Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
168 changes: 84 additions & 84 deletions develop/dev-guide-sample-application-python-peewee.md

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion latest_translation_commit.json
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"target":"release-8.5","sha":"0205ededf901476ea31dcd603f21ab9c9bed3f0d"}
{"target":"release-8.5","sha":"6b3c0fadec1d62f44690ecaafa0ac03d762a2ba9"}
48 changes: 24 additions & 24 deletions tidb-cloud/ai-feature-concepts.md
Original file line number Diff line number Diff line change
@@ -1,50 +1,50 @@
---
title: AI Features
summary: Learn about AI features for TiDB Cloud.
summary: 了解 TiDB Cloud 的 AI 功能。
---

# AI Features
# AI 功能

The AI features in TiDB Cloud enable you to fully leverage advanced technologies for data exploration, search, and integration. From natural language-driven SQL query generation to high-performance vector search, TiDB combines database capabilities with modern AI features to power innovative applications. With support for popular AI frameworks, embedding models, and seamless integration with ORM libraries, TiDB offers a versatile platform for use cases such as semantic search and AI-powered analytics.
TiDB Cloud 的 AI 功能让你能够充分利用先进技术进行数据探索、搜索和集成。从基于自然语言的 SQL 查询生成,到高性能的向量搜索,TiDB 将数据库能力与现代 AI 功能相结合,为创新应用提供强大动力。TiDB 支持主流 AI 框架、嵌入模型,并可与 ORM 库无缝集成,为语义搜索和 AI 驱动分析等场景提供了多样化的平台。

This document highlights these AI features and how they enhance the TiDB experience.
本文档将重点介绍这些 AI 功能,以及它们如何提升 TiDB 的使用体验。

## Chat2Query (Beta)
## Chat2QueryBeta

Chat2Query is an AI-powered feature integrated into SQL Editor that assists users in generating, debugging, or rewriting SQL queries using natural language instructions. For more information, see [Explore your data with AI-assisted SQL Editor](/tidb-cloud/explore-data-with-chat2query.md).
Chat2Query 是集成在 SQL Editor 中的 AI 驱动功能,能够帮助用户通过自然语言指令生成、调试或重写 SQL 查询。更多信息,参见 [Explore your data with AI-assisted SQL Editor](/tidb-cloud/explore-data-with-chat2query.md)

In addition, TiDB Cloud provides a Chat2Query API for TiDB Cloud Serverless clusters. After it is enabled, TiDB Cloud will automatically create a system Data App called Chat2Query and a Chat2Data endpoint in Data Service. You can call this endpoint to let AI generate and execute SQL statements by providing instructions. For more information, see [Get started with Chat2Query API](/tidb-cloud/use-chat2query-api.md).
此外,TiDB Cloud TiDB Cloud Serverless 集群提供了 Chat2Query API。启用后,TiDB Cloud 会自动创建一个名为 Chat2Query 的系统 Data App,以及一个 Data Service 中的 Chat2Data endpoint。你可以调用该 endpoint,通过提供指令让 AI 生成并执行 SQL 语句。更多信息,参见 [Get started with Chat2Query API](/tidb-cloud/use-chat2query-api.md)

## Vector search (Beta)
## 向量搜索(Beta

Vector search is a search method that prioritizes the meaning of your data to deliver relevant results.
向量搜索是一种以数据语义为核心、提供相关性结果的搜索方式。

Unlike traditional full-text search, which relies on exact keyword matching and word frequency, vector search converts various data types (such as text, images, or audio) into high-dimensional vectors and queries based on the similarity between these vectors. This search method captures the semantic meaning and contextual information of the data, leading to a more precise understanding of user intent.
与依赖精确关键词匹配和词频的传统全文搜索不同,向量搜索会将多种数据类型(如文本、图片或音频)转换为高维向量,并基于这些向量之间的相似度进行查询。这种搜索方式能够捕捉数据的语义含义和上下文信息,从而更准确地理解用户意图。

