databases (vector ai)10 minutes

Get Started with Pinecone

Unverified

Quick Summary

The fully managed vector database for production AI

Best for: Startup founders and enterprise teams building RAG pipelines who need a managed vector database with no infrastructure to run
Time to first integration: 10 minutes

📋Prerequisites

  • Node.js 18+ installed
  • A Pinecone account — sign up here
  • An existing project (Next.js, React, or Node.js recommended)

Setup Steps

4 steps
1

Create an index

Create an index in the Pinecone console (dimension must match your embedding model).

2

Install

Add the Pinecone SDK to your project.

bash
npm install @pinecone-database/pinecone
3

Initialize

Create a client with your API key.

typescript
import { Pinecone } from '@pinecone-database/pinecone' const pc = new Pinecone({ apiKey: process.env.PINECONE_API_KEY })
4

Upsert and query

Upsert vectors, then query by vector for similarity search.

typescript
const index = pc.index('my-index') await index.upsert([{ id: '1', values: [/* ... */] }]) const results = await index.query({ vector: [/* ... */], topK: 5 })

Related Guides

Setting up a full stack? Check out these complementary guides.

Links