​
Neptune Analytics Vector Store

Neptune Analytics is a memory-optimized graph database engine for analytics. With Neptune Analytics, you can get insights and find trends by processing large amounts of graph data in seconds, including vector search.

​
Installation

pip install mem0ai[vector_stores]

​
Usage

config = {
    "vector_store": {
        "provider": "neptune",
        "config": {
            "collection_name": "mem0",
            "endpoint": f"neptune-graph://my-graph-identifier",
        },
    },
}

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 movies? 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"})

​
Parameters

Let’s see the available parameters for the neptune config:
ParameterDescriptionDefault Value
collection_nameThe name of the collection to store the vectorsmem0
endpointConnection URL for the Neptune Analytics serviceneptune-graph://my-graph-identifier