Using streamlit, openai 'text-davinci-003'/'gpt-3.5-turbo-instruct' and Langchain to create a program aided language model. They are achieve state of the art results on math word problems. This project is a proof of concept to see if we can make an application to help people with their math problems by using a language model to help them understand the problem better.
Use an LLM -> decompose the problem into runnable steps -> run program in PY IDE -> return results to user.
Learn more by reading the paper or visiting the website.
To install requirements, make a virtual environment and run:
make venv/bin/activate
# activate the virtual environment
source venv/bin/activate
make install
To run the app, make sure you are in the virtual environment and run:
make run
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.