Neptune Analytics - Mem0

Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds, including vector search.

Installation

The Neptune Analytics provider needs the AWS Neptune Graph client. Install it alongside mem0ai:

<CodeGroup> ```bash Python pip install mem0ai[vector-stores] ```

bash

npm install @aws-sdk/client-neptune-graph

</CodeGroup>

Usage

Configure AWS credentials in your environment (environment variables, shared config file, an IAM role, or an instance profile). Both SDKs pick them up automatically through the standard AWS credential chain.

<CodeGroup> ```python Python from mem0 import Memory

config = { "vector_store": { "provider": "neptune", "config": { "collection_name": "mem0", "endpoint": "neptune-graph://g-abc123xyz0", }, }, }

m = Memory.from_config(config) messages = [ {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"}, {"role": "assistant", "content": "How about a thriller movie? They can be quite engaging."}, {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."}, {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."} ] m.add(messages, user_id="alice", metadata={"category": "movies"})


```typescript TypeScript
import { Memory } from 'mem0ai/oss';

const config = {
  vectorStore: {
    provider: 'neptune',
    config: {
      collectionName: 'mem0',
      graphIdentifier: 'g-abc123xyz0',
      // Any other key here (region, credentials, maxAttempts, ...) is
      // forwarded to the underlying NeptuneGraphClient constructor.
      region: 'us-east-1',
    },
  },
};

const memory = new Memory(config);
const messages = [
  { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
  { role: "assistant", content: "How about a thriller movie? They can be quite engaging." },
  { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
  { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." },
];
await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });

</CodeGroup>

Config

<Tabs> <Tab title="Python"> | Parameter | Description | Default Value | | --- | --- | --- | | `collection_name` | The name of the collection to store the vectors | `mem0` | | `endpoint` | Connection URL for the Neptune Analytics service, must be `neptune-graph://<graph-id>` | Required | </Tab> <Tab title="TypeScript"> | Parameter | Description | Default Value | | --- | --- | --- | | `collectionName` | The name of the collection to store the vectors | `memories` | | `graphIdentifier` | Graph ID, e.g. `g-abc123xyz0`. Takes priority over `endpoint`. | Required, unless `endpoint` supplies it | | `endpoint` | Either `neptune-graph://<graph-id>` (or a bare graph ID) to supply the graph ID, or an `https://` service endpoint to override the AWS endpoint. An `https://` value must be paired with `graphIdentifier`. | `undefined` | | `dimension` | Embedding vector dimension | Auto-detected from the embedder when omitted | | `client` | A pre-built `NeptuneGraphClient` to use instead of constructing one | `undefined` | | any other key | Forwarded as-is to the [`NeptuneGraphClient`](https://www.npmjs.com/package/@aws-sdk/client-neptune-graph) constructor, e.g. `region`, `credentials`, `maxAttempts` | N/A | </Tab> </Tabs>

Both SDKs store vectors on graph nodes labeled MEM0_VECTOR_<collection_name>. Point them at the same graph with the same collection_name — the defaults differ, mem0 in Python and memories in TypeScript — and get(), list(), and delete() interoperate across SDKs.

<Note> `search()` is not currently cross-SDK compatible. The TypeScript provider filters on Neptune's reserved `~label` metafield, while the Python provider filters on a synthetic `label` property that only Python's own `insert()` writes. Python's `search()` therefore cannot see nodes written by the TypeScript provider. </Note>

IAM Permissions

Your AWS identity (user or role) needs a policy that allows the ExecuteQuery actions used for reads, writes, and deletes:

json

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "neptune-graph:ReadDataViaQuery",
        "neptune-graph:WriteDataViaQuery",
        "neptune-graph:DeleteDataViaQuery"
      ],
      "Resource": "*"
    }
  ]
}

For production, scope the resource ARN down to your specific graph.