> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sundaypyjamas.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Vector Store API

> Per-app vector collections for similarity search and custom retrieval pipelines

## Overview

Each app can have one or more named **vector stores** — collections of embeddings you manage directly, useful when you want full control over chunking and retrieval instead of using the higher-level [RAG API](/api-reference/rag/introduction).

<Steps>
  <Step title="Create an index">
    [`POST .../create-index`](/api-reference/vector-store/indexes#create-index) with your embedding dimension and distance metric.
  </Step>

  <Step title="Upsert vectors">
    [`POST .../upsert`](/api-reference/vector-store/vectors#upsert-vectors) with `{ id, vector, payload }` points.
  </Step>

  <Step title="Query">
    [`POST .../query`](/api-reference/vector-store/vectors#query-vectors) with a raw vector (or `query` text for Bedrock Knowledge Base–backed apps).
  </Step>
</Steps>

## Base URL

```
https://suite.sundaypyjamas.com/api/v1/apps/{appId}/vector/{vectorName}
```

`vectorName` is a namespace you choose per app — e.g. `"docs"`, `"products"` — allowing one app to maintain multiple independent vector collections.

## Authentication

```http theme={null}
Authorization: Bearer spj_ai_your_api_key_here
```

Widget tokens are also accepted as a fallback for browser-embedded use cases.

## Resources

<CardGroup cols={2}>
  <Card title="Indexes" icon="database" href="/api-reference/vector-store/indexes">
    Create, list, inspect, and delete vector collections.
  </Card>

  <Card title="Vectors" icon="chart-scatter" href="/api-reference/vector-store/vectors">
    Upsert and query vector points.
  </Card>
</CardGroup>