtered-disk-ann
Meilisearch Expands Search Power with Arroy's Filtered Disk ANN

Article by Clément Renault titled: Meilisearch Expands Search Power with Arroy's Filtered Disk ANN.

keroDec 16, 2023
You all asked for it! I just released the second part of my blog series on Arroy: #DiskANN-inspired library. https://blog.kerollmops.com/multithreading-and-memory-mapping-refining-ann-performance-with-arroy
Multithreading and Memory-Mapping: Refining ANN Performance with Arroy

Dive into my journey of porting Spotify's Annoy library to Rust using LMDB. Learn how I tackled memory-mapped file challenges, optimized tree node generation, and achieved significant performance improvements for indexing large vector datasets. Discover the power of the Share Nothing principle and prepare for future insights on incremental indexing and filtering.

keroDec 8, 2023
Today, I want to discuss the beginning of our journey in building our homemade #DiskANN data structure and how we made it work on top of #lmdb. We were highly inspired by the @spotifyeng work. We made it safer, much faster and added a bunch of features to it. https://blog.kerollmops.com/spotify-inspired-elevating-meilisearch-with-hybrid-search-and-rust
Spotify-Inspired: Elevating Meilisearch with Hybrid Search and Rust

Article by Clément Renault titled: Spotify-Inspired: Elevating Meilisearch with Hybrid Search and Rust.

keroDec 1, 2023
What if I tell you that Meilisearch is about to ship with a homemade #DiskANN vector store? Spotify/Annoy highly inspired our new library. Arroy allows you to do Approximate Nearest Neighbors search in hundreds of millions of vectors. https://github.com/meilisearch/arroy
GitHub - meilisearch/arroy: Annoy-inspired Approximate Nearest Neighbors in Rust, based on LMDB and optimized for memory usage :boom:

Annoy-inspired Approximate Nearest Neighbors in Rust, based on LMDB and optimized for memory usage :boom: - GitHub - meilisearch/arroy: Annoy-inspired Approximate Nearest Neighbors in Rust, based o...

GitHub