new nav: add ai docs and update toc by shizn · Pull Request #22384 · pingcap/docs

shizn · 2026-01-30T06:33:01Z

What is changed, added or deleted? (Required)

This PR consolidates the docs from https://pingcap.github.io/ai/quickstart/ to the AI doc set.

Which TiDB version(s) do your changes apply to? (Required)

Tips for choosing the affected version(s):

By default, CHOOSE MASTER ONLY so your changes will be applied to the next TiDB major or minor releases. If your PR involves a product feature behavior change or a compatibility change, CHOOSE THE AFFECTED RELEASE BRANCH(ES) AND MASTER.

For details, see tips for choosing the affected versions.

What is the related PR or file link(s)?

This PR is translated from:
Other reference link(s):

Do your changes match any of the following descriptions?

Delete files
Change aliases
Need modification after applied to another branch
Might cause conflicts after applied to another branch

gemini-code-assist · 2026-01-30T06:34:52Z

Summary of Changes

Hello @shizn, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request delivers a substantial overhaul and expansion of the documentation related to TiDB's AI features. The changes aim to provide a more structured, comprehensive, and user-friendly resource for developers looking to build AI-powered applications with TiDB. The focus is on practical guidance, diverse examples, and broad integration support to streamline the development process.

Highlights

Documentation Restructuring: The entire 'ai' documentation section has been significantly reorganized into logical subdirectories: 'concepts', 'guides', 'examples', 'integrations', and 'reference'. This improves navigability and clarity for users exploring TiDB's AI capabilities.
Comprehensive Table of Contents: The main AI landing page (ai/_index.md) now features a detailed Table of Contents, providing a quick overview and direct links to all major sections, including getting started, core concepts, practical guides, examples, and various integrations.
New Guides and Examples: A large number of new documentation pages have been added, covering detailed guides for features like auto embedding, filtering, join queries, raw SQL, reranking, table operations, and transactions. New examples demonstrate basic CRUD, auto embedding, full-text search, hybrid search, image search, RAG applications, conversational memory, Text2SQL, and vector search using PyTiDB.
Expanded Integrations: New integration guides have been introduced for various embedding providers (Cohere, Google Gemini, Hugging Face, Jina AI, NVIDIA NIM, OpenAI, OpenAI-compatible, TiDB Cloud Hosted) and AI frameworks (LangChain, LlamaIndex). Additionally, documentation for the TiDB Model Context Protocol (MCP) Server and its integration with tools like Claude Code, Claude Desktop, Cursor, VS Code, and Windsurf has been added.
Updated AI Overview and Quickstart: The primary AI overview page (ai/index.md) has been updated to reflect TiDB's role in modern AI applications, emphasizing integrated vector search, full-text search, and a seamless Python SDK. A new quickstart guide (ai/quickstart.md) helps users rapidly get started with TiDB's AI features using the Python SDK.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request significantly restructures and expands the "TiDB for AI" documentation, introducing a new table of contents, a demo gallery, and numerous guides and examples. The changes are well-organized and make the documentation much more comprehensive. My review includes suggestions for improving clarity, correcting minor typos and grammatical errors, and ensuring consistency across the new documents, in line with the repository's documentation style guide.

gemini-code-assist · 2026-01-30T06:38:28Z

ai/integrations/llamaindex.md

+
+```python
+tidbvec = TiDBVectorStore(
+   connection_string=tidb_connection_url,


The variable tidb_connection_url is not defined in the preceding code. It should be tidb_connection_string to match the variable defined earlier in the document.

