Supporting LLM routing by integrating Not Diamond

[devanshrj]

🚀 The feature

For mem0, we would like to add our model router as a component in your library, so that users can automatically route their prompts without relying on complex business logic. I believe Not Diamond might fit in using something like this approach, but what do you think? I'm happy to take on this work if you're open to it.

config = {
    "llm": {
        "provider": "notdiamond",
        "config": [{
            "model": "openai/gpt-4o",
            "temperature": 0,
            "max_tokens": 8000,
        },
        {
            "model": "anthropic/claude-3-5-sonnet-20240620",
            "temperature": 0,
            "max_tokens": 8000,
        }]
    },
}

# Initialize Memory with the configuration
m = Memory.from_config(config)

# Add a memory
m.add("I'm visiting Paris", user_id="john")

# Retrieve memories
memories = m.get_all(user_id="john")

Motivation, pitch

Hi there! I am a big fan of mem0 and would love to integrate Not Diamond into it. Not Diamond automatically routes your prompts to the AI model best-suited to respond to that prompt. By using Not Diamond as an AI “meta-model,” you can achieve state-of-the-art performance that beats every foundation model on every major benchmark.*

*If you’d like to learn more about our routing, check out this example walkthrough video with Tomas, our CEO. You can also

• see how we work by using our Chat app,
• learn more at our website, or
• read our docs.