kartik-mem0
fbb8e71224
Each fix verified against mem0/vector_stores/ source and configs:
- baidu: table_name default mem0_table → mem0 (BaiduDBConfig)
- langchain: TS import mem0ai → mem0ai/oss; fix undefined LangchainVectorStore
variable to use MemoryVectorStore directly
- mongodb: collection_name default mem0_collection → mem0; mongo_uri default
corrected to mongodb://localhost:27017 (MongoDBConfig)
- neon: hnsw default False → True (PGVectorConfig.hnsw = True)
- neptune_analytics: extra name vector_stores → vector-stores (pyproject.toml)
- pgvector: diskann default True → False; hnsw default False → True
(PGVectorConfig)
- upstash-vector: move enable_embeddings inside config: {} block
(UpstashVectorConfig field, not top-level VectorStoreConfig)
- valkey: remove non-existent distance_metric row (not in ValkeyConfig);
fix extra name vector_stores → vector-stores
- vertex_ai: region is required (no default in GoogleMatchingEngineConfig)
- weaviate: install pip install weaviate weaviate-client → weaviate-client
(weaviate is not a separate package)
- overview: update TS supported vector DBs list to reflect actual
mem0-ts/src/oss/src/vector_stores/ files
47 lines
1.6 KiB
Plaintext
47 lines
1.6 KiB
Plaintext
---
|
|
title: "Neptune Analytics"
|
|
description: "Use AWS Neptune Analytics as a vector store in Mem0, combining graph analytics with vector search capabilities."
|
|
---
|
|
# Neptune Analytics Vector Store
|
|
|
|
[Neptune Analytics](https://docs.aws.amazon.com/neptune-analytics/latest/userguide/what-is-neptune-analytics.html/) 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
|
|
|
|
```bash
|
|
pip install mem0ai[vector-stores]
|
|
```
|
|
|
|
## Usage
|
|
|
|
```python
|
|
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:
|
|
|
|
| Parameter | Description | Default Value |
|
|
| --- | --- | --- |
|
|
| `collection_name` | The name of the collection to store the vectors | `mem0` |
|
|
| `endpoint` | Connection URL for the Neptune Analytics service | `neptune-graph://my-graph-identifier` |
|