Skip to main content

​
概述

向量存储 存储 嵌入 数据并执行相似性搜索。

​
接口

LangChain 为向量存储提供了统一的接口，允许您：
  • addDocuments - 向存储中添加文档。
  • delete - 按 ID 删除存储的文档。
  • similaritySearch - 查询语义相似的文档。
这种抽象使您可以在不同实现之间切换，而无需更改应用程序逻辑。

​
初始化

LangChain 中的大多数向量存储在初始化时接受一个嵌入模型作为参数。 
import { OpenAIEmbeddings } from "@langchain/openai";
import { MemoryVectorStore } from "@langchain/classic/vectorstores/memory";

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

​
添加文档

您可以使用 addDocuments 函数向向量存储添加文档。 
import { Document } from "@langchain/core/documents";
const document = new Document({
  pageContent: "Hello world",
});
await vectorStore.addDocuments([document]);

​
删除文档

您可以使用 delete 函数从向量存储中删除文档。 
await vectorStore.delete({
  filter: {
    pageContent: "Hello world",
  },
});

​
相似性搜索

使用 similaritySearch 发出语义查询，返回最接近的嵌入文档： 
const results = await vectorStore.similaritySearch("Hello world", 10);
许多向量存储支持以下参数：
  • k — 要返回的结果数量
  • filter — 基于元数据的条件过滤

​
相似性度量与索引

嵌入相似性可以使用以下方法计算：
  • 余弦相似度
  • 欧几里得距离
  • 点积
高效搜索通常使用索引方法，如 HNSW（分层可导航小世界），但具体细节取决于向量存储。

​
元数据过滤

通过元数据（例如来源、日期）进行过滤可以优化搜索结果： 
vectorStore.similaritySearch("query", 2, { source: "tweets" });

​
主要集成

选择嵌入模型：
安装依赖项：
npm i @langchain/openai
添加环境变量：
OPENAI_API_KEY=your-api-key
实例化模型：
import { OpenAIEmbeddings } from "@langchain/openai";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-large"
});
安装依赖项
npm i @langchain/openai
添加环境变量：
AZURE_OPENAI_API_INSTANCE_NAME=<YOUR_INSTANCE_NAME>
AZURE_OPENAI_API_KEY=<YOUR_KEY>
AZURE_OPENAI_API_VERSION="2024-02-01"
实例化模型：
import { AzureOpenAIEmbeddings } from "@langchain/openai";

const embeddings = new AzureOpenAIEmbeddings({
  azureOpenAIApiEmbeddingsDeploymentName: "text-embedding-ada-002"
});
安装依赖项：
npm i @langchain/aws
添加环境变量：
BEDROCK_AWS_REGION=your-region
实例化模型：
import { BedrockEmbeddings } from "@langchain/aws";

const embeddings = new BedrockEmbeddings({
  model: "amazon.titan-embed-text-v1"
});
安装依赖项：
npm i @langchain/google-genai
添加环境变量：
GOOGLE_API_KEY=your-api-key
实例化模型：
import { GoogleGenerativeAIEmbeddings } from "@langchain/google-genai";

const embeddings = new GoogleGenerativeAIEmbeddings({
  model: "text-embedding-004"
});
安装依赖项：
npm i @langchain/google-vertexai
添加环境变量：
GOOGLE_APPLICATION_CREDENTIALS=credentials.json
实例化模型：
import { VertexAIEmbeddings } from "@langchain/google-vertexai";

const embeddings = new VertexAIEmbeddings({
  model: "gemini-embedding-001"
});
安装依赖项：
npm i @langchain/mistralai
添加环境变量：
MISTRAL_API_KEY=your-api-key
实例化模型：
import { MistralAIEmbeddings } from "@langchain/mistralai";

const embeddings = new MistralAIEmbeddings({
  model: "mistral-embed"
});
安装依赖项：
npm i @langchain/cohere
添加环境变量：
COHERE_API_KEY=your-api-key
实例化模型：
import { CohereEmbeddings } from "@langchain/cohere";

const embeddings = new CohereEmbeddings({
  model: "embed-english-v3.0"
});
安装依赖项：
npm i @langchain/ollama
实例化模型：
import { OllamaEmbeddings } from "@langchain/ollama";

