65 lines
2.7 KiB
Plaintext
65 lines
2.7 KiB
Plaintext
[Elasticsearch](https://www.elastic.co/) is a distributed, RESTful search and analytics engine that can efficiently store and search vector data using dense vectors and k-NN search.
|
||
|
||
### Installation
|
||
|
||
Elasticsearch support requires additional dependencies. Install them with:
|
||
|
||
```bash
|
||
pip install elasticsearch>=8.0.0
|
||
```
|
||
|
||
### Usage
|
||
|
||
```python
|
||
import os
|
||
from mem0 import Memory
|
||
|
||
os.environ["OPENAI_API_KEY"] = "sk-xx"
|
||
|
||
config = {
|
||
"vector_store": {
|
||
"provider": "elasticsearch",
|
||
"config": {
|
||
"collection_name": "mem0",
|
||
"host": "localhost",
|
||
"port": 9200,
|
||
"embedding_model_dims": 1536
|
||
}
|
||
}
|
||
}
|
||
|
||
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"})
|
||
```
|
||
|
||
### Config
|
||
|
||
Let's see the available parameters for the `elasticsearch` config:
|
||
|
||
| Parameter | Description | Default Value |
|
||
| ---------------------- | -------------------------------------------------- | ------------- |
|
||
| `collection_name` | The name of the index to store the vectors | `mem0` |
|
||
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
|
||
| `host` | The host where the Elasticsearch server is running | `localhost` |
|
||
| `port` | The port where the Elasticsearch server is running | `9200` |
|
||
| `cloud_id` | Cloud ID for Elastic Cloud deployment | `None` |
|
||
| `api_key` | API key for authentication | `None` |
|
||
| `user` | Username for basic authentication | `None` |
|
||
| `password` | Password for basic authentication | `None` |
|
||
| `verify_certs` | Whether to verify SSL certificates | `True` |
|
||
| `auto_create_index` | Whether to automatically create the index | `True` |
|
||
|
||
### Features
|
||
|
||
- Efficient vector search using Elasticsearch's native k-NN search
|
||
- Support for both local and cloud deployments (Elastic Cloud)
|
||
- Multiple authentication methods (Basic Auth, API Key)
|
||
- Automatic index creation with optimized mappings for vector search
|
||
- Memory isolation through payload filtering
|