As performance infrastructure expands, so does the volume of data generated. This can make the review process challenging. Discover how the YugabyteDB performance team addressed this issue by building two AI-driven systems, one focused on regression detection and the other on making performance knowledge easier to query and share.
Read this blog (and the related book) to gain a deep, practical understanding of vector databases, their significance in the AI era, and when they are not applicable. Learn why YugabyteDB is an ideal choice for Vector search and AI workloads, and how vector stores, complete vector databases, and hybrid systems compare, plus how you can model, index, query, scale, and operate vector and relational workloads together.
Thanks to this new integration, you can turn Visual Studio (VS) Code into a fully-fledged MCP client for your YugabyteDB database. This blog guides you through using VS Code as the MCP client and connecting it to the YugabyteDB MCP Server. It also details how you can explore the YugabyteDB database via natural-language prompts.
AI doesn’t change the importance of data, it simply exposes weaknesses faster and at a much larger scale. If you’re building or modernizing AI-driven systems, the database you choose matters more than ever. Download our new white paper to discover what to look for in a next-generation data platform and how YugabyteDB meets those demands.
YugabyteDB is officially supported in Google’s MCP Toolbox for Databases, making it easier for you to build production AI agents with confidence. Discover how developers can access YugabyteDB’s distributed SQL capabilities, including load balancing, topology-aware routing, and data sovereignty controls, as documented and tested configuration options rather than custom workarounds.
Data migration is more than a technical exercise; it’s a strategic initiative that enables your business to evolve. By understanding the three major migration approaches (big‑bang, phased/trickle, and hybrid), the types of migration you may undertake, and the stages involved in a migration project, you can make the right choices to ensure business success.
Scaling to billions of vectors doesn’t require new systems or trade-offs, just YugabyteDB’s distributed PostgreSQL solution delivering simplicity, performance, and developer familiarity. We have successfully benchmarked YugabyteDB’s vector index performance with the Deep1B dataset, running a staggering one billion vectors. In this blog, we explore why scalable vector indexes are essential, share the benchmark results, and highlight the advantages of unifying vector and relational data in a single store.
Online retail shopping reached a new all-time high in 2024, and records are expected to be smashed again this year. At the heart of every retail application is data. For many retailers, database modernization is essential for both survival and success. This blog examines the 2024 holiday shopping season, what we can learn from it, and how your database impacts performance and customer experiences. It also shares top strategies to deliver a successful 2025 shopping experience.
Discover how you can integrate YugabyteDB’s Retail Analytics sample dataset with an MCP server (Google’s MCP Toolbox for Databases). We demonstrate how to define simple SQL tools using tools.yaml and illustrate how an Agent Development Kit (ADK) agent can discover and utilize these tools. All necessary files and a minimal ADK Python agent are provided, ready for you to copy, paste, and run locally!
Thanks to the pgvector PostgreSQL extension, YugabyteDB functions as a highly performant vector database. Its scalability allows it to store and search billions of vectors. This blog starts by detailing why a vector database is essential to agentic AI and how YugabyteDB meets key requirements for global organizations, including data sovereignty and zero-downtime. In the second part, we demonstrate how you can easily leverage this technology to provide AI with your organization’s information using n8n, a no-code orchestration tool.
