Milvus Milvus is an open-source vector database that suits AI applications of every size from running a demo chatbot in Jupyter notebook to building web-scale search that serves billions of users.
Usage
import os
from mem0 import Memory
config = {
"vector_store": {
"provider": "milvus",
"config": {
"collection_name": "test",
"embedding_model_dims": "123",
"url": "127.0.0.1",
"token": "8e4b8ca8cf2c67",
}
}
}
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
Here’s the parameters available for configuring Milvus Database:
| Parameter | Description | Default Value |
|---|
url | Full URL/Uri for Milvus/Zilliz server | http://localhost:19530 |
token | Token for Zilliz server / for local setup defaults to None. | None |
collection_name | The name of the collection | mem0 |
embedding_model_dims | Dimensions of the embedding model | 1536 |
metric_type | Metric type for similarity search | L2 |
