向量存储集成

使用 LangChain JavaScript 集成 vector stores。

概述

A vector store stores embedded data and performs similarity search.

Interface

LangChain provides a unified interface for vector stores, allowing you to:

• addDocuments - Add documents to the store.
• delete - Remove stored documents by ID.
• similaritySearch - Query for semantically similar documents.

This abstraction lets you switch between different implementations without altering your application logic.

初始化

Most vectorstores in LangChain accept an embedding model as an argument when initializing the vector store.

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);

Adding documents

You can add documents to the vector store by using the addDocuments function.

import { Document } from "@langchain/core/documents";
const document = new Document({
  pageContent: "Hello world",
});
await vectorStore.addDocuments([document]);

Deleting documents

You can delete documents from the vector store by using the delete function.

await vectorStore.delete({
  filter: {
    pageContent: "Hello world",
  },
});

相似度搜索

Issue a semantic query using similaritySearch, which returns the closest embedded documents:

const results = await vectorStore.similaritySearch("Hello world", 10);

Many vector stores support parameters like:

• k — number of results to return
• filter — conditional filtering based on metadata

Similarity metrics & indexing

Embedding similarity may be computed using:

• Cosine similarity
• Euclidean distance
• Dot product

Efficient search often employs indexing methods such as HNSW (Hierarchical Navigable Small World), though specifics depend on the vector store.

Metadata filtering

Filtering by metadata (e.g., source, date) can refine search results:

vectorStore.similaritySearch("query", 2, { source: "tweets" });

Top integrations

Select embedding model:

OpenAI

安装依赖：

npm

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"
});

Azure

安装依赖

npm

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"
});

AWS

安装依赖：

npm

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"
});

Google Gemini

安装依赖：

npm

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"
});

Google Vertex

安装依赖：

npm

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"
});

MistralAI

安装依赖：

npm

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"
});

Cohere

安装依赖：

npm

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"
});

Ollama

安装依赖：

npm

npm i @langchain/ollama

实例化模型：

import { OllamaEmbeddings } from "@langchain/ollama";

const embeddings = new OllamaEmbeddings({
  model: "llama2",
  baseUrl: "http://localhost:11434", // Default value
});

Select vector store:

Memory

npm i langchain

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

const vectorStore = new MemoryVectorStore(embeddings);

Chroma

npm

npm i @langchain/community

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

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

FAISS

npm

npm i @langchain/community

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

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

MongoDB

Manual embedding

npm

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",
});

Automated embedding

npm

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({ collection });

PGVector

npm

npm i @langchain/community

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

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

Pinecone

npm

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,
});

Redis

npm

npm i @langchain/redis

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

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

Qdrant

npm

npm i @langchain/qdrant

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

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

Oracle AI Database

npm

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();

Weaviate

npm

npm i @langchain/weaviate

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

const vectorStore = new WeaviateStore(embeddings, {
    client: weaviateClient,
    indexName: "Langchainjs_test",
});

LangChain.js integrates with a variety of vector stores. You can check out a full list below:

All vector stores

AnalyticDB

查看指南

Astra DB

查看指南

Azion EdgeSQL

查看指南

Azure AI Search

查看指南

Azure DocumentDB

查看指南

Azure Cosmos DB for NoSQL

查看指南

Cassandra

查看指南

Chroma

查看指南

ClickHouse

查看指南

CloseVector

查看指南

Cloudflare Vectorize

查看指南

Convex

查看指南

Couchbase Query

查看指南

Couchbase Search

查看指南

Elasticsearch

查看指南

Faiss

查看指南

Google Cloud SQL for PostgreSQL

查看指南

Google Vertex AI Matching Engine

查看指南

SAP HANA Cloud Vector Engine

查看指南

HNSWLib

查看指南

LanceDB

查看指南

libSQL

查看指南

MariaDB

查看指南

In-memory

查看指南

Milvus

查看指南

Momento Vector Index (MVI)

查看指南

MongoDB Atlas

查看指南

MyScale

查看指南

Neo4j Vector Index

查看指南

Neon Postgres

查看指南

Oracle AI Database

查看指南

OpenSearch

查看指南

PGVector

查看指南

Pinecone

查看指南

Prisma

查看指南

Qdrant

查看指南

Redis

查看指南

Rockset

查看指南

SingleStore

查看指南

Supabase

查看指南

Tigris

查看指南

turbopuffer

查看指南

TypeORM

查看指南

Typesense

查看指南

Upstash Vector

查看指南

USearch

查看指南

Vectara

查看指南

Vercel Postgres

查看指南

Voy

查看指南

Weaviate

查看指南

Xata

查看指南

Zep Open Source

查看指南

Zep Cloud

查看指南

---

将这些文档连接到 Claude、VSCode 等工具，通过 MCP 获取实时答案。

在 GitHub 上编辑此页面 或 提交 issue。