Azure Cosmos DB with DiskANN Part 2: Scaling to 1 Billion Vectors with
Introduction In the first part of our series on Azure Cosmos DB Vector Search with DiskANN, we explored the fundamentals of vector indexing and search capabilities using Azure Cosmos DB for NoSQL and demonstrated a few early performance and cost characteristics. In Part 2, we’ll demonstrate how to scale to 1 billion vector datasets, while […]
The post Azure Cosmos DB with DiskANN Part 2: Scaling to 1 Billion Vectors with <100ms Search Latency appeared first on Azure Cosmos DB Blog.
Published on:
Learn moreRelated posts
What’s New with Microsoft Foundry (formerly Azure AI Foundry) from Ignite 2025
Microsoft Ignite 2025 just wrapped up, and one of the biggest themes this year was the evolution of Azure AI Foundry, now simply called Micros...
Announcing: Dynamic Data Masking for Azure Cosmos DB (Preview)
Today marks a big step forward with the public preview of Dynamic Data Masking (DDM) for Azure Cosmos DB. This feature helps organizations pro...
Use Azure SRE Agent with Azure Cosmos DB: Smarter Diagnostics for Your Applications
We’re excited to announce the Azure Cosmos DB SRE Agent built on Azure SRE Agent; a new capability designed to simplify troubleshooting and im...
General Availability: Priority-Based Execution in Azure Cosmos DB
Have you ever faced a situation where two different workloads share the same container, and one ends up slowing down the other? This is a comm...