The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Fixed s3 vectors memory initialization issue from configuration (#3481)
Abdullah Irfan9df392b26a18
diff --git a/docs/components/vectordbs/dbs/s3_vectors.mdx b/docs/components/vectordbs/dbs/s3_vectors.mdxindex 8faf09b46..47be4fb83 100644--- a/docs/components/vectordbs/dbs/s3_vectors.mdx+++ b/docs/components/vectordbs/dbs/s3_vectors.mdx@@ -28,7 +28,7 @@ config = {"provider": "s3_vectors","config": {"vector_bucket_name": "my-mem0-vector-bucket",- "index_name": "my-memories-index",+ "collection_name": "my-memories-index","embedding_model_dims": 1536,"distance_metric": "cosine","region_name": "us-east-1"@@ -50,13 +50,13 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})Here are the available parameters for the `s3_vectors` config:-| Parameter | Description | Default Value |-| ---------------------- | -------------------------------------------------------------------- | ------------- |-| `vector_bucket_name` | The name of the S3 Vector bucket to use. It will be created if it doesn't exist. | Required |-| `index_name` | The name of the vector index within the bucket. | `mem0` |-| `embedding_model_dims` | Dimensions of the embedding model. Must match your embedder. | `1536` |-| `distance_metric` | Distance metric for similarity search. Options: `cosine`, `euclidean`. | `cosine` |-| `region_name` | The AWS region where the bucket and index reside. | `None` (uses default from AWS config) |+| Parameter | Description | Default Value |+| ---------------------- | -------------------------------------------------------------------------------- | ------------------------------------- |+| `vector_bucket_name` | The name of the S3 Vector bucket to use. It will be created if it doesn't exist. | Required |+| `collection_name` | The name of the vector index within the bucket. | `mem0` |+| `embedding_model_dims` | Dimensions of the embedding model. Must match your embedder. | `1536` |+| `distance_metric` | Distance metric for similarity search. Options: `cosine`, `euclidean`. | `cosine` |+| `region_name` | The AWS region where the bucket and index reside. | `None` (uses default from AWS config) |### IAM Permissions@@ -64,15 +64,15 @@ Your AWS identity (user or role) needs permissions to perform actions on S3 Vect```json{- "Version": "2012-10-17",- "Statement": [- {- "Effect": "Allow",- "Action": "s3vectors:*",- "Resource": "*"- }- ]+ "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.\ No newline at end of file+For production, it is recommended to scope down the resource ARN to your specific buckets and indexes.diff --git a/mem0/configs/vector_stores/s3_vectors.py b/mem0/configs/vector_stores/s3_vectors.pyindex 95c50f675..4118a4086 100644--- a/mem0/configs/vector_stores/s3_vectors.py+++ b/mem0/configs/vector_stores/s3_vectors.py@@ -5,17 +5,13 @@ from pydantic import BaseModel, ConfigDict, Field, model_validatorclass S3VectorsConfig(BaseModel):vector_bucket_name: str = Field(description="Name of the S3 Vector bucket")- index_name: str = Field("mem0", description="Name of the vector index")- embedding_model_dims: int = Field(- 1536, description="Dimension of the embedding vector"- )+ collection_name: str = Field("mem0", description="Name of the vector index")+ embedding_model_dims: int = Field(1536, description="Dimension of the embedding vector")distance_metric: str = Field("cosine",description="Distance metric for similarity search. Options: 'cosine', 'euclidean'",)- region_name: Optional[str] = Field(- None, description="AWS region for the S3 Vectors client"- )+ region_name: Optional[str] = Field(None, description="AWS region for the S3 Vectors client")@model_validator(mode="before")@classmethoddiff --git a/mem0/vector_stores/s3_vectors.py b/mem0/vector_stores/s3_vectors.pyindex 37b80cb9c..f6504c379 100644--- a/mem0/vector_stores/s3_vectors.py+++ b/mem0/vector_stores/s3_vectors.py@@ -25,14 +25,14 @@ class S3Vectors(VectorStoreBase):def __init__(self,vector_bucket_name: str,- index_name: str,+ collection_name: str,embedding_model_dims: int,distance_metric: str = "cosine",region_name: Optional[str] = None,):self.client = boto3.client("s3vectors", region_name=region_name)self.vector_bucket_name = vector_bucket_name- self.collection_name = index_name+ self.collection_name = collection_nameself.embedding_model_dims = embedding_model_dimsself.distance_metric = distance_metricdiff --git a/tests/vector_stores/test_s3_vectors.py b/tests/vector_stores/test_s3_vectors.pyindex 29b877c0c..e8141e2f5 100644--- a/tests/vector_stores/test_s3_vectors.py+++ b/tests/vector_stores/test_s3_vectors.py@@ -1,6 +1,8 @@+from mem0.configs.vector_stores.s3_vectors import S3VectorsConfigimport pytestfrom botocore.exceptions import ClientError+from mem0.memory.main import Memoryfrom mem0.vector_stores.s3_vectors import S3VectorsBUCKET_NAME = "test-bucket"@@ -17,20 +19,42 @@ def mock_boto_client(mocker):return mock_client+def mock_embedder(mocker):+ mock_embedder = mocker.MagicMock()+ mock_embedder.return_value.embed.return_value = [0.1, 0.2, 0.3]+ mocker.patch("mem0.utils.factory.EmbedderFactory.create", mock_embedder)++ return mock_embedder+++def mock_llm(mocker):+ mock_llm = mocker.MagicMock()+ mocker.patch("mem0.utils.factory.LlmFactory.create", mock_llm)+ mocker.patch("mem0.memory.storage.SQLiteManager", mocker.MagicMock())++ return mock_llm++def test_initialization_creates_resources(mock_boto_client):"""Test that bucket and index are created if they don't exist."""- not_found_error = ClientError({"Error": {"Code": "NotFoundException"}}, "OperationName")+ not_found_error = ClientError(+ {"Error": {"Code": "NotFoundException"}}, "OperationName"+ )mock_boto_client.get_vector_bucket.side_effect = not_found_errormock_boto_client.get_index.side_effect = not_found_errorS3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,region_name=REGION,)- mock_boto_client.create_vector_bucket.assert_called_once_with(vectorBucketName=BUCKET_NAME)+ mock_boto_client.create_vector_bucket.assert_called_once_with(+ vectorBucketName=BUCKET_NAME+ )mock_boto_client.create_index.assert_called_once_with(vectorBucketName=BUCKET_NAME,indexName=INDEX_NAME,@@ -47,7 +71,7 @@ def test_initialization_uses_existing_resources(mock_boto_client):S3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,region_name=REGION,)@@ -56,11 +80,41 @@ def test_initialization_uses_existing_resources(mock_boto_client):mock_boto_client.create_index.assert_not_called()+def test_memory_initialization_with_config(mock_boto_client, mock_llm, mock_embedder):+ """Test Memory initialization with S3Vectors from config."""++ # check that Attribute error is not raised+ mock_boto_client.get_vector_bucket.return_value = {}+ mock_boto_client.get_index.return_value = {}++ config = {+ "vector_store": {+ "provider": "s3_vectors",+ "config": {+ "vector_bucket_name": BUCKET_NAME,+ "collection_name": INDEX_NAME,+ "embedding_model_dims": EMBEDDING_DIMS,+ "distance_metric": "cosine",+ "region_name": REGION,+ },+ }+ }++ try:+ memory = Memory.from_config(config)++ assert memory.vector_store is not None+ assert isinstance(memory.vector_store, S3Vectors)+ assert isinstance(memory.config.vector_store.config, S3VectorsConfig)+ except AttributeError:+ pytest.fail("Memory initialization failed")++def test_insert(mock_boto_client):"""Test inserting vectors."""store = S3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,)vectors = [[0.1, 0.2], [0.3, 0.4]]@@ -94,7 +148,7 @@ def test_search(mock_boto_client):}store = S3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,)query_vector = [0.1, 0.2]@@ -108,10 +162,12 @@ def test_search(mock_boto_client):def test_get(mock_boto_client):"""Test retrieving a vector by ID."""- mock_boto_client.get_vectors.return_value = {"vectors": [{"key": "id1", "metadata": {"meta": "data1"}}]}+ mock_boto_client.get_vectors.return_value = {+ "vectors": [{"key": "id1", "metadata": {"meta": "data1"}}]+ }store = S3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,)result = store.get("id1")@@ -131,7 +187,7 @@ def test_delete(mock_boto_client):"""Test deleting a vector."""store = S3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,)store.delete("id1")@@ -144,13 +200,15 @@ def test_delete(mock_boto_client):def test_reset(mock_boto_client):"""Test resetting the vector index."""# GIVEN: The index does not exist, so it gets created on init and reset- not_found_error = ClientError({"Error": {"Code": "NotFoundException"}}, "OperationName")+ not_found_error = ClientError(+ {"Error": {"Code": "NotFoundException"}}, "OperationName"+ )mock_boto_client.get_index.side_effect = not_found_error# WHEN: The store is initializedstore = S3Vectors(vector_bucket_name=BUCKET_NAME,- index_name=INDEX_NAME,+ collection_name=INDEX_NAME,embedding_model_dims=EMBEDDING_DIMS,)@@ -161,5 +219,7 @@ def test_reset(mock_boto_client):store.reset()# THEN: The index is deleted and then created again- mock_boto_client.delete_index.assert_called_once_with(vectorBucketName=BUCKET_NAME, indexName=INDEX_NAME)+ mock_boto_client.delete_index.assert_called_once_with(+ vectorBucketName=BUCKET_NAME, indexName=INDEX_NAME+ )assert mock_boto_client.create_index.call_count == 2