Showing results for Vector database - Azure Cosmos DB Blog

At Microsoft Build 2025, we're excited to announce general availability of search capabilities for Azure Cosmos DB, including full-text and hybrid search, enabling developers to build highly performant, scalable, and intelligent applications. We're also introducing new preview enhancements such as multi-language support and fuzzy search, further en...

Vector search with Azure Cosmos DB  In Part 1 and Part 2 of this series, we explored vector search with Azure Cosmos DB and best practices for scaling it to 1 billion vector datasets while maintaining low query latency. In Part 3, we saw how we can create efficient sharded DiskANN indices for multi-tenant apps.  In Part 4, we’ll look at the eff...

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 maintain...

Microsoft Ignite 2024 took over the Windy City this week, bringing with it new technological innovation and exciting product announcements aplenty! If you missed the first day of the show, don't worry – we’ve got you covered with all the latest and greatest Azure Cosmos DB news. This year's event saw great enthusiasm and attendance at McCorm...

We’re excited to announce several new features and advancements for search and retrieval functionalities in Azure Cosmos DB for NoSQL including: These features open the door to building new search and AI scenarios on Azure Cosmos DB, particularly benefiting Retrieval-Augmented Generation (RAG) and multi-agent AI applications by...

Azure Cosmos DB powers some of the world’s most popular intelligent apps like ChatGPT. In a recent hackathon, Over 9,500 developers engaged with Azure Cosmos DB and Azure AI services, making it one of the most popular on Devpost, ranking in the top 0.2% of all Devpost hackathons.  Participants explored AI fundamentals and built their own AI appl...

We are excited to publish a new whitepaper titled, Microsoft DiskANN in Azure Cosmos DB, where we examine the impressive capabilities of Microsoft DiskANN, a state-of-the-art indexing system designed for accurate and cost-efficient vector search at any scale. We start off with a review of key vector search and database concepts, then follow by d...

We are thrilled to introduce the Azure Cosmos DB Samples Gallery —your ultimate destination for top-tier Azure Cosmos DB samples, technical guidance, and content created by both Microsoft and the community, including Azure OpenAI samples.   Who is it for? Designed for developers and technical professionals, this gallery is an invaluable ...

We’re excited to announce that the DiskANN vector index is now in open public preview in Azure Cosmos DB for NoSQL! This means that anyone who enrolls an Azure Cosmos DB for NoSQL resource in the Vector Search Public Preview now automatically gets access to the most powerful and scalable vector index on the planet. What is DiskANN? ...

Vector Search with Azure Cosmos DB Azure Cosmos DB NoSQL features advanced vector indexing and search capabilities powered by DiskANN, a suite of highly scalable, accurate, and cost-effective approximate nearest neighbor (ANN) algorithms for low-latency vector search at any scale. Azure Cosmos DB features key capabilities important for building...