> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mem0.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Cloudflare Vectorize

> Use Cloudflare Vectorize as a vector database in Mem0 for building AI-powered applications at the edge.

[Cloudflare Vectorize](https://developers.cloudflare.com/vectorize/) is a vector database offering from Cloudflare, allowing you to build AI-powered applications with vector embeddings.

### Usage

<CodeGroup>
  ```typescript TypeScript theme={null}
  import { Memory } from 'mem0ai/oss';

  const config = {
    vectorStore: {
      provider: 'vectorize',
      config: {
        indexName: 'my-memory-index',
        accountId: 'your-cloudflare-account-id',
        apiKey: 'your-cloudflare-api-key',
        dimension: 1536, // Optional: defaults to 1536
      },
    },
  };

  const memory = new Memory(config);
  const messages = [
      {"role": "user", "content": "I'm looking for a good book to read."},
      {"role": "assistant", "content": "Sure, what genre are you interested in?"},
      {"role": "user", "content": "I enjoy fantasy novels with strong world-building."},
      {"role": "assistant", "content": "Great! I'll keep that in mind for future recommendations."}
  ]
  await memory.add(messages, { userId: "bob", metadata: { interest: "books" } });
  ```
</CodeGroup>

### Config

Here are the parameters available for configuring Vectorize:

<Tabs>
  <Tab title="TypeScript">
    | Parameter   | Description                       | Default Value     |
    | ----------- | --------------------------------- | ----------------- |
    | `indexName` | The name of the Vectorize index   | `None` (Required) |
    | `accountId` | Your Cloudflare account ID        | `None` (Required) |
    | `apiKey`    | Your Cloudflare API token         | `None` (Required) |
    | `dimension` | Dimensions of the embedding model | `1536`            |
  </Tab>
</Tabs>