LangChain

import os
from mem0 import Memory
from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

# Initialize a LangChain vector store
embeddings = OpenAIEmbeddings()
vector_store = Chroma(
    persist_directory="./chroma_db",
    embedding_function=embeddings,
    collection_name="mem0"  # Required collection name
)

# Pass the initialized vector store to the config
config = {
    "vector_store": {
        "provider": "langchain",
        "config": {
            "client": vector_store
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about 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"})

import { Memory } from "mem0ai/oss";
import { OpenAIEmbeddings } from "@langchain/openai";
import { MemoryVectorStore } from "langchain/vectorstores/memory";

const embeddings = new OpenAIEmbeddings();
const vectorStore = new MemoryVectorStore(embeddings);

const config = {
    "vector_store": {
        "provider": "langchain",
        "config": { "client": vectorStore }
    }
}

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 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." }
]

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