Cloudflare Vectorize

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

Cloudflare Vectorize is a vector database offering from Cloudflare, allowing you to build AI-powered applications with vector embeddings.

Usage

TypeScript

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" } });

Config

Here are the parameters available for configuring Vectorize:

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