pgvector-node

pgvector support for Node.js

Supports Sequelize, node-postgres, pg-promise, and Prisma

Installation

Run:

npm install pgvector

And follow the instructions for your database library:

• Sequelize
• node-postgres
• pg-promise
• Prisma

Sequelize

Register the type

const { Sequelize } = require('sequelize');
const pgvector = require('pgvector/sequelize');

pgvector.registerType(Sequelize);

Add a vector field

Item.init({
  embedding: {
    type: DataTypes.VECTOR(3)
  }
}, ...);

Insert a vector

await Item.create({embedding: [1, 2, 3]});

Get the nearest neighbors to a vector

const items = await Item.findAll({
  order: [sequelize.literal(`embedding <-> '[1, 2, 3]'`)],
  limit: 5
});

node-postgres

Register the type

const pgvector = require('pgvector/pg');

await pgvector.registerType(client);

Insert a vector

const embedding = [1, 2, 3];
await client.query('INSERT INTO items (embedding) VALUES ($1)', [pgvector.toSql(embedding)]);

Get the nearest neighbors to a vector

const result = await client.query('SELECT * FROM items ORDER BY embedding <-> $1 LIMIT 5', [pgvector.toSql(embedding)]);

pg-promise

Register the type

const pgvector = require('pgvector/pg');

const initOptions = {
  async connect(e) {
    await pgvector.registerType(e.client);
  }
};
const pgp = require('pg-promise')(initOptions);

Insert a vector

const embedding = [1, 2, 3];
await db.none('INSERT INTO items (embedding) VALUES ($1)', [pgvector.toSql(embedding)]);

Get the nearest neighbors to a vector

const result = await db.any('SELECT * FROM items ORDER BY embedding <-> $1 LIMIT 5', [pgvector.toSql(embedding)]);

Prisma

Import the library

const pgvector = require('pgvector/utils')

Add the extension to the schema

generator client {
  provider        = "prisma-client-js"
  previewFeatures = ["postgresqlExtensions"]
}

datasource db {
  provider   = "postgresql"
  url        = env("DATABASE_URL")
  extensions = [vector]
}

Add a vector column to the schema

model Item {
  id        Int                       @id @default(autoincrement())
  embedding Unsupported("vector(3)")?
}

Insert a vector

const embedding = pgvector.toSql([1, 1, 1])
await prisma.$executeRaw`INSERT INTO items (embedding) VALUES (${embedding}::vector)`

Get the nearest neighbors to a vector

const embedding = pgvector.toSql([1, 1, 1])
const items = await prisma.$queryRaw`SELECT id, embedding::text FROM items ORDER BY embedding <-> ${embedding}::vector LIMIT 5`

History

View the changelog

Contributing

Everyone is encouraged to help improve this project. Here are a few ways you can help:

• Report bugs
• Fix bugs and submit pull requests
• Write, clarify, or fix documentation
• Suggest or add new features

To get started with development:

git clone https://github.com/pgvector/pgvector-node.git
cd pgvector-node
npm install
npm run build:cjs
createdb pgvector_node_test
npx prisma migrate dev
npm test