向量存储

¥Vector stores

向量存储 存储 embedded 数据并执行相似性搜索。

¥A vector store stores embedded data and performs similarity search.

Pick your embedding model:

OpenAI

Install dependencies

npm

npm i @langchain/openai

yarn

yarn add @langchain/openai

pnpm

pnpm add @langchain/openai

OPENAI_API_KEY=your-api-key

import { OpenAIEmbeddings } from "@langchain/openai";

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

Azure

Install dependencies

npm

npm i @langchain/openai

yarn

yarn add @langchain/openai

pnpm

pnpm add @langchain/openai

AZURE_OPENAI_API_INSTANCE_NAME=<YOUR_INSTANCE_NAME>
AZURE_OPENAI_API_KEY=<YOUR_KEY>
AZURE_OPENAI_API_VERSION="2024-02-01"

import { AzureOpenAIEmbeddings } from "@langchain/openai";

const embeddings = new AzureOpenAIEmbeddings({
  azureOpenAIApiEmbeddingsDeploymentName: "text-embedding-ada-002"
});

AWS

Install dependencies

npm

npm i @langchain/aws

yarn

yarn add @langchain/aws

pnpm

pnpm add @langchain/aws

BEDROCK_AWS_REGION=your-region

import { BedrockEmbeddings } from "@langchain/aws";

const embeddings = new BedrockEmbeddings({
  model: "amazon.titan-embed-text-v1"
});

VertexAI

Install dependencies

npm

npm i @langchain/google-vertexai

yarn

yarn add @langchain/google-vertexai

pnpm

pnpm add @langchain/google-vertexai

GOOGLE_APPLICATION_CREDENTIALS=credentials.json

import { VertexAIEmbeddings } from "@langchain/google-vertexai";

const embeddings = new VertexAIEmbeddings({
  model: "text-embedding-004"
});

MistralAI

Install dependencies

npm

npm i @langchain/mistralai

yarn

yarn add @langchain/mistralai

pnpm

pnpm add @langchain/mistralai

MISTRAL_API_KEY=your-api-key

import { MistralAIEmbeddings } from "@langchain/mistralai";

const embeddings = new MistralAIEmbeddings({
  model: "mistral-embed"
});

Cohere

Install dependencies

npm

npm i @langchain/cohere

yarn

yarn add @langchain/cohere

pnpm

pnpm add @langchain/cohere

COHERE_API_KEY=your-api-key

import { CohereEmbeddings } from "@langchain/cohere";

const embeddings = new CohereEmbeddings({
  model: "embed-english-v3.0"
});

Pick your vector store:

Memory

Install dependencies

npm

npm i langchain

yarn

yarn add langchain

pnpm

pnpm add langchain

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

const vectorStore = new MemoryVectorStore(embeddings);

Chroma

Install dependencies

npm

npm i @langchain/community

yarn

yarn add @langchain/community

pnpm

pnpm add @langchain/community

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

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

FAISS

Install dependencies

npm

npm i @langchain/community

yarn

yarn add @langchain/community

pnpm

pnpm add @langchain/community

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

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

MongoDB

Install dependencies

npm

npm i @langchain/mongodb

yarn

yarn add @langchain/mongodb

pnpm

pnpm add @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: collection,
  indexName: "vector_index",
  textKey: "text",
  embeddingKey: "embedding",
});

PGVector

Install dependencies

npm

npm i @langchain/community

yarn

yarn add @langchain/community

pnpm

pnpm add @langchain/community

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

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

Pinecone

Install dependencies

npm

npm i @langchain/pinecone

yarn

yarn add @langchain/pinecone

pnpm

pnpm add @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,
});

Qdrant

Install dependencies

npm

npm i @langchain/qdrant

yarn

yarn add @langchain/qdrant

pnpm

pnpm add @langchain/qdrant

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

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

LangChain.js 可与各种向量存储集成。你可以查看以下完整列表：

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

Name	Description
AnalyticDB	analyticdb}
Astra 数据库	astra-db}
Azion EdgeSQL	AzionVectorStore 用于使用向量嵌入管理和搜索文档集合，直接在 Azion 的边缘平台上使用 Edge SQL 进行操作。
Azure AI 搜索	azure-ai-search}
Azure Cosmos DB for MongoDB vCore	azure-cosmos-db-for-mongodb-vcore}
Azure Cosmos DB for NoSQL	azure-cosmos-db-for-nosql}
Cassandra	cassandra}
ClickHouse	clickhouse}
CloseVector	closevector}
Cloudflare Vectorize	cloudflare-vectorize}
Convex	convex}
Couchbase	couchbase}
Google Cloud SQL for PostgreSQL	Cloud SQL 是一项完全托管的关系数据库服务，提供高性能、无缝集成和卓越的可扩展性，并提供 PostgreSQL 等数据库引擎。
Google Vertex AI 匹配引擎	google-vertex-ai-matching-engine}
SAP HANA 云矢量引擎	sap-hana-cloud-vector-engine}
LanceDB	lancedb}
libSQL	libsql}
Milvus	milvus}
Momento 向量索引(MVI)	momento-vector-index-mvi}
MyScale	myscale}
Neo4j 向量索引	neo4j-vector-index}
Neon Postgres	neon-postgres}
OpenSearch	opensearch}
Prisma	prisma}
Rockset	rockset}
SingleStore	singlestore}
Tigris	tigris}
Turbopuffer	turbopuffer}
TypeORM	typeorm}
Typesense	typesense}
USearch	usearch}
Vectara	vectara}
Vercel Postgres	vercel-postgres}
Voy	voy}
Xata	xata}
Zep 开源	zep-open-source}
Zep 云	zep-cloud}