---
name: vector-express
description: "Provisions an Upstash Vector index for a Express app with `npx extraorbital add vector` (no signup, no card) and wires it into Express with `@upstash/vector`. Use when a Express project needs Vector index, embeddings, semantic search, RAG, a vector database or UPSTASH_VECTOR_REST_URL, or when UPSTASH_VECTOR_REST_URL is missing or unset in .env."
---

# Vector index in Express

<!-- Generated from ExtraOrbital's service registry by `pnpm skills:build` in platform/app. Edit the generator, not this file. -->

ExtraOrbital provisions an Upstash Vector index in one command and writes the credentials into the project's env file. For anything this recipe does not cover, use the `extraorbital` skill or https://extraorbital.dev/llms.txt.

## 1. Provision

```bash
npx extraorbital add vector
```

Run it from the project root. It is idempotent (a second run returns the same resource) and writes to `.env.local` if the project has one, otherwise `.env`, keeping that file out of git. Add `--json` to parse the result; credential values are redacted there, and you should never print them either.

| Variable | |
| --- | --- |
| `UPSTASH_VECTOR_REST_URL` |  |
| `UPSTASH_VECTOR_REST_TOKEN` |  |

Free on the Prototype plan: 10K queries + 10K updates/day.

## 2. Install the client

```bash
npm install @upstash/vector
```

## 3. Connect

Node does not read env files by itself: start with `node --env-file=.env` (Node 20.6+), naming `.env.local` instead if that is where ExtraOrbital wrote, or load it with `dotenv`.

**`src/vector.js`**

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

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

## 4. Use it

**`src/app.js`**

```js
import { vectorIndex } from "./vector.js";

// Express 5 sends a rejected promise to the error handler; on Express 4, wrap this in try/catch.
app.get("/api/vector", async (req, res) => {
  const info = await vectorIndex.info();
  res.json({ vectors: info.vectorCount, dimension: info.dimension });
});
```

Store and search:

```ts
// Each vector must have the index's dimension (1536 unless provisioned otherwise).
await vectorIndex.upsert({ id: "doc-42", vector: embedding, metadata: { title: "Q3 report" } });
const hits = await vectorIndex.query({ vector: queryEmbedding, topK: 5, includeMetadata: true });
```

## 5. Verify

```bash
npx extraorbital list        # the resource is listed as active
node --env-file=.env src/server.js
curl http://localhost:3000/api/vector
```

A JSON answer means the credentials, the client and the route all work. Delete the route afterwards if the app does not need it.

## Pitfalls

- Dimensions and the similarity function are fixed at creation. Match the embedding model: `npx extraorbital add vector --dimensions 3072` (default 1536, `COSINE`); to change them, provision a new `--slug` and re-index.
- `provision .` creates the index at 1536 dimensions when it detects the variables; run `add vector --dimensions …` first if your model differs.
- Embeddings come from your model; for an API key to call one, see the `ai-gateway-*` skills.
- Snippets are ES modules (`"type": "module"`). In CommonJS, swap `import` for `require`.
- Create clients once at module scope, as here, not per request.
- Exit code 3 means the account is past its free allowance: show the human the link the command printed and wait. Do not retry or work around it.

Docs: https://extraorbital.dev/docs/resources/vector.md