Even when the search terms do not exactly match the content in the database, vector search can still provide results that align with the user's intent by analyzing the semantics of the data. For example, a full-text search for "a swimming animal" only returns results containing these exact keywords. In contrast, vector search can return results for other swimming animals, such as fish or ducks, even if these results do not contain the exact keywords.
即使搜索词与数据库中的内容并不完全匹配,向量搜索也可以通过分析数据的语义,返回符合用户意图的结果。例如,全文搜索 “a swimming animal” 只会返回包含这些精确关键词的结果,而向量搜索则可以返回其他游泳动物(如鱼或鸭子)的结果,即使这些结果中并不包含完全相同的关键词。

For more information, see [Vector Search (Beta) Overview](/vector-search/vector-search-overview.md).
更多信息,参见 [Vector Search (Beta) Overview](/vector-search/vector-search-overview.md)

## AI integrations
## AI 集成

### AI frameworks
### AI 框架

TiDB provides official support for several popular AI frameworks, enabling you to easily integrate AI applications developed based on these frameworks with TiDB Vector Search.
TiDB 官方支持多种主流 AI 框架,使你能够轻松将基于这些框架开发的 AI 应用与 TiDB 向量搜索集成。

For a list of supported AI frameworks, see [Vector Search Integration Overview](/vector-search/vector-search-integration-overview.md#ai-frameworks).
支持的 AI 框架列表,参见 [Vector Search Integration Overview](/vector-search/vector-search-integration-overview.md#ai-frameworks)

### Embedding models and services
### 嵌入模型与服务

A vector embedding, also known as an embedding, is a sequence of numbers that represents real-world objects in a high-dimensional space. It captures the meaning and context of unstructured data, such as documents, images, audio, and videos.
向量嵌入(embedding),也称为嵌入,是一组数字序列,用于在高维空间中表示现实世界的对象。它能够捕捉非结构化数据(如文档、图片、音频和视频)的语义和上下文信息。

Embedding models are algorithms that transform data into [vector embeddings](/vector-search/vector-search-overview.md#vector-embedding). The choice of an appropriate embedding model is crucial for ensuring the accuracy and relevance of semantic search results.
嵌入模型是一类将数据转换为 [vector embeddings](/vector-search/vector-search-overview.md#vector-embedding) 的算法。选择合适的嵌入模型对于确保语义搜索结果的准确性和相关性至关重要。

TiDB Vector Search supports storing vectors of up to 16383 dimensions, which accommodates most embedding models. For unstructured text data, you can find top-performing text embedding models on the [Massive Text Embedding Benchmark (MTEB) Leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
TiDB 向量搜索支持存储最多 16383 维的向量,能够满足大多数嵌入模型的需求。对于非结构化文本数据,你可以在 [Massive Text Embedding Benchmark (MTEB) Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) 上找到表现最优的文本嵌入模型。

### Object Relational Mapping (ORM) libraries
### 对象关系映射(ORM)库

Object Relational Mapping (ORM) libraries are tools that facilitate the interaction between applications and relational databases by allowing developers to work with database records as if they were objects in their programming language of choice.
对象关系映射(ORM)库是一类工具,能够让开发者以所选编程语言中的对象方式操作数据库记录,从而简化应用与关系型数据库之间的交互。

TiDB lets you integrate vector search with ORM libraries to manage vector data alongside traditional relational data. This integration is particularly useful for applications that need to store and query vector embeddings generated by AI models. By using ORM libraries, developers can seamlessly interact with vector data stored in TiDB, leveraging the database's capabilities to perform complex vector operations like nearest neighbor search.
TiDB 支持将向量搜索与 ORM 库集成,实现对向量数据和传统关系数据的统一管理。这一集成对于需要存储和查询 AI 模型生成的向量嵌入的应用尤为有用。通过使用 ORM 库,开发者可以无缝操作存储在 TiDB 中的向量数据,利用数据库能力执行如最近邻搜索等复杂的向量操作。

For a list of supported ORM libraries, see [Vector Search Integration Overview](/vector-search/vector-search-integration-overview.md#object-relational-mapping-orm-libraries).
支持的 ORM 库列表,参见 [Vector Search Integration Overview](/vector-search/vector-search-integration-overview.md#object-relational-mapping-orm-libraries)
Loading