my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	[OpenSearch](https://opensearch.org/) 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.
#2
#3	### Installation
#4
#5	OpenSearch support requires additional dependencies. Install them with:
#6
#7	```bash
#8	pip install opensearch-py
#9	```
#10
#11	### Prerequisites
#12
#13	Before using OpenSearch with Mem0, you need to set up a collection in AWS OpenSearch Service.
#14
#15	#### AWS OpenSearch Service
#16	You can create a collection through the AWS Console:
#17	- Navigate to [OpenSearch Service Console](https://console.aws.amazon.com/aos/home)
#18	- Click "Create collection"
#19	- Select "Serverless collection" and then enable "Vector search" capabilities
#20	- Once created, note the endpoint URL (host) for your configuration
#21
#22
#23	### Usage
#24
#25	```python
#26	import os
#27	from mem0 import Memory
#28	import boto3
#29	from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth
#30
#31	# For AWS OpenSearch Service with IAM authentication
#32	region = 'us-west-2'
#33	service = 'aoss'
#34	credentials = boto3.Session().get_credentials()
#35	auth = AWSV4SignerAuth(credentials, region, service)
#36
#37	config = {
#38	"vector_store": {
#39	"provider": "opensearch",
#40	"config": {
#41	"collection_name": "mem0",
#42	"host": "your-domain.us-west-2.aoss.amazonaws.com",
#43	"port": 443,
#44	"http_auth": auth,
#45	"embedding_model_dims": 1024,
#46	"connection_class": RequestsHttpConnection,
#47	"pool_maxsize": 20,
#48	"use_ssl": True,
#49	"verify_certs": True
#50	}
#51	}
#52	}
#53	```
#54
#55	### Add Memories
#56
#57	```python
#58	m = Memory.from_config(config)
#59	messages = [
#60	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#61	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#62	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#63	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#64	]
#65	m.add(messages, user_id="alice", metadata={"category": "movies"})
#66	```
#67
#68	### Search Memories
#69
#70	```python
#71	results = m.search("What kind of movies does Alice like?", user_id="alice")
#72	```
#73
#74	### Features
#75
#76	- Fast and Efficient Vector Search
#77	- Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service
#78	- Multiple authentication and security methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
#79	- Automatic index creation with optimized mappings for vector search
#80	- Memory optimization through disk-based vector search and quantization
#81	- Real-time analytics and observability
#82

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public