Suggested change

connection_string=tidb_connection_url,

connection_string=tidb_connection_string,

gemini-code-assist · 2026-01-30T06:38:29Z

ai/guides/tables.md

+    ```python
+    table.update(
+        values={
+            "content": "TiDB Cloud Starter is a fully managed, auto-scaling cloud database service"


This line is missing a comma at the end, which will cause a syntax error in the Python dictionary. Adding the comma will fix the code example.

Suggested change

"content": "TiDB Cloud Starter is a fully managed, auto-scaling cloud database service"

"content": "TiDB Cloud Starter is a fully managed, auto-scaling cloud database service",

gemini-code-assist · 2026-01-30T06:38:29Z

ai/guides/fulltext-search.md

+        (7, 'Bluetooth5.3ヘッドホン ノイズキャンセリング 没入サウンド 快適装着'),
+        (8, 'IPX7防水イヤホン スポーツ対応 タッチ操作 高音質音楽'),
+        (9, 'スポーツイヤホン 安定装着 防汗 長持ちバッテリー ワークアウト対応'),
+        (10, '有线ヘッドホン スタジオ级 HDサウンド 快适装着 プロ音楽体験'),


There is a typo in the Japanese text. 快适装着 should be 快適装着.

Suggested change

(10, '有线ヘッドホンスタジオ级 HDサウンド快适装着プロ音楽体験'),

Item(id=10, title="有線ヘッドホンスタジオ級 HDサウンド快適装着プロ音楽体験"),

ai/integrations/embedding-openai-compatible.md

gemini-code-assist · 2026-01-30T06:38:29Z

ai/integrations/embedding-overview.md

+- [OpenAI](embedding-openai.md)
+- [OpenAI Compatible](embedding-openai-compatible.md) 
+- [Cohere](embedding-cohere.md)
+- [Jina AI](embedding-jinaai.md)


There is a typo in the link filename. It should be embedding-jina-ai.md.

Suggested change

- [Jina AI](embedding-jinaai.md)

- [Jina AI](embedding-jina-ai.md)

gemini-code-assist · 2026-01-30T06:38:29Z

ai/integrations/embedding-tidb-cloud-hosted.md

+
+!!! info
+
+    `tidbcloud_free` prefix models is not required to configure the API key.


Grammatical correction for subject-verb agreement.

Suggested change

`tidbcloud_free` prefix models is not required to configure the API key.

`tidbcloud_free` prefix models do not require you to configure an API key.

gemini-code-assist · 2026-01-30T06:38:29Z

ai/integrations/langchain.md

+
+### Step 5. Embed and store document vectors
+
+TiDB vector store supports both cosine distance (`consine`) and Euclidean distance (`l2`) for measuring similarity between vectors. The default strategy is cosine distance.


There is a typo in consine. It should be cosine.

Suggested change

TiDB vector store supports both cosine distance (`consine`) and Euclidean distance (`l2`) for measuring similarity between vectors. The default strategy is cosine distance.

TiDB vector store supports both cosine distance (`cosine`) and Euclidean distance (`l2`) for measuring similarity between vectors. The default strategy is cosine distance.

gemini-code-assist · 2026-01-30T06:38:30Z

ai/integrations/langchain.md

+```python
+search_query = f"""
+    SELECT
+        VEC_Cosine_Distance(se.embedding, :query_vector) as distance,


The SQL function name should be in uppercase to be consistent with SQL standards and other parts of the documentation.

Suggested change

VEC_Cosine_Distance(se.embedding, :query_vector) as distance,

VEC_COSINE_DISTANCE(se.embedding, :query_vector) as distance,

ai/examples/auto-embedding-with-pytidb.md

ai/integrations/tidb-mcp-server.md

… updated Markdown syntax

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

…hizn/docs into pr/22384

ti-chi-bot · 2026-02-02T03:21:21Z

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please ask for approval from qiancai. For more information see the Code Review Process.
Please ensure that each of them provides their approval before proceeding.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

ai/_index.md

…hizn/docs into pr/22384

ti-chi-bot · 2026-02-02T07:14:31Z

@shizn: The following test failed, say /retest to rerun all failed tests or /retest-required to rerun all mandatory failed tests:

Test name	Commit	Details	Required	Rerun command
pull-verify	`a800d6f`	link	true	`/test pull-verify`

Full PR test history. Your PR dashboard.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here.

ti-chi-bot · 2026-02-02T08:36:43Z

[LGTM Timeline notifier]

Timeline:

2026-02-02 08:36:43.080559277 +0000 UTC m=+83274.181957974: ☑️ agreed by qiancai.

Update ai content and add toc

