Ollama - Mem0

Usage

You can use LLMs from Ollama to run Mem0 locally. These models support tool calling.

Python

import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "your-api-key" # for embedder

config = {
    "llm": {
        "provider": "ollama",
        "config": {
            "model": "mixtral:8x7b",
            "temperature": 0.1,
            "max_tokens": 2000,
        }
    }
}

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"})

TypeScript

import { Memory } from 'mem0ai/oss';

const config = {
  llm: {
    provider: 'ollama',
    config: {
      model: 'llama3.1:8b', // or any other Ollama model
      url: 'http://localhost:11434', // Ollama server URL
      temperature: 0.1,
    },
  },
};

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" } });

Config

All available parameters for the ollama config are present in Master List of All Params in Config.