Showing results for AI - Azure Cosmos DB Blog

As AI-driven apps become more sophisticated, there's an increasing need for them to mimic collaborative problem solving - like a team of domain experts working together. Multi-agent apps offer exactly that: collections of specialized agents that cooperate to handle complex tasks. But to make them production-grade, you need more than just clever pro...

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...

We’re announcing new integrations between Azure Cosmos DB and the Azure AI ecosystem: the Azure AI Foundry Connection for Azure Cosmos DB and bring-your-own thread storage in Azure AI Agent Service. These capabilities make it easier for developers to build enterprise-ready agentic applications using their own data stored in Azure Cosmos DB. Azure ...

Microsoft Build is less than a week away, and the Azure Cosmos DB team will be out in force to showcase the newest features and capabilities for building AI apps and agents with scalable, fast, high-performance data.  Whether you’re in person at the Seattle Convention Center or watching the live or on-demand digital show, we can’t wait to show ...

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 Azure Cosmos DB now includes Sharded DiskANN, a powerful capability that optimized for large-scale multitenant apps by splitting a DiskANN index into smaller, more performant pieces. When you specify a VectorIndexShardKey in your container’s indexing policy, Azure Cosmos DB creates multiple DiskANN indexes, one for each unique value o...

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...

This blog post covers how to build a chat history implementation using Azure Cosmos DB for NoSQL Go SDK and langchaingo. If you are new to the Go SDK, the sample chatbot application presented in the blog serves as a practical introduction, covering basic operations like read, upsert, etc. It also demonstrates using the Azure Cosmos DB Linux-based e...

This article is guest authored by Youssef Moussaoui, member of the technical staff, Microsoft Copilot. As part of the team developing Microsoft Copilot, we’re constantly looking for ways to improve the application and keep our millions of users engaged. With this in mind, we recently evaluated the structure of our backend and began looking for a...

Azure Cosmos DB was named by Bloomberg as the no. 1 Database of choice for Retrieval Augmented Generation (RAG) and Large Language Model (LLM) customization. It is used by OpenAI to scale it’s ChatGPT service, and by many thousands of customers worldwide, serving billions of end-users with globally distributed apps at planet scale. In this blog ...