OpenSearch is an enterprise-grade search and observability suite that brings order to unstructured data at scale. OpenSearch supports k-NN (k-Nearest Neighbors) and allows you to store and retrieve high-dimensional vector embeddings efficiently.

Installation

OpenSearch support requires an additional client library. Install the one for your SDK:

<CodeGroup> ```bash Python pip install opensearch-py ```

bash

npm install @opensearch-project/opensearch

</CodeGroup>

Prerequisites

Before using OpenSearch with Mem0, you need to set up a collection in AWS OpenSearch Service.

AWS OpenSearch Service

You can create a collection through the AWS Console:

Navigate to OpenSearch Service Console
Click "Create collection"
Select "Serverless collection" and then enable "Vector search" capabilities
Once created, note the endpoint URL (host) for your configuration

Usage

<CodeGroup> ```python Python import os from mem0 import Memory import boto3 from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth

For AWS OpenSearch Service with IAM authentication

region = 'us-west-2' service = 'aoss' credentials = boto3.Session().get_credentials() auth = AWSV4SignerAuth(credentials, region, service)

config = { "vector_store": { "provider": "opensearch", "config": { "collection_name": "mem0", "host": "your-domain.us-west-2.aoss.amazonaws.com", "port": 443, "http_auth": auth, "embedding_model_dims": 1024, "connection_class": RequestsHttpConnection, "pool_maxsize": 20, "use_ssl": True, "verify_certs": True } } }


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

// Basic self-hosted OpenSearch. For AWS OpenSearch Serverless, build an
// @opensearch-project/opensearch Client with AwsSigv4Signer and pass it as
// `client` instead of host/port/user/password.
const config = {
  vectorStore: {
    provider: 'opensearch',
    config: {
      collectionName: 'mem0',
      embeddingModelDims: 1024,
      host: 'localhost',
      port: 9200,
      user: 'admin',
      password: 'admin',
      useSSL: false,
      verifyCerts: false,
    },
  },
};

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 thriller movies? 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>

Configuration Options

<Tabs> <Tab title="Python"> | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | `collection_name` | string | required | Name of the OpenSearch index | | `host` | string | required | OpenSearch endpoint URL | | `port` | int | 9200 | Port number | | `http_auth` | object | None | Authentication credentials (e.g., AWSV4SignerAuth) | | `embedding_model_dims` | int | 1536 | Dimension of embedding vectors | | `use_ssl` | bool | False | Enable SSL/TLS connection | | `verify_certs` | bool | False | Verify SSL certificates | | `auto_refresh` | bool | False | Automatically refresh index after insert. OpenSearch refreshes every ~1 second by default, so this is rarely needed. | </Tab> <Tab title="TypeScript"> | Parameter | Type | Default | Description | |-----------|------|---------|-------------| | `collectionName` | string | required | Name of the OpenSearch index | | `embeddingModelDims` | number | 1536 | Dimension of embedding vectors | | `host` | string | `localhost` | OpenSearch endpoint host | | `port` | number | 9200 | Port number | | `httpAuth` | object | None | Authentication credentials, an object or `[user, password]` tuple | | `user` | string | None | Username for basic auth (used together with `password`) | | `password` | string | None | Password for basic auth (used together with `user`) | | `useSSL` | boolean | false | Enable SSL/TLS connection | | `verifyCerts` | boolean | false | Verify SSL certificates | | `autoRefresh` | boolean | false | Refresh the index after each write so new memories are searchable immediately. Not supported on AWS Serverless. | | `client` | object | None | Preconfigured OpenSearch client, e.g. one built with AwsSigv4Signer for AWS auth | </Tab> </Tabs> <Note> The defaults above match a local OpenSearch instance. The AWS OpenSearch Serverless example earlier on this page intentionally overrides them with `port=443`, `use_ssl=True`, and `verify_certs=True`, which are required when connecting to a Serverless collection. </Note> <Note> For **AWS OpenSearch Serverless**, keep `auto_refresh=False` (the default). The `indices.refresh()` API is not supported on Serverless collections. </Note>

Add Memories

python

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about thriller movies? 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"})

Search Memories

python

results = m.search("What kind of movies does Alice like?", filters={"user_id": "alice"})

Features

Fast and Efficient Vector Search
Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service
Multiple authentication and security methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
Automatic index creation with optimized mappings for vector search
Memory optimization through disk-based vector search and quantization
Real-time analytics and observability