Weaviate 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

pip install weaviate weaviate-client

​
Usage

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

Let’s see the available parameters for the weaviate config:

ParameterDescriptionDefault Value
collection_nameThe name of the collection to store the vectorsmem0
embedding_model_dimsDimensions of the embedding model1536
cluster_urlURL for the Weaviate serverNone
auth_client_secretAPI key for Weaviate authenticationNone