{"id":8672,"date":"2024-09-12T08:00:51","date_gmt":"2024-09-12T15:00:51","guid":{"rendered":"https:\/\/devblogs.microsoft.com\/cosmosdb\/?p=8672"},"modified":"2024-09-11T12:16:01","modified_gmt":"2024-09-11T19:16:01","slug":"diskann-for-azure-cosmos-db-now-in-open-public-preview","status":"publish","type":"post","link":"https:\/\/devblogs.microsoft.com\/cosmosdb\/diskann-for-azure-cosmos-db-now-in-open-public-preview\/","title":{"rendered":"DiskANN for Azure Cosmos DB Now in Open Public Preview!"},"content":{"rendered":"<div class=\"content user-select-text\" tabindex=\"0\" aria-description=\"\" aria-label=\"Sent by Copilot: Certainly! Here are two paragraphs about **DiskANN** in **Azure Cosmos DB** being in open public preview: 1. **DiskANN Vector Indexing and Search in Azure Cosmos DB**: Azure Cosmos DB, Microsoft's NoSQL database service, has introduced a powerful feature: **DiskANN vector indexing and search**. This feature is now available in **public preview**. With DiskANN, developers can perform **vector similarity searches** with high performance, accuracy, and scalability. DiskANN leverages a suite of state-of-the-art vector indexing algorithms developed at **Microsoft Research**. It allows you to determine the similarity between text strings using vector embeddings stored directly in Azure Cosmos DB. This eliminates the need for a separate vector database and simplifies your architecture. Whether you're building generative AI applications or working with large-scale vector data, DiskANN-powered vector indexing in Azure Cosmos DB provides a robust solution. 2. **Seamless Integration and Benefits**: By enrolling in the **Vector Search preview feature**, developers automatically gain access to the DiskANN vector index type. This integration enables you to combine vector search capabilities with Azure Cosmos DB's rich query filters. Additionally, you can take advantage of features like **flexible schema-less document structures**, **serverless or provisioned throughput models**, **99.999% availability**, and **instant autoscale**. Azure Cosmos DB becomes your one-stop database for both transactional and vector data workloads. Whether you're building recommendation systems, content similarity engines, or personalized search experiences, DiskANN in Azure Cosmos DB empowers you to unlock the full potential of vector-based applications. [^1^] [^2^] If you're interested in trying out this exciting feature, you can enroll in the preview by following the steps provided in the [official documentation](^3^). Happy exploring! \ud83d\ude80\">\n<div class=\"ac-container ac-adaptiveCard has-image\">\n<div class=\"ac-textBlock\">\n<div class=\"content user-select-text\" tabindex=\"0\" aria-description=\"\" aria-label=\"Sent by Copilot: Certainly! Here's a draft for your blog post about **DiskANN in Azure Cosmos DB**: --- # **DiskANN in Azure Cosmos DB Now in Public Preview** We're excited to announce that **Azure Cosmos DB for NoSQL** now includes **DiskANN vector indexing and search** in its public preview! This powerful feature allows developers to perform **vector similarity searches** with high performance, accuracy, and scalability. Let's dive into the details: 1. **What is DiskANN?** - **DiskANN** is a state-of-the-art suite of **vector indexing algorithms** developed at **Microsoft Research**. It enables efficient storage and retrieval of high-dimensional vectors. - With DiskANN, you can build applications that require similarity searches, such as **recommendation engines**, **image recognition**, and **natural language processing**. - DiskANN-powered vector indexing is available alongside other indexing options like **flat vector indexes** and **quantized vectors**. 2. **Why Use DiskANN in Azure Cosmos DB?** - **High Performance**: DiskANN provides blazing-fast vector search capabilities, allowing you to find similar vectors across large datasets. - **Rich Query Filters**: Combine vector search with Azure Cosmos DB's flexible query filters to create powerful and customized queries. - **Flexible Schema-less Document Structures**: Leverage Azure Cosmos DB's schema-less design to store both transactional data and vectors in a single database. - **99.999% Availability**: Azure Cosmos DB ensures high availability for your critical workloads. - **Instant Autoscale**: Scale your vector search workloads dynamically based on demand. Enroll in the **Vector Search preview feature**, and you'll automatically gain access to the **DiskANN vector index type**. Simplify your AI architectures, keep data and vectors in sync, and explore the possibilities of vector-based applications with Azure Cosmos DB. Learn more about DiskANN-powered vector indexing in Azure Cosmos DB [here](https:\/\/azure.microsoft.com\/en-us\/updates\/public-preview-diskann-vector-indexing-and-search-in-azure-cosmos-db-nosql\/). --- Feel free to customize and expand upon this draft for your blog post! \ud83d\ude0a\">\n<div class=\"ac-container ac-adaptiveCard has-image\">\n<div class=\"ac-textBlock\">\n<p>We\u2019re excited to announce that the <strong>DiskANN vector index is now in open public preview in Azure Cosmos DB for NoSQL! <\/strong>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.<\/p>\n<h2>What is DiskANN?