Skip to main content

Astra 数据库

¥Astra DB

Compatibility

仅在 Node.js 上可用。

¥Only available on Node.js.

DataStax Astra 数据库 是一个基于 Apache Cassandra 构建的无服务器向量数据库，可通过易于使用的 JSON API 轻松访问。

¥DataStax Astra DB is a serverless vector-capable database built on Apache Cassandra and made conveniently available through an easy-to-use JSON API.

设置​

¥Setup

  1. 创建一个 Astra DB 账户。

    ¥Create an Astra DB account.

  2. 创建一个 支持向量的数据库。

    ¥Create a vector enabled database.

  3. 从数据库详细信息中获取你的 API Endpoint 和 Token。

    ¥Grab your API Endpoint and Token from the Database Details.

  4. 设置以下环境变量：

    ¥Set up the following env vars:

export ASTRA_DB_APPLICATION_TOKEN=YOUR_ASTRA_DB_APPLICATION_TOKEN_HERE
export ASTRA_DB_ENDPOINT=YOUR_ASTRA_DB_ENDPOINT_HERE
export ASTRA_DB_COLLECTION=YOUR_ASTRA_DB_COLLECTION_HERE
export OPENAI_API_KEY=YOUR_OPENAI_API_KEY_HERE

其中 ASTRA_DB_COLLECTION 是你想要的集合名称

¥Where ASTRA_DB_COLLECTION is the desired name of your collection

  1. 安装 Astra TS 客户端和 LangChain 社区包

    ¥Install the Astra TS Client & the LangChain community package

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 @langchain/openai @datastax/astra-db-ts @langchain/community @langchain/core

索引文档​

¥Indexing docs

import { OpenAIEmbeddings } from "@langchain/openai";
import {
  AstraDBVectorStore,
  AstraLibArgs,
} from "@langchain/community/vectorstores/astradb";

const astraConfig: AstraLibArgs = {
  token: process.env.ASTRA_DB_APPLICATION_TOKEN as string,
  endpoint: process.env.ASTRA_DB_ENDPOINT as string,
  collection: process.env.ASTRA_DB_COLLECTION ?? "langchain_test",
  collectionOptions: {
    vector: {
      dimension: 1536,
      metric: "cosine",
    },
  },
};

const vectorStore = await AstraDBVectorStore.fromTexts(
  [
    "AstraDB is built on Apache Cassandra",
    "AstraDB is a NoSQL DB",
    "AstraDB supports vector search",
  ],
  [{ foo: "foo" }, { foo: "bar" }, { foo: "baz" }],
  new OpenAIEmbeddings(),
  astraConfig
);

// Querying docs:
const results = await vectorStore.similaritySearch("Cassandra", 1);

// or filtered query:
const filteredQueryResults = await vectorStore.similaritySearch("A", 1, {
  foo: "bar",
});

API Reference:

向量类型​

¥Vector Types

Astra DB 支持 cosine（默认）、dot_product 和 euclidean 相似性搜索；这在向量存储首次创建时作为 CreateCollectionOptions 的一部分进行定义：

¥Astra DB supports cosine (the default), dot_product, and euclidean similarity search; this is defined when the vector store is first created as part of the CreateCollectionOptions:

  vector: {
      dimension: number;
      metric?: "cosine" | "euclidean" | "dot_product";
  };

¥Related