my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Amazon S3 Vectors
#3	---
#4
#5	[Amazon S3 Vectors](https://aws.amazon.com/s3/features/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.
#6
#7	### Installation
#8
#9	S3 Vectors support requires additional dependencies. Install them with:
#10
#11	```bash
#12	pip install boto3
#13	```
#14
#15	### Usage
#16
#17	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).
#18
#19	```python
#20	import os
#21	from mem0 import Memory
#22
#23	# Ensure your AWS credentials are configured in your environment
#24	# e.g., by setting AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_DEFAULT_REGION
#25
#26	config = {
#27	"vector_store": {
#28	"provider": "s3_vectors",
#29	"config": {
#30	"vector_bucket_name": "my-mem0-vector-bucket",
#31	"collection_name": "my-memories-index",
#32	"embedding_model_dims": 1536,
#33	"distance_metric": "cosine",
#34	"region_name": "us-east-1"
#35	}
#36	}
#37	}
#38
#39	m = Memory.from_config(config)
#40	messages = [
#41	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#42	{"role": "assistant", "content": "How about a thriller movie? They can be quite engaging."},
#43	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#44	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#45	]
#46	m.add(messages, user_id="alice", metadata={"category": "movies"})
#47	```
#48
#49	### Config
#50
#51	Here are the parameters available for configuring Amazon S3 Vectors:
#52
#53	\| Parameter \| Description \| Default Value \|
#54	\| ---------------------- \| -------------------------------------------------------------------------------- \| ------------------------------------- \|
#55	\| `vector_bucket_name` \| The name of the S3 Vector bucket to use. It will be created if it doesn't exist. \| Required \|
#56	\| `collection_name` \| The name of the vector index within the bucket. \| `mem0` \|
#57	\| `embedding_model_dims` \| Dimensions of the embedding model. Must match your embedder. \| `1536` \|
#58	\| `distance_metric` \| Distance metric for similarity search. Options: `cosine`, `euclidean`. \| `cosine` \|
#59	\| `region_name` \| The AWS region where the bucket and index reside. \| `None` (uses default from AWS config) \|
#60
#61	### IAM Permissions
#62
#63	Your AWS identity (user or role) needs permissions to perform actions on S3 Vectors. A minimal policy would look like this:
#64
#65	```json
#66	{
#67	"Version": "2012-10-17",
#68	"Statement": [
#69	{
#70	"Effect": "Allow",
#71	"Action": "s3vectors:*",
#72	"Resource": "*"
#73	}
#74	]
#75	}
#76	```
#77
#78	For production, it is recommended to scope down the resource ARN to your specific buckets and indexes.
#79

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public