TiDB for AI

TiDB is a distributed SQL database designed for modern AI applications, offering integrated vector search, full-text search, and hybrid search capabilities. This document provides an overview of the AI features and tools available for building AI-powered applications with TiDB.

Quick start

Get up and running quickly with TiDB's AI capabilities.

Document	Description
Get Started with Python	Build your first AI application with TiDB in minutes using Python.
Get Started with SQL	Quick start guide for vector search using SQL.

Concepts

Understand the foundational concepts behind AI-powered search in TiDB.

Document	Description
Vector Search	Comprehensive overview of vector search, including concepts, how it works, and use cases.

Guides

Step-by-step guides for building AI applications with TiDB using the pytidb SDK or SQL.

Document	Description
Connect to TiDB	Connect to TiDB Cloud or TiDB Self-Managed using `pytidb`.
Working with Tables	Create, query, and manage tables with vector fields.
Vector Search	Perform semantic similarity searches using `pytidb`.
Full-Text Search	Keyword-based text search with BM25 ranking.
Hybrid Search	Combine vector and full-text search for better results.
Image Search	Search images using multimodal embeddings.
Auto Embedding	Automatically generate embeddings on data insertion.
Filtering	Filter search results with metadata conditions.

Examples

Complete code examples and demos showcasing TiDB's AI capabilities.

Document	Description
Basic CRUD Operations	Fundamental table operations with `pytidb`.
Vector Search	Semantic similarity search example.
RAG Application	Build a Retrieval-Augmented Generation application.
Image Search	Multimodal image search with Jina AI embeddings.
Conversational Memory	Persistent memory for AI agents and chatbots.
Text-to-SQL	Convert natural language to SQL queries.

Integrations

Integrate TiDB with popular AI frameworks, embedding providers, and development tools.

Document	Description
Integration Overview	Overview of all available integrations.
Embedding Providers	Unified interface for OpenAI, Cohere, Jina AI, and more.
LangChain	Use TiDB as a vector store with LangChain.
LlamaIndex	Use TiDB as a vector store with LlamaIndex.
MCP Server	Connect TiDB to Claude Code, Cursor, and other AI-powered IDEs.

Reference

Technical reference documentation for TiDB's AI and vector search features.

Document	Description
Vector Data Types	Vector column types and usage.
Functions and Operators	Distance functions and vector operations.
Vector Search Index	Create and manage vector indexes for performance.
Performance Tuning	Optimize vector search performance.
Limitations	Current limitations and constraints.