JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add neptune example notebook and documentation (#3224)

Browse Source 
Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
This commit is contained in:
Andrew Carbonetto
2025-08-12 13:00:18 -07:00
committed by GitHub
parent 8557533b8f
commit ab099312d5
7 changed files with 219 additions and 343 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/examples/aws_example.mdx
+24 -12
View File
@@ -1,17 +1,17 @@
---
title: AWS Bedrock and AOSS
title: Amazon Stack: AWS Bedrock, AOSS, and Neptune Analytics
---
<Snippet file="blank-notif.mdx" />
This example demonstrates how to configure and use the `mem0ai` SDK with **AWS Bedrock** and **OpenSearch Service (AOSS)** for persistent memory capabilities in Python.
This example demonstrates how to configure and use the `mem0ai` SDK with **AWS Bedrock**, **OpenSearch Service (AOSS)**, and **AWS Neptune Analytics** for persistent memory capabilities in Python.
## Installation
Install the required dependencies:
Install the required dependencies to include the Amazon data stack, including **boto3**, **opensearch-py**, and **langchain-aws**:
```bash
pip install mem0ai boto3 opensearch-py
pip install "mem0ai[graph,extras]"
```
## Environment Setup
@@ -34,11 +34,15 @@ print(os.environ['AWS_SECRET_ACCESS_KEY'])
## Configuration and Usage
This sets up Mem0 with AWS Bedrock for embeddings and LLM, and OpenSearch as the vector store.
This sets up Mem0 with:
- [AWS Bedrock for LLM](https://docs.mem0.ai/components/llms/models/aws_bedrock)
- [AWS Bedrock for embeddings](https://docs.mem0.ai/components/embedders/models/aws_bedrock#aws-bedrock)
- [OpenSearch as the vector store](https://docs.mem0.ai/components/vectordbs/dbs/opensearch)
- [Neptune Analytics as your graph store](https://docs.mem0.ai/open-source/graph_memory/overview#initialize-neptune-analytics).
```python
import boto3
from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth
from opensearchpy import RequestsHttpConnection, AWSV4SignerAuth
from mem0.memory.main import Memory
region = 'us-west-2'
@@ -56,7 +60,7 @@ config = {
"llm": {
"provider": "aws_bedrock",
"config": {
"model": "anthropic.claude-3-5-haiku-20241022-v1:0",
"model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
"temperature": 0.1,
"max_tokens": 2000
}
@@ -68,21 +72,29 @@ config = {
"host": "your-opensearch-domain.us-west-2.es.amazonaws.com",
"port": 443,
"http_auth": auth,
"embedding_model_dims": 1024,
"connection_class": RequestsHttpConnection,
"pool_maxsize": 20,
"use_ssl": True,
"verify_certs": True
"verify_certs": True,
"embedding_model_dims": 1024,
}
}
},
"graph_store": {
"provider": "neptune",
"config": {
"endpoint": f"neptune-graph://my-graph-identifier",
},
},
}
# Initialize memory system
# Initialize the memory system
m = Memory.from_config(config)
```
## Usage
Reference [Notebook example](https://github.com/mem0ai/mem0/blob/main/examples/graph-db-demo/neptune-example.ipynb)
#### Add a memory:
```python
@@ -117,4 +129,4 @@ memory = m.get(memory_id)
## Conclusion
With Mem0 and AWS services like Bedrock and OpenSearch, you can build intelligent AI companions that remember, adapt, and personalize their responses over time. This makes them ideal for long-term assistants, tutors, or support bots with persistent memory and natural conversation abilities.
With Mem0 and AWS services like Bedrock, OpenSearch, and Neptune Analytics, you can build intelligent AI companions that remember, adapt, and personalize their responses over time. This makes them ideal for long-term assistants, tutors, or support bots with persistent memory and natural conversation abilities.