Vector Documentation Skill

Quick Start

Vector is a high‑performance vector database for storing, querying, and managing vector embeddings.

Basic workflow:

• Install the Vector TS SDK.
• Connect to a Vector instance.
• Upsert vectors, query them, and manage namespaces.

Example (TypeScript):

ts
1import { Index } from "@upstash/vector";
2const index = new Index({
3  url: process.env.UPSTASH_VECTOR_REST_URL!,
4  token: process.env.UPSTASH_VECTOR_REST_TOKEN!,
5});
6
7await index.upsert([{ id: "1", vector: [0.1, 0.2], metadata: { tag: "example" } }]);
8
9const results = await index.query({
10  vector: [0.1, 0.2],
11  topK: 5,
12});

For full usage, refer to the linked skill files below.

Other Skill Files

TS SDK Reference

• sdk-methods: Explains SDK commands: delete, fetch, info, query, range, reset, resumable-query, upsert

Features

• features/namespaces: Explains namespaces and dataset organization.
• features/index-structure: Covers hybrid and sparse index structures.
• features/filtering-and-metadata: Details metadata storage and server-side filtering.

Use these files for deeper guidance on SDK usage, advanced configurations, algorithms, and integrations.