AWS Neptune Analytics

pip install "mem0ai[graph,extras]"

import os

# Set these in your environment or notebook
os.environ['AWS_REGION'] = 'us-west-2'
os.environ['AWS_ACCESS_KEY_ID'] = 'AK00000000000000000'
os.environ['AWS_SECRET_ACCESS_KEY'] = 'AS00000000000000000'

# Confirm they are set
print(os.environ['AWS_REGION'])
print(os.environ['AWS_ACCESS_KEY_ID'])
print(os.environ['AWS_SECRET_ACCESS_KEY'])

import boto3
from mem0.memory.main import Memory

region = 'us-west-2'
neptune_analytics_endpoint = 'neptune-graph://my-graph-identifier'

config = {
    "embedder": {
        "provider": "aws_bedrock",
        "config": {
            "model": "amazon.titan-embed-text-v2:0"
        }
    },
    "llm": {
        "provider": "aws_bedrock",
        "config": {
            "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
            "temperature": 0.1,
            "max_tokens": 2000
        }
    },
    "vector_store": {
        "provider": "neptune",
        "config": {
            "collection_name": "mem0",
            "endpoint": neptune_analytics_endpoint,
        },
    },
    "graph_store": {
        "provider": "neptune",
        "config": {
            "endpoint": neptune_analytics_endpoint,
        },
    },
}

# Initialize the memory system
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 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."}
]

# Store inferred memories (default behavior)
result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})

relevant_memories = m.search(query, user_id="alice")

all_memories = m.get_all(user_id="alice")

memory = m.get(memory_id)