Skip to main content
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 additional dependencies. Install them with: 
pip install opensearch-py

​
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

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
        }
    }
}

​
Configuration Options

ParameterTypeDefaultDescription
collection_namestringrequiredName of the OpenSearch index
hoststringrequiredOpenSearch endpoint URL
portint9200Port number
http_authobjectNoneAuthentication credentials (e.g., AWSV4SignerAuth)
embedding_model_dimsint1536Dimension of embedding vectors
use_sslboolFalseEnable SSL/TLS connection
verify_certsboolFalseVerify SSL certificates
auto_refreshboolFalseAutomatically refresh index after insert. OpenSearch refreshes every ~1 second by default, so this is rarely needed.
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.
For AWS OpenSearch Serverless, keep auto_refresh=False (the default). The indices.refresh() API is not supported on Serverless collections.

​
Add Memories

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

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