64d3f42

ti-chi-bot bot added missing-translation-status This PR does not have translation status info. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files. labels Jan 30, 2026

gemini-code-assist bot reviewed Jan 30, 2026

View reviewed changes

shizn and others added 2 commits January 29, 2026 23:00

fix

ddf0188

consolidated content for auto embedding, removed duplicated docs, and…

60b8cc9

… updated Markdown syntax

qiancai force-pushed the feature/preview-top-navigation branch from 34b5b17 to 60b8cc9 Compare January 31, 2026 01:12

qiancai and others added 6 commits January 31, 2026 09:17

Apply suggestions from code review

e3ad131

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

add missing empty lines

7a0638b

add groupID for SimpleTab

272ce0a

fix the format issue of notes

7c75907

Merge branch 'feature/preview-top-navigation' of https://github.com/s…

c6baa31

…hizn/docs into pr/22384

move chat2query andsql-proxy-account doc back to tidb-cloud

a0b7af1

qiancai added area/tidb-cloud This PR relates to the area of TiDB Cloud. and removed area/tidb-cloud This PR relates to the area of TiDB Cloud. labels Feb 2, 2026

qiancai self-assigned this Feb 2, 2026

qiancai added type/refactor The issue belongs to a refactor work. translation/no-need No need to translate this PR. and removed missing-translation-status This PR does not have translation status info. labels Feb 2, 2026

Update TOC-ai.md

d86769f

qiancai reviewed Feb 2, 2026

View reviewed changes

ai/_index.md Outdated Show resolved Hide resolved

qiancai added 5 commits February 2, 2026 11:31

Update ai/_index.md

2928093

implement comments from gemini

432aa21

Merge branch 'feature/preview-top-navigation' of https://github.com/s…

78815c9

…hizn/docs into pr/22384

rename the two quick start guides

a0a7f4c

fix broken links caused by file directory changes

6441f7c

ti-chi-bot bot added the area/develop This PR relates to the area of TiDB App development. label Feb 2, 2026

Update dev-guide-vector-search.md

a800d6f

qiancai approved these changes Feb 2, 2026

View reviewed changes

ti-chi-bot bot added the needs-1-more-lgtm Indicates a PR needs 1 more LGTM. label Feb 2, 2026

qiancai changed the title ~~Update ai content and add toc~~ new nav: add ai docs and update toc Feb 2, 2026

qiancai merged commit b1d964c into pingcap:feature/preview-top-navigation Feb 2, 2026
4 of 9 checks passed

	connection_string=tidb_connection_url,
	connection_string=tidb_connection_string,

	"content": "TiDB Cloud Starter is a fully managed, auto-scaling cloud database service"
	"content": "TiDB Cloud Starter is a fully managed, auto-scaling cloud database service",

	(10, '有线ヘッドホンスタジオ级 HDサウンド快适装着プロ音楽体験'),
	Item(id=10, title="有線ヘッドホンスタジオ級 HDサウンド快適装着プロ音楽体験"),

	- [Jina AI](embedding-jinaai.md)
	- [Jina AI](embedding-jina-ai.md)


		!!! info

		`tidbcloud_free` prefix models is not required to configure the API key.

	`tidbcloud_free` prefix models is not required to configure the API key.
	`tidbcloud_free` prefix models do not require you to configure an API key.


		### Step 5. Embed and store document vectors

		TiDB vector store supports both cosine distance (`consine`) and Euclidean distance (`l2`) for measuring similarity between vectors. The default strategy is cosine distance.

	VEC_Cosine_Distance(se.embedding, :query_vector) as distance,
	VEC_COSINE_DISTANCE(se.embedding, :query_vector) as distance,

Conversation

shizn commented Jan 30, 2026 • edited by qiancai Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What is changed, added or deleted? (Required)

Which TiDB version(s) do your changes apply to? (Required)

What is the related PR or file link(s)?

Do your changes match any of the following descriptions?

Uh oh!

gemini-code-assist bot commented Jan 30, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Jan 30, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

ti-chi-bot bot commented Feb 2, 2026

Uh oh!

Uh oh!

ti-chi-bot bot commented Feb 2, 2026

Uh oh!

ti-chi-bot bot commented Feb 2, 2026

[LGTM Timeline notifier]

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

shizn commented Jan 30, 2026 •

edited by qiancai

Loading