DiskANN

Concept

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.

Title graphic: DiskANN (Concept)

Tipo	Concept

Articles about DiskANN (4)

Como resolver o problema dos bilhões de vetores no Azure AI Search
2026-08-26 · Mirko Peters
Bem-vindo ao nosso mergulho profundo em um dos desafios mais urgentes da inteligência artificial corporativa moderna: escalar a busca vetorial para bilhões de registros. Se você te
Resolvendo o problema de bilhões de vetores no Azure AI Search
2026-08-26 · Mirko Peters
Explore os desafios técnicos específicos de pesquisar conjuntos de dados massivos em escala. Este post analisa como a alta dimensionalidade e as restrições de memória afetam as car
Conquering the Billion-Vector Problem in Azure AI Search
2026-08-26 · Mirko Peters
Welcome 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…
Solving the Billion-Vector Problem in Azure AI Search
2026-08-26 · Mirko Peters
Explore the unique technical challenges of searching massive datasets at scale. This post breaks down how high dimensionality and memory constraints impact enterpri…

Glossário

Community wiki

Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.

Especialistas e empresas para este tópico

Ninguém indicou ainda este tópico. Adicione-o ao seu perfil.

Sources

Profile: www.microsoft.com/research/publication/diskann-fast-accurate-billion-point-nearest-neighbor-search-on-a-single-node
Feed for this topic (RSS): entity/diskann/feed.xml
Articles on this topic: 4

Maintained by Mirko Peters (Microsoft MVP) · Last updated: 2026-11-03