Upstash Vector Db Skills

This handles Upstash Vector DB setup and semantic search operations, especially when you're building on Vercel. It covers the full workflow from creating an index in the console to querying with auto-embedding, plus namespace management for multi-tenant scenarios. The skill pushes MixBread AI as the preferred embedding provider, which is a specific opinion but backed by decent documentation. Code examples are practical and include error handling, batch operations, and a complete Vercel function implementation. If you're doing RAG or need serverless vector search without managing infrastructure, this gives you the patterns. The namespace isolation feature is honestly useful for keeping tenant data separate without spinning up multiple databases.

skills.sh installs: 368
GitHub stars: 23
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add gocallum/nextjs16-agent-skills --skill upstash-vector-db-skills --agent claude-code

Installs into .claude/skills of the current project.

Files

Quick Setup

1. Create Vector Index (Upstash Console)

Go to Upstash Console
Create Vector Index: name, region (closest to app), type (Dense for semantic search)
Select embedding model: MixBread AI recommended (or use Upstash built-in models)
Copy UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN to .env

2. Install SDK

pnpm add @upstash/vector

3. Environment

UPSTASH_VECTOR_REST_URL=your_url
UPSTASH_VECTOR_REST_TOKEN=your_token

Code Examples

Initialize Client (Node.js / TypeScript)

import { Index } from "@upstash/vector";

const index = new Index({
  url: process.env.UPSTASH_VECTOR_REST_URL,
  token: process.env.UPSTASH_VECTOR_REST_TOKEN,
});

SKILL.md on GitHub