Description

This feature adds a graph_store option to connect to Amazon Neptune clusters (Neptune DB). Neptune DB is more permanent storage than Neptune Analytics, which may be preferable in certain cases. However, Neptune DB lacks vector storage - and for this reason, when configured in mem0, the graph_store will store edge vectors in the vector_store.

Amazon Neptune DB can be configured, for example:
note: That collection_name is available for both the vector and graph stores.

config = {
    "embedder": {
        "provider": "aws_bedrock",
        "config": {
            "model": bedrock_embedder_model,
        }
    },
    "llm": {
        "provider": "aws_bedrock",
        "config": {
            "model": bedrock_llm_model,
            "temperature": 0.1,
            "max_tokens": 2000
        }
    },
    "vector_store": {
        "provider": "opensearch",
        "config": {
            "collection_name": "mem0ai_vector_store",
            "host": opensearch_host,
            "port": opensearch_port,
            "http_auth": auth,
            "embedding_model_dims": embedding_model_dims,
            "use_ssl": True,
            "verify_certs": True,
            "connection_class": RequestsHttpConnection,
        },
    },
    "graph_store": {
        "provider": "neptunedb",
        "config": {
            "collection_name": "mem0ai_neptune_vector_store",
            "endpoint": f"neptune-db://{neptune_host}",
        },
    },
}

Type of change

• New feature (non-breaking change which adds functionality)

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

Please delete options that are not relevant.

• Unit Test: tests/memory/test_neptune_memory.py
• Test Script: examples/graph-db-demo/neptune-example.ipynb

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules
• I have checked my code and corrected any misspellings

Maintainer Checklist

• closes #xxxx (Replace xxxx with the GitHub issue number)
• Made sure Checks passed