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 为向量存储提供了一个统一的接口，允许您：
  • addDocuments - 向存储添加文档。
  • delete - 按 ID 删除存储的文档。
  • similaritySearch - 查询语义相似的文档。
这种抽象允许您在不更改应用程序逻辑的情况下切换不同的实现。

​
初始化

LangChain 中的大多数向量存储在初始化向量存储时接受嵌入模型作为参数。 
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，它返回最接近的嵌入文档： 
const results = await vectorStore.similaritySearch("Hello world", 10);
许多向量存储支持如下参数：
  • k — 要返回的结果数量
  • filter — 基于元数据的条件过滤

​
相似性度量和索引

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

​
元数据过滤

按元数据（例如来源、日期）过滤可以细化搜索结果： 
vectorStore.similaritySearch("query", 2, { source: "tweets" });

​
热门集成

选择嵌入模型：
Install dependencies:
npm i @langchain/openai
Add environment variables:
OPENAI_API_KEY=your-api-key
Instantiate the model:
import { OpenAIEmbeddings } from "@langchain/openai";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-large"
});
Install dependencies
npm i @langchain/openai
Add environment variables:
AZURE_OPENAI_API_INSTANCE_NAME=<YOUR_INSTANCE_NAME>
AZURE_OPENAI_API_KEY=<YOUR_KEY>
AZURE_OPENAI_API_VERSION="2024-02-01"
Instantiate the model:
import { AzureOpenAIEmbeddings } from "@langchain/openai";

const embeddings = new AzureOpenAIEmbeddings({
  azureOpenAIApiEmbeddingsDeploymentName: "text-embedding-ada-002"
});
Install dependencies:
npm i @langchain/aws
Add environment variables:
BEDROCK_AWS_REGION=your-region
Instantiate the model:
import { BedrockEmbeddings } from "@langchain/aws";

const embeddings = new BedrockEmbeddings({
  model: "amazon.titan-embed-text-v1"
});
Install dependencies:
npm i @langchain/google-genai
Add environment variables:
GOOGLE_API_KEY=your-api-key
Instantiate the model:
import { GoogleGenerativeAIEmbeddings } from "@langchain/google-genai";

const embeddings = new GoogleGenerativeAIEmbeddings({
  model: "text-embedding-004"
});
Install dependencies:
npm i @langchain/google-vertexai
Add environment variables:
GOOGLE_APPLICATION_CREDENTIALS=credentials.json
Instantiate the model:
import { VertexAIEmbeddings } from "@langchain/google-vertexai";

const embeddings = new VertexAIEmbeddings({
  model: "gemini-embedding-001"
});
Install dependencies:
npm i @langchain/mistralai
Add environment variables:
MISTRAL_API_KEY=your-api-key
Instantiate the model:
import { MistralAIEmbeddings } from "@langchain/mistralai";

const embeddings = new MistralAIEmbeddings({
  model: "mistral-embed"
});
Install dependencies:
npm i @langchain/cohere
Add environment variables:
COHERE_API_KEY=your-api-key
Instantiate the model:
import { CohereEmbeddings } from "@langchain/cohere";

const embeddings = new CohereEmbeddings({
  model: "embed-english-v3.0"
});
Install dependencies:
npm i @langchain/ollama
Instantiate the model:
import { OllamaEmbeddings } from "@langchain/ollama";

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

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

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

​
所有向量存储

AnalyticDB

Astra DB

Azion EdgeSQL

Azure AI Search

Azure Cosmos DB for MongoDB vCore

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

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