Skip to main content
Amazon S3 Vectors is a purpose-built, cost-optimized vector storage and query service for semantic search and AI applications. It provides S3-level elasticity and durability with sub-second query performance.

​
Installation

S3 Vectors support requires additional dependencies. Install them with: 
pip install boto3

​
Usage

To use Amazon S3 Vectors with Mem0, you need to have an AWS account and the necessary IAM permissions (s3vectors:*). Ensure your environment is configured with AWS credentials (e.g., via ~/.aws/credentials or environment variables). 
import os
from mem0 import Memory

# Ensure your AWS credentials are configured in your environment
# e.g., by setting AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_DEFAULT_REGION

config = {
    "vector_store": {
        "provider": "s3_vectors",
        "config": {
            "vector_bucket_name": "my-mem0-vector-bucket",
            "index_name": "my-memories-index",
            "embedding_model_dims": 1536,
            "distance_metric": "cosine",
            "region_name": "us-east-1"
        }
    }
}

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 movie? 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"})

​
Config

Here are the available parameters for the s3_vectors config:
ParameterDescriptionDefault Value
vector_bucket_nameThe name of the S3 Vector bucket to use. It will be created if it doesn’t exist.Required
index_nameThe name of the vector index within the bucket.mem0
embedding_model_dimsDimensions of the embedding model. Must match your embedder.1536
distance_metricDistance metric for similarity search. Options: cosine, euclidean.cosine
region_nameThe AWS region where the bucket and index reside.None (uses default from AWS config)

​
IAM Permissions

Your AWS identity (user or role) needs permissions to perform actions on S3 Vectors. A minimal policy would look like this: 
{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": "s3vectors:*",
            "Resource": "*"
        }
    ]
}
For production, it is recommended to scope down the resource ARN to your specific buckets and indexes.