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
51 lines
1.7 KiB
Plaintext
51 lines
1.7 KiB
Plaintext
---
|
||
title: "Weaviate"
|
||
description: "Use Weaviate as an open-source vector search engine in Mem0 for storing and retrieving vector embeddings."
|
||
---
|
||
[Weaviate](https://weaviate.io/) is an open-source vector search engine. It allows efficient storage and retrieval of high-dimensional vector embeddings, enabling powerful search and retrieval capabilities.
|
||
|
||
|
||
### Installation
|
||
```bash
|
||
pip install weaviate-client
|
||
```
|
||
|
||
### Usage
|
||
|
||
```python Python
|
||
import os
|
||
from mem0 import Memory
|
||
|
||
os.environ["OPENAI_API_KEY"] = "sk-xx"
|
||
|
||
config = {
|
||
"vector_store": {
|
||
"provider": "weaviate",
|
||
"config": {
|
||
"collection_name": "test",
|
||
"cluster_url": "http://localhost:8080",
|
||
"auth_client_secret": None,
|
||
}
|
||
}
|
||
}
|
||
|
||
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 movie? 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"})
|
||
```
|
||
|
||
### Config
|
||
|
||
Here are the parameters available for configuring Weaviate:
|
||
|
||
| Parameter | Description | Default Value |
|
||
| --- | --- | --- |
|
||
| `collection_name` | The name of the collection to store the vectors | `mem0` |
|
||
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
|
||
| `cluster_url` | URL for the Weaviate server | `None` |
|
||
| `auth_client_secret` | API key for Weaviate authentication | `None` | |