Weaviate

pip install weaviate-client

npm install weaviate-client

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"})

import { Memory } from "mem0ai/oss";

const config = {
  vectorStore: {
    provider: "weaviate",
    config: {
      collectionName: "test",
      embeddingModelDims: 1536,
      clusterUrl: "http://localhost:8080",
    },
  },
};

const memory = new Memory(config);

const 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.",
  },
];

await memory.add(messages, {
  userId: "alice",
  metadata: {
    category: "movies",
  },
});