const embeddings = new OllamaEmbeddings({
  model: "llama2",
  baseUrl: "http://localhost:11434", // 默认值
});
选择向量存储： 
npm i langchain

import { MemoryVectorStore } from "@langchain/classic/vectorstores/memory";

const vectorStore = new MemoryVectorStore(embeddings);

npm i @langchain/community

import { Chroma } from "@langchain/community/vectorstores/chroma";

const vectorStore = new Chroma(embeddings, {
  collectionName: "a-test-collection",
});

npm i @langchain/community

import { FaissStore } from "@langchain/community/vectorstores/faiss";

const vectorStore = new FaissStore(embeddings, {});

npm i @langchain/mongodb

import { MongoDBAtlasVectorSearch } from "@langchain/mongodb"
import { MongoClient } from "mongodb";

const client = new MongoClient(process.env.MONGODB_ATLAS_URI || "");
const collection = client
  .db(process.env.MONGODB_ATLAS_DB_NAME)
  .collection(process.env.MONGODB_ATLAS_COLLECTION_NAME);

const vectorStore = new MongoDBAtlasVectorSearch(embeddings, {
  collection,
  indexName: "vector_index",
  textKey: "text",
  embeddingKey: "embedding",
});

npm i @langchain/community

import { PGVectorStore } from "@langchain/community/vectorstores/pgvector";

const vectorStore = await PGVectorStore.initialize(embeddings, {});

npm i @langchain/pinecone

import { PineconeStore } from "@langchain/pinecone";
import { Pinecone as PineconeClient } from "@pinecone-database/pinecone";

const pinecone = new PineconeClient();
const vectorStore = new PineconeStore(embeddings, {
  pineconeIndex,
  maxConcurrency: 5,
});

npm i @langchain/redis

import { RedisVectorStore } from "@langchain/redis";

const vectorStore = new RedisVectorStore(embeddings, {
  redisClient: client,
  indexName: "langchainjs-testing",
});

npm i @langchain/qdrant

import { QdrantVectorStore } from "@langchain/qdrant";

const vectorStore = await QdrantVectorStore.fromExistingCollection(embeddings, {
  url: process.env.QDRANT_URL,
  collectionName: "langchainjs-testing",
});

npm i @oracle/langchain-oracledb @langchain/core

import oracledb from "oracledb";
import { OracleEmbeddings, OracleVS } from "@oracle/langchain-oracledb";

const connection = await oracledb.getConnection({
  user: process.env.ORACLE_USER,
  password: process.env.ORACLE_PASSWORD,
  connectionString: process.env.ORACLE_DSN,
});

const embeddings = new OracleEmbeddings(connection, {
  provider: "database",
  model: process.env.DEMO_ONNX_MODEL ?? "DEMO_MODEL",
});

const vectorStore = new OracleVS(embeddings, {
  client: connection,
  tableName: "DEMO_VECTORS",
  query: "Find support tickets mentioning service outages.",
  distanceStrategy: "DOT",
});
await vectorStore.initialize();

npm i @langchain/weaviate

import { WeaviateStore } from "@langchain/weaviate";

const vectorStore = new WeaviateStore(embeddings, {
    client: weaviateClient,
    indexName: "Langchainjs_test",
});
LangChain.js 集成了多种向量存储。您可以在下方查看完整列表：

​
所有向量存储

AnalyticDB

Astra DB

Azion EdgeSQL

Azure AI Search

Azure DocumentDB

Azure Cosmos DB for NoSQL

Cassandra

Chroma

ClickHouse

CloseVector

Cloudflare Vectorize

Convex

Couchbase Query

Couchbase Search

Elasticsearch

Faiss

Google Cloud SQL for PostgreSQL

Google Vertex AI Matching Engine

SAP HANA Cloud Vector Engine

HNSWLib

LanceDB

libSQL

MariaDB

In-memory

Milvus

Momento Vector Index (MVI)

MongoDB Atlas

MyScale

Neo4j Vector Index

Neon Postgres

Oracle AI Database

OpenSearch

PGVector

Pinecone

Prisma

Qdrant

Redis

Rockset

SingleStore

Supabase

Tigris

turbopuffer

TypeORM

Typesense

Upstash Vector

USearch

Vectara

Vercel Postgres

Voy

Weaviate

Xata

Zep Open Source

Zep Cloud

Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.