​
Overview

Mem0 includes built-in support for various popular large language models. Memory can utilize the LLM provided by the user, ensuring efficient use for specific needs.

OpenAI

Groq

Together

AWS Bedrock

Litellm

Google AI

Anthropic

Mistral AI

OpenAI Azure

​
OpenAI

To use OpenAI LLM models, you have to set the OPENAI_API_KEY environment variable. You can obtain the OpenAI API key from the OpenAI Platform.

Once you have obtained the key, you can use it like this:

import os
from mem0 import Memory

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

config = {
    "llm": {
        "provider": "openai",
        "config": {
            "model": "gpt-4o",
            "temperature": 0.2,
            "max_tokens": 1500,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
Groq

Groq is the creator of the world’s first Language Processing Unit (LPU), providing exceptional speed performance for AI workloads running on their LPU Inference Engine.

In order to use LLMs from Groq, go to their platform and get the API key. Set the API key as GROQ_API_KEY environment variable to use the model as given below in the example.

import os
from mem0 import Memory

os.environ["GROQ_API_KEY"] = "your-api-key"

config = {
    "llm": {
        "provider": "groq",
        "config": {
            "model": "mixtral-8x7b-32768",
            "temperature": 0.1,
            "max_tokens": 1000,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
TogetherAI

To use TogetherAI LLM models, you have to set the TOGETHER_API_KEY environment variable. You can obtain the TogetherAI API key from their Account settings page.

Once you have obtained the key, you can use it like this:

import os
from mem0 import Memory

os.environ["TOGETHER_API_KEY"] = "your-api-key"

config = {
    "llm": {
        "provider": "togetherai",
        "config": {
            "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
            "temperature": 0.2,
            "max_tokens": 1500,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
AWS Bedrock

​
Setup

  • Before using the AWS Bedrock LLM, make sure you have the appropriate model access from Bedrock Console.
  • You will also need to authenticate the boto3 client by using a method in the AWS documentation
  • You will have to export AWS_REGION, AWS_ACCESS_KEY, and AWS_SECRET_ACCESS_KEY to set environment variables.
import os
from mem0 import Memory

os.environ['AWS_REGION'] = 'us-east-1'
os.environ["AWS_ACCESS_KEY"] = "xx"
os.environ["AWS_SECRET_ACCESS_KEY"] = "xx"

config = {
    "llm": {
        "provider": "aws_bedrock",
        "config": {
            "model": "arn:aws:bedrock:us-east-1:123456789012:model/your-model-name",
            "temperature": 0.2,
            "max_tokens": 1500,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
Litellm

Litellm is compatible with over 100 large language models (LLMs), all using a standardized input/output format. You can explore the available models to use with Litellm. Ensure you set the API_KEY for the model you choose to use.

import os
from mem0 import Memory

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

config = {
    "llm": {
        "provider": "litellm",
        "config": {
            "model": "gpt-3.5-turbo",
            "temperature": 0.2,
            "max_tokens": 1500,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
Google AI

To use Google AI model, you have to set the GOOGLE_API_KEY environment variable. You can obtain the Google API key from the Google Maker Suite

Once you have obtained the key, you can use it like this:

import os
from mem0 import Memory

os.environ["GEMINI_API_KEY"] = "your-api-key"

config = {
    "llm": {
        "provider": "litellm",
        "config": {
            "model": "gemini/gemini-pro",
            "temperature": 0.2,
            "max_tokens": 1500,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
Anthropic

To use anthropic’s models, please set the ANTHROPIC_API_KEY which you find on their Account Settings Page.

import os
from mem0 import Memory

os.environ["ANTHROPIC_API_KEY"] = "your-api-key"

config = {
    "llm": {
        "provider": "litellm",
        "config": {
            "model": "claude-3-opus-20240229",
            "temperature": 0.1,
            "max_tokens": 2000,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
Mistral AI

To use mistral’s models, please Obtain the Mistral AI api key from their console. Set the MISTRAL_API_KEY environment variable to use the model as given below in the example.

import os
from mem0 import Memory

os.environ["MISTRAL_API_KEY"] = "your-api-key"

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

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

​
OpenAI Azure

To use Azure AI models, you have to set the AZURE_API_KEY, AZURE_API_BASE, and AZURE_API_VERSION environment variables. You can obtain the Azure API key from the Azure.

import os
from mem0 import Memory


os.environ["AZURE_API_KEY"] = "your-api-key"

# Needed to use custom models
os.environ["AZURE_API_BASE"] = "your-api-base-url"
os.environ["AZURE_API_VERSION"] = "version-to-use"

config = {
    "llm": {
        "provider": "litellm",
        "config": {
            "model": "azure_ai/command-r-plus",
            "temperature": 0.1,
            "max_tokens": 2000,
        }
    }
}

m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})