Skip to main content

libSQL

Turso 是一个与 SQLite 兼容的数据库，构建于 libSQL（SQLite 的开放贡献分支）。向量相似性搜索作为原生数据类型内置于 Turso 和 libSQL 中，使你能够直接在数据库中存储和查询向量。

¥Turso is a SQLite-compatible database built on libSQL, the Open Contribution fork of SQLite. Vector Similiarity Search is built into Turso and libSQL as a native datatype, enabling you to store and query vectors directly in the database.

LangChain.js 支持使用本地 libSQL 或远程 Turso 数据库作为向量存储，并提供简单的 API 与其交互。

¥LangChain.js supports using a local libSQL, or remote Turso database as a vector store, and provides a simple API to interact with it.

本指南提供了 libSQL 向量存储入门的快速概述。有关 libSQL 所有功能和配置的详细文档，请参阅 API 参考。

¥This guide provides a quick overview for getting started with libSQL vector stores. For detailed documentation of all libSQL features and configurations head to the API reference.

概述​

¥Overview

集成详情​

¥Integration details

ClassPackagePY supportPackage latest
LibSQLVectorStore@langchain/community❌npm version

设置​

¥Setup

要使用 libSQL 向量存储，你需要创建一个 Turso 账户或设置一个本地 SQLite 数据库，并安装 @langchain/community 集成软件包。

¥To use libSQL vector stores, you'll need to create a Turso account or set up a local SQLite database, and install the @langchain/community integration package.

本指南还将使用 OpenAI 嵌入，这需要你安装 @langchain/openai 集成包。如果你愿意，还可以使用其他受支持的嵌入模型。

¥This guide will also use OpenAI embeddings, which require you to install the @langchain/openai integration package. You can also use other supported embeddings models if you wish.

你可以在使用 libSQL 矢量存储时使用本地 SQLite，也可以使用托管的 Turso 数据库。

¥You can use local SQLite when working with the libSQL vector store, or use a hosted Turso Database.

tip

请参阅 此部分包含有关安装集成包的一般说明。

¥See this section for general instructions on installing integration packages.

npm install @libsql/client @langchain/openai @langchain/community

现在是时候创建数据库了。你可以在本地创建一个，也可以使用托管的 Turso 数据库。

¥Now it's time to create a database. You can create one locally, or use a hosted Turso database.

本地 libSQL​

¥Local libSQL

创建一个新的本地 SQLite 文件并连接到 shell：

¥Create a new local SQLite file and connect to the shell:

sqlite3 file.db

托管的 Turso​

¥Hosted Turso

访问 sqlite.new 创建新数据库、为其命名并创建数据库身份验证令牌。

¥Visit sqlite.new to create a new database, give it a name, and create a database auth token.

确保复制数据库身份验证令牌和数据库 URL，其内容应类似于：

¥Make sure to copy the database auth token, and the database URL, it should look something like:

libsql://[database-name]-[your-username].turso.io

设置表和索引​

¥Setup the table and index

执行以下 SQL 命令创建新表或将嵌入列添加到现有表。

¥Execute the following SQL command to create a new table or add the embedding column to an existing table.

确保修改 SQL 的以下部分：

¥Make sure to modify the following parts of the SQL:

  • TABLE_NAME 是你要创建的表的名称。

    ¥TABLE_NAME is the name of the table you want to create.

  • content 用于存储 Document.pageContent 值。

    ¥content is used to store the Document.pageContent values.

  • metadata 用于存储 Document.metadata 对象。

    ¥metadata is used to store the Document.metadata object.

  • EMBEDDING_COLUMN 用于存储向量值，请使用你计划使用的模型的维度大小（OpenAI 为 1536）。

    ¥EMBEDDING_COLUMN is used to store the vector values, use the dimensions size used by the model you plan to use (1536 for OpenAI).

CREATE TABLE IF NOT EXISTS TABLE_NAME (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    content TEXT,
    metadata TEXT,
    EMBEDDING_COLUMN F32_BLOB(1536) -- 1536-dimensional f32 vector for OpenAI
);

现在在 EMBEDDING_COLUMN 列上创建索引 - 索引名称很重要！：

¥Now create an index on the EMBEDDING_COLUMN column - the index name is important!:

CREATE INDEX IF NOT EXISTS idx_TABLE_NAME_EMBEDDING_COLUMN ON TABLE_NAME(libsql_vector_idx(EMBEDDING_COLUMN));

确保将 TABLE_NAME 和 EMBEDDING_COLUMN 替换为你在上一步中使用的值。

¥Make sure to replace the TABLE_NAME and EMBEDDING_COLUMN with the values you used in the previous step.

实例化​

¥Instantiation

要初始化新的 LibSQL 矢量存储，你需要在远程工作时提供数据库 URL 和 Auth Token，或者通过传递本地 SQLite 的文件名来初始化。

¥To initialize a new LibSQL vector store, you need to provide the database URL and Auth Token when working remotely, or by passing the filename for a local SQLite.

import { LibSQLVectorStore } from "@langchain/community/vectorstores/libsql";
import { OpenAIEmbeddings } from "@langchain/openai";
import { createClient } from "@libsql/client";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});

const libsqlClient = createClient({
  url: "libsql://[database-name]-[your-username].turso.io",
  authToken: "...",
});

// Local instantiation
// const libsqlClient = createClient({
//  url: "file:./dev.db",
// });

const vectorStore = new LibSQLVectorStore(embeddings, {
  db: libsqlClient,
  table: "TABLE_NAME",
  column: "EMBEDDING_COLUMN",
});

管理向量存储​

¥Manage vector store

将项目添加到向量存储​

¥Add items to vector store

import type { Document } from "@langchain/core/documents";

const documents: Document[] = [
  { pageContent: "Hello", metadata: { topic: "greeting" } },
  { pageContent: "Bye bye", metadata: { topic: "greeting" } },
];

await vectorStore.addDocuments(documents);

从向量存储中删除项目​

¥Delete items from vector store

await vectorStore.deleteDocuments({ ids: [1, 2] });

查询向量存储​

¥Query vector store

插入文档后，即可查询向量存储。

¥Once you have inserted the documents, you can query the vector store.

直接查询​

¥Query directly

执行简单的相似性搜索可以按如下方式完成：

¥Performing a simple similarity search can be done as follows:

const resultOne = await vectorStore.similaritySearch("hola", 1);

for (const doc of similaritySearchResults) {
  console.log(`${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}

对于关系数据库和图数据库，字段特定语言 (DSL) 用于查询数据。

¥For similarity search with scores:

const similaritySearchWithScoreResults =
  await vectorStore.similaritySearchWithScore("hola", 1);

for (const [doc, score] of similaritySearchWithScoreResults) {
  console.log(
    `${score.toFixed(3)} ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`
  );
}

API 参考​

¥API reference

有关 LibSQLVectorStore 所有功能和配置的详细文档，请参阅 API 参考。

¥For detailed documentation of all LibSQLVectorStore features and configurations head to the API reference.

¥Related