Build Complete AI Apps Fast with One Database to Serve Agent Context, Branching and Search

How do I store and query vector embeddings?

How do I integrate TiDB with LangChain?

How do I integrate TiDB with LlamaIndex?

How do I run hybrid search in TiDB?

How do I improve vector search performance?

Explore Real AI Use Cases

See how teams build end-to-end AI systems on TiDB, from data ingestion to intelligent user experiences.

AI-Powered Financial Insights

Building an AI-powered crypto ETF insight app with GPTs and TiDB Cloud Data Service.

Retrieval-Augmented Generation (RAG)

Building RAG applications with TiDB.

Agentic AI Systems

How to build an AI agent that builds full-stack apps.

AI-Ready Backends

Mastering TiDB Cloud Data Service: building a data-driven backend.

Real-Time Hybrid Architectures

Supercharge real-time applications with TiDB and DragonflyDB.

Get Hands-On with Vector Search

Store embeddings, run similarity search, and combine vector queries with SQL in one system.

Get Started with Vector Search (Python)

Get Started with Vector Search (SQL)

Integrate with AI Frameworks

Use TiDB as the data and retrieval layer in modern AI stacks.

Amazon Bedrock

Gemini

LangChain

LlamaIndex

Tune and Scale Vector Search

Use these when you need precise configuration or performance tuning.

Vector Search Data Types

Vector Data Operators