As an open-source, distributed SQL database built on top of PostgreSQL, YugabyteDB is committed to maintaining deep compatibility with the PostgreSQL ecosystem. In this blog, we share our approach to aligning YugabyteDB with the latest PostgreSQL versions, the challenges we face, and our future plans to narrow the compatibility gap.
Modern organizations use a variety of databases to manage information. As AI and machine learning models continue to grow in popularity, a new category has emerged: vector databases. This blog provides a clear definition of vector databases and answers key questions about how they work, how they differ from regular databases, and when you should use them for your AI and ML projects.
In this post, we walk through how to build a RAG pipeline using YugabyteDB’s new vector capabilities to enable smarter and more context-aware support automation. Discover how to ingest internal documents, vectorize them, store them efficiently in YugabyteDB, and finally how to use an LLM like GPT-4 to answer internal questions—rooted in your own support stack data.
The AI app-building landscape is evolving rapidly – you’ll soon be able to quickly build robust AI applications that scale from thousands to billions of vectors using familiar PostgreSQL and powerful vector search capabilities, without architectural changes. In this blog, we examine the current and future AI landscape and share the benefits of the new and enhanced AI functionality introduced in the latest YugabyteDB release.
Imagine a database that allows you to recover that critical row you deleted in production, and lets you test schema changes on real data without risking the original. Discover how YugabyteDB’s point-in-time capabilities, including point-in-time recovery, instant database cloning, and time travel queries, make it easy to rewind your data, spin up lightweight clones, and explore historical states with precision.
The YugabyteDB MCP Server brings your AI stack and your operational data into the same conversation. Easily accessible on AWS Marketplace, teams can now skip time-consuming procurement processes and deploy the YugabyteDB MCP Server in just a few minutes. Find out more.
Traditional architectures, particularly those using single-node or application-level sharding, are prone to failure and offer limited availability. In this blog, we consider two architecture options for scaling a database horizontally and employ probability theory to assess the resilience of each architecture to potential failure.
Discover how to build Agentic AI workflows using tools like n8n, YugabyteDB, and LangChain. By seamlessly integrating YugabyteDB’s vector embedding capabilities, OpenAI models, and n8n workflow orchestration, businesses can develop robust and scalable AI solutions that deliver real value.
The YugabyteDB MCP Server is a new, lightweight, Python-based server that allows LLMs like Anthropic’s Claude to interact directly with your YugabyteDB database. In this blog we demonstrate how MCP allows an AI application to access, query, analyze, and interpret data in your YugabyteDB database, using only natural language prompts.
As vector search becomes foundational to modern AI workloads, databases must rethink how their architecture handles high-dimensional vector data at scale. This blog reveals how YugabyteDB integrates a distributed vector indexing engine powered by USearch to deliver a fast, scalable, and resilient vector search natively with a Postgres-compatible SQL interface.
