https://www.m365.fm/entity/diskann/DiskANN is a graph-based approximate nearest neighbor search algorithm from Microsoft Research that keeps a compressed navigation layer in RAM and the full-precision graph on SSD. It is used in services such as Azure Cosmos DB and SQL Server vector search.enhttps://www.m365.fm/community/u/mirko-p/blog/conquering-the-billion-vector-problem-in-azure-ai-search/https://www.m365.fm/community/u/mirko-p/blog/conquering-the-billion-vector-problem-in-azure-ai-search/Wed, 26 Aug 2026 15:52:25 -0000articleWelcome to our deep dive into one of the most pressing challenges in modern enterprise artificial intelligence: scaling vector search to billions of records. If you…https://www.m365.fm/community/u/mirko-p/blog/solving-the-billion-vector-problem-in-azure-ai-search/https://www.m365.fm/community/u/mirko-p/blog/solving-the-billion-vector-problem-in-azure-ai-search/Wed, 26 Aug 2026 09:52:17 -0000articleExplore the unique technical challenges of searching massive datasets at scale. This post breaks down how high dimensionality and memory constraints impact enterpri…https://www.m365.fm/show/episodes/the-billion-vector-problem-hnsw-vs-diskann-in-azure-ai-search/https://www.m365.fm/show/episodes/the-billion-vector-problem-hnsw-vs-diskann-in-azure-ai-search/Mon, 08 Jun 2026 00:00:00 -0000episodeThe explosion of AI-powered applications has created a new challenge: how do you efficiently search through billions of vector embeddings without exploding infrastructure costs? In this episode, we explore the “billion-vector problem” and compare two leading…