📣

TiDB Cloud Premium is now in public preview. Unlimited growth, instant elasticity, advanced security for enterprise workloads. Try it out →

TiDB for AI

TiDB provides data and workspace capabilities for building AI applications and running AI agent workflows.

For application development, you can use SQL or Python SDK for TiDB AI (pytidb) with structured data, vector search, full-text search, hybrid search, and AI-powered retrieval.
For AI agents and automation, you can use TiDB Cloud CLI (ti) to manage TiDB Cloud Starter instances and SQL workflows, and use TiDB Cloud Filesystems as persistent, shared storage across local machines, CI jobs, and ephemeral agent sandboxes. Filesystems also support mounted workspaces, Git workflows, journals, and delegated secrets.

Get started

Choose a path based on what you want to build:

Goal	Start here
Build an AI application with vector search	Get Started with Vector Search via Python or Get Started with Vector Search via SQL
Build agent and automation workflows with TiDB Cloud	Get Started with TiDB Cloud CLI

Build AI applications with TiDB

Use the pytidb SDK or SQL to connect to TiDB, search and retrieve data, and build AI-powered applications.

Connect to TiDB

Document	Description
Connect to TiDB via Python	Connect to TiDB Cloud or TiDB Self-Managed using `pytidb`.

Search & retrieval

Vector search

Document	Description
Vector Search Overview	Comprehensive overview of vector search, including concepts, how it works, and use cases.
Vector Search Guide	Perform semantic similarity searches using `pytidb`.
Vector Search Example	Semantic similarity search example with `pytidb`.

Full-text search

Document	Description
Full-Text Search via Python	Keyword-based text search with BM25 ranking using `pytidb`.
Full-Text Search via SQL	Keyword-based text search with BM25 ranking using SQL.
Full-Text Search Example	Full-text search example with `pytidb`.

Hybrid search

Document	Description
Hybrid Search Guide	Combine vector and full-text search for better results.
Hybrid Search Example	Hybrid search example with `pytidb`.

Auto embeddings

Document	Description
Auto Embedding Guide	Automatically generate embeddings on data insertion.
Auto Embedding Example	Auto embedding example with `pytidb`.

Image search

Document	Description
Image Search Guide	Search images using multimodal embeddings.
Image Search Example	Multimodal image search example with Jina AI embeddings.

Reranking

Document	Description
Reranking	Rerank search results for improved relevance.

Work with data

Document	Description
Working with Tables	Create, query, and manage tables with vector fields.
Filtering	Filter search results with metadata conditions.
Join Queries	Perform join queries across tables.
Raw SQL Queries	Execute raw SQL queries directly.
Transactions	Use transactions for data consistency.

Application examples

Document	Description
RAG Example	Build a Retrieval-Augmented Generation application.
Conversational Memory Example	Persistent memory for AI agents and chatbots.
Text-to-SQL Example	Convert natural language to SQL queries.

Build agent and automation workflows with TiDB Cloud CLI

The TiDB Cloud CLI (ti) lets users, scripts, CI jobs, and AI agents manage TiDB Cloud from a terminal. Use it to automate TiDB Cloud Starter and SQL operations or to keep files and workspaces available independently of the machines and sandboxes that use them.

What you want to do	Start here
Understand what `ti` manages and when to use it	TiDB Cloud CLI Overview
Install and configure `ti`, then complete a first workflow	Get Started with TiDB Cloud CLI
Automate TiDB Cloud Starter instance, branch, and SQL operations	Manage TiDB Cloud Starter Instances
Persist and share files across machines, CI jobs, and sandboxes	Manage Filesystem Resources and Work with Filesystem Data
Use mounted workspaces, Git workspaces, journals, or delegated secrets	Mount a Filesystem, Manage Git Workspaces, Use Filesystem Journals, and Manage Filesystem Vault Secrets
Follow an end-to-end automation or agent example	Run a Daily TiDB Cloud CLI Workflow or Use TiDB Cloud Filesystem in an Agent Sandbox
Look up commands, global options, output behavior, and errors	TiDB Cloud CLI Command Reference

Integrations

Connect TiDB to embedding providers, AI frameworks, application libraries, cloud services, and AI development tools.

Integration area	Start here
All integrations	AI Integrations for TiDB
Auto Embedding providers	Auto Embedding Overview
AI frameworks	LlamaIndex
ORM libraries	SQLAlchemy, Django ORM, and Peewee
Cloud embedding services	Jina AI Embedding and Amazon Bedrock
MCP clients and AI development tools	TiDB MCP Server

Reference

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

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