store with DynamoDB

[5enxia]

Package

langchain-checkpoint-aws

Checked other resources

• I added a descriptive title to this issue
• I searched the LangChain documentation with the integrated search
• I used the GitHub search to find a similar issue and didn't find it
• I am sure this is a feature request and not a bug report or question

Feature Description

memory store with DynamoDB

Use Case

There is already an implementation of store memory using Valkey, but there are cases where high read and write performance and vector store are not required.
I think it would be useful to have store memory using DynamoDB for such cases.

Proposed Implementation (optional)

from langgraph_checkpoint_aws import DynamoDBStore

# Basic usage
with DynamoDBStore.from_conn_string(
    "table-name",
) as store:
    # Setup vector search index
    store.setup()
    
    # Store documents
    store.put(
        ("documents", "user123"),
        "report_1",
        {
            "text": "Machine learning report on customer behavior analysis...",
            "tags": ["ml", "analytics", "report"],
            "author": "data_scientist"
        }
    )
    
    # get documents
    results = store.get(
        ("documents", "user123"),
        "report_1"
    )

Additional Context

related works

There is already an implementation by skamalj, but it is unmaintained and support from the community would be greatly appreciated.

boto3 dynamodb

https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb.html

LangGraph's BaseStore

https://github.com/langchain-ai/langgraph/blob/main/libs/checkpoint/langgraph/store/base/__init__.py