<\/h2>\n<div class=\"content user-select-text\" tabindex=\"0\" aria-description=\"\" aria-label=\"Sent by Copilot: DiskANN is a powerful tool designed for low-latency, cost-effective, and highly accurate vector search at any scale. It leverages disk-based storage to handle large datasets efficiently, ensuring quick retrieval times. This makes it an ideal solution for applications requiring real-time search capabilities without compromising on accuracy. Additionally, DiskANN's scalability allows it to maintain performance even as data volumes grow.\">\n<div class=\"ac-container ac-adaptiveCard\">\n<div class=\"ac-textBlock\">\n<p><a href=\"https:\/\/www.microsoft.com\/research\/publication\/diskann-fast-accurate-billion-point-nearest-neighbor-search-on-a-single-node\/?msockid=091c323873cd6bd6392120ac72e46a98\" target=\"_blank\" rel=\"noopener\">DiskANN<\/a> is a powerful set of algorithms developed at Microsoft Research for low-latency, cost-effective, and highly accurate vector search at scale. It&#8217;s an ideal solution for applications requiring fast and efficient search capabilities without compromising on accuracy.<\/p>\n<p><a href=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-8060\" src=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch.png\" alt=\"Image DiskANNArch\" width=\"2500\" height=\"1406\" srcset=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch.png 2500w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch-300x169.png 300w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch-1024x576.png 1024w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch-768x432.png 768w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch-1536x864.png 1536w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/05\/DiskANNArch-2048x1152.png 2048w\" sizes=\"(max-width: 2500px) 100vw, 2500px\" \/><\/a><\/p>\n<ul>\n<li>DiskANN is a graph-based indexing and search system that performs fast and accurate approximate nearest neighbor (ANN) search at\u00a0<strong>any-scale<\/strong>.<\/li>\n<li>It primarily uses an SSD-based index to scale to an order of magnitude more points compared to in-memory indices, while still retaining\u00a0<strong>high QPS and low latency.<\/strong><\/li>\n<li>Quantized (compressed) vectors are kept in memory, and DiskANN balances interactions between the two to offer low latency and high accuracy.<\/li>\n<li>DiskANN is based on a novel graph index called\u00a0<strong>Vamana<\/strong>\u00a0that is more versatile than existing graph indices by maintaining accuracy despite many insertions, modifications, and deletions, without the need for expensive index rebuilds.<\/li>\n<\/ul>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<h2>Why use Azure Cosmos DB with DiskANN?<\/h2>\n<div class=\"ac-textBlock\">\n<div class=\"content user-select-text\" tabindex=\"0\" aria-description=\"\" aria-label=\"Sent by Copilot: Certainly! Let's give it a fresh spin: **Azure Cosmos DB**, the NoSQL powerhouse, doesn't just tiptoe into the world of vectors\u2014it **breaks through** with the swagger of a cosmic explorer! \ud83d\ude80 Imagine a symphony of **advanced vector indexing** and **search capabilities**, all orchestrated by the **DiskANN** suite\u2014an ensemble of algorithms that's not just accurate, but **cost-effective** too. These algorithms are like the **rockstars** of approximate nearest neighbor (ANN) search, delivering low-latency vector magic at **any scale**. But wait, there's more! Azure Cosmos DB isn't just a backstage pass; it's the **main act** for building **Modern AI applications**. Here's why it's stealing the show: 1. **Mission-Critical Vector Store**: Picture a vault where vectors strut their stuff, flaunting **industry-leading similarity search performance**. And guess what? It doesn't lean on niche solutions; it's the **headliner** itself! 2. **No-ETL Magic**: Forget the backstage chaos of data separation. With Azure Cosmos DB, data and vectors waltz together, reducing the complexity and overhead of AI application architectures. It's like having a **front-row seat** to the future. 3. **Vector Search Meets Query Filters**: Imagine a fusion of vector search and flexible query filters\u2014like a **dance-off** between precision and versatility. Whether you're solving mysteries or predicting trends, this combo has your back. 4. **Quick Starts and Cosmic Autoscale**: Azure Cosmos DB offers two modes: **serverless** (for those who want to dip their toes) and **provisioned throughput** (for the adrenaline junkies). It's like choosing between a leisurely stroll or a warp-speed jump to the stars. 5. **Production-Ready Brilliance**: With **5 levels of built-in multitenancy**, global replication, and SLAs that defy gravity (up to **99.999% availability**), Azure Cosmos DB is the **constellation** where dreams become reality. So, fellow cosmic voyager, buckle up! Azure Cosmos DB isn't just a database; it's a **cosmic odyssey** waiting for you to explore. \ud83c\udf0c\u2728\">\n<div class=\"ac-container ac-adaptiveCard has-image\">\n<div class=\"ac-textBlock\">\n<p>Azure Cosmos DB offers essential capabilities that, combined with DiskANN, make it the most powerful database for cutting-edge AI applications.<\/p>\n<ol>\n<li><strong>Mission-Critical Vector Store<\/strong>: Say goodbye to niche solutions! Our vector store delivers industry-leading similarity search performance, ensuring your critical workloads thrive.