Skip to main content

OceanBase: Data + AI

OceanBase is a distributed, high-performance, and cloud-native database that supports both SQL and NoSQL data models. Since its 4.3.3 release, OceanBase has supported Vector storage and retrieval-augmented generation (RAG) capabilities. This page provides a comprehensive guide to using OceanBase for AI applications.

AI Workshops​

Since 2024-10-23, OceanBase has held several AI workshops in cities across China.

RAG Bot​

Project link: RAG Bot

In this workshop, attendees build a RAG chatbot that answers questions related to OceanBase documentation. It uses open-source OceanBase documentation repositories as multi-modal data sources, converting documents into vectors and structured data stored in OceanBase. When users ask questions, the chatbot converts their questions into vectors and performs vector retrieval in the database. By combining the retrieved document content with the user's questions, it leverages Tongyi Qianwen's large language model capabilities to provide more accurate answers.

Events:

  • Event in Beijing, China on 2024-10-23
  • Event in Guangzhou, China on 2024-11-23

Dify (MySQL Compatible)​

Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. We have patched Dify to be compatible with MySQL protocol databases, including OceanBase. With OceanBase, Dify can store and query structured data and vector data in, just one unified database, a OceanBase instance.

Project link: Dify

Events:

  • Event in Shanghai, China on 2024-12-07

DB-GPT​

DB-GPT is an AI native data app development framework with AWEL(Agentic Workflow Expression Language) and agents.

Project link: DB-GPT

Events:

  • Event in Chengdu, China on 2024-12-21