Files
t6_mem0/docs/components/vectordbs/dbs/opensearch.mdx

66 lines
2.9 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

[OpenSearch](https://opensearch.org/) is an open-source, enterprise-grade search and observability suite that brings order to unstructured data at scale. OpenSearch supports k-NN (k-Nearest Neighbors) and allows you to store and retrieve high-dimensional vector embeddings efficiently.
### Installation
OpenSearch support requires additional dependencies. Install them with:
```bash
pip install opensearch>=2.8.0
```
### Usage
```python
import os
from mem0 import Memory
os.environ["OPENAI_API_KEY"] = "sk-xx"
config = {
"vector_store": {
"provider": "opensearch",
"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": "Im 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 `opensearch` 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 OpenSearch server is running | `localhost` |
| `port` | The port where the OpenSearch server is running | `9200` |
| `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 | `False` |
| `auto_create_index` | Whether to automatically create the index | `True` |
| `use_ssl` | Whether to use SSL for connection | `False` |
### Features
- Fast and Efficient Vector Search
- Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service.
- Multiple Authentication and Security Methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
- Automatic index creation with optimized mappings for vector search
- Memory Optimization through Disk-Based Vector Search and Quantization
- Real-Time Analytics and Observability