cmu-l3 / llmlean

LLMs + Lean, on your laptop or in the cloud

LLMLean

LLMlean integrates LLMs and Lean for tactic suggestions, proof completion, and more.

Here's an example of using LLMLean on problems from Mathematics in Lean:

llmlean_example.mp4

You can use an LLM running on your laptop, or an LLM from the Open AI API or Together.ai API:

LLM on your laptop:

1. Install ollama.

2. Pull a language model:

ollama pull wellecks/ntpctx-llama3-8b

3. Add llmlean to lakefile:

require llmlean from git
  "https://github.com/cmu-l3/llmlean.git"

4. Import:

import LLMlean

Now use a tactic described below.

LLM in the cloud (OpenAI):

1. Get an OpenAI API key.

2. Set 2 environment variables:

export LLMLEAN_API=openai
export LLMLEAN_API_KEY=your-openai-api-key

Then do steps (3) and (4) above. Now use a tactic described below.

LLM in the cloud (together.ai):

1. Get a together.ai API key.

2. Set 2 environment variables:

export LLMLEAN_API=together
export LLMLEAN_API_KEY=your-together-api-key

Then do steps (3) and (4) above. Now use a tactic described below.

---

llmstep tactic

Next-tactic suggestions via llmstep "{prefix}". Examples:

• llmstep ""

  

• llmstep "apply "

  

The suggestions are checked in Lean.

llmqed tactic

Complete the current proof via llmqed. Examples:

• 

The suggestions are checked in Lean.

For the best performance, especially for the llmqed tactic, we recommend using the Open AI API.

Demo in PFR

As an example, we provide detailed instructions of using LLMLean in the Polynomial Freiman Ruzsa conjecture formalization. Please see the following:

• PFR

Customization

Please see the following:

• Customization