<\/li>\n<li><strong>No-ETL Simplicity<\/strong>: Keep data and vectors in harmony. By sidestepping ETL (Extract, Transform, Load) complexities, you\u2019ll streamline your AI application architecture keeping your data in one solution.<\/li>\n<li><strong>Flexible Query Filters<\/strong>: Seamlessly blend vector search with custom query filters to enhance the precision and relevancy of the vector search results.<\/li>\n<li><strong>Quick Start Options<\/strong>: Dive in swiftly and economically with Azure Cosmos DB\u2019s serverless mode. Alternatively, harness dynamic, instant Autoscale capabilities in provisioned throughput mode.<\/li>\n<li><strong>Production-Ready Excellence<\/strong>: With built-in multitenancy (offering five levels), global replication, and industry-leading SLAs, we guarantee up to\u00a0<strong>99.999% availability<\/strong>.<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<h2>Enroll in the Vector Search Preview<\/h2>\n<p>Developing AI applications with Azure Cosmos DB has never been easier. Here&#8217;s how to get started:<\/p>\n<p><strong>Step 1: <\/strong>Setup an Azure Cosmos DB for NoSQL resource in your Azure subscription.<\/p>\n<p><strong>Step 2: <\/strong>In the Azure Portal, navigate to your Azure Cosmos DB for NoSQL resource, select the \u201cFeatures\u201d tab, and then enroll in the \u201cVector Search for NoSQL API (preview)\u201d.<\/p>\n<p><a href=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview.png\"><img decoding=\"async\" class=\"aligncenter size-full wp-image-8666\" src=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview.png\" alt=\"Image VSpreview\" width=\"1712\" height=\"783\" srcset=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview.png 1712w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview-300x137.png 300w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview-1024x468.png 1024w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview-768x351.png 768w, https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-content\/uploads\/sites\/52\/2024\/09\/VSpreview-1536x703.png 1536w\" sizes=\"(max-width: 1712px) 100vw, 1712px\" \/><\/a><\/p>\n<p>And that&#8217;s it! You&#8217;re now setup to perform highly scalable and cost-effective vector search using DiskANN!<\/p>\n<h2>Next Steps<\/h2>\n<ul>\n<li>Learn more about <a href=\"https:\/\/learn.microsoft.com\/azure\/cosmos-db\/nosql\/vector-search\" target=\"_blank\" rel=\"noopener\">Vector Database capabilities in Azure Cosmos DB for NoSQL<\/a><\/li>\n<li>Read about <a href=\"https:\/\/devblogs.microsoft.com\/cosmosdb\/azure-cosmos-db-vector-search-with-diskann-part-1-full-space-search\/\" target=\"_blank\" rel=\"noopener\">DiskANN usage and performance\u00a0<\/a><\/li>\n<li>Check out the <a href=\"https:\/\/github.com\/AzureCosmosDB\/AISamples\">Azure Cosmos DB AI Samples GitHub repository<\/a> to get started quickly and easily!<\/li>\n<\/ul>\n<h2 id=\"about-azure-cosmos-db6\">About Azure Cosmos DB<button class=\"linkicon\" aria-label=\"Copy Post URL\"><\/button><\/h2>\n<p>Azure Cosmos DB is a fully managed and serverless distributed database for modern app development, with SLA-backed speed and availability, automatic and instant scalability, and support for open-source PostgreSQL, MongoDB, and Apache Cassandra.\u00a0<a href=\"https:\/\/cosmos.azure.com\/try\/\" target=\"_blank\" rel=\"noopener\">Try Azure Cosmos DB for free here.<\/a>\u00a0To stay in the loop on Azure Cosmos DB updates, follow us on\u00a0<a href=\"https:\/\/twitter.com\/AzureCosmosDB\" target=\"_blank\" rel=\"noopener\">X<\/a>,\u00a0<a href=\"https:\/\/aka.ms\/AzureCosmosDBYouTube\" target=\"_blank\" rel=\"noopener\">YouTube<\/a>, and\u00a0<a href=\"https:\/\/www.linkedin.com\/company\/azure-cosmos-db\/\" target=\"_blank\" rel=\"noopener\">LinkedIn<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We\u2019re 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. [&hellip;]<\/p>\n","protected":false},"author":118435,"featured_media":8673,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1610,14],"tags":[499,1917,1872,1866,1867,1868],"class_list":["post-8672","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","category-core-sql-api","tag-azure-cosmos-db","tag-diskann","tag-nosql","tag-vector-database","tag-vector-db","tag-vector-search"],"acf":[],"blog_post_summary":"<p>We\u2019re 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. [&hellip;]<\/p>\n","_links":{"self":[{"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/posts\/8672","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/users\/118435"}],"replies":[{"embeddable":true,"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/comments?post=8672"}],"version-history":[{"count":0,"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/posts\/8672\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/media\/8673"}],"wp:attachment":[{"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/media?parent=8672"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/categories?post=8672"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devblogs.microsoft.com\/cosmosdb\/wp-json\/wp\/v2\/tags?post=8672"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}