Giter Site home page Giter Site logo

move-me's Introduction

πŸƒβ€β™€οΈ MOVE ME

πŸ”₯ Motivation

I'm passionate and enthusiastic about both sports and AI. When ChatGPT was announced in November 2022, and later the API, I immediately started to ideate how such technology could expand my experience with sports. The thing I love the most about crossfit is how different is it everyday. So, what if anyone who is at home can experience the same? One click, less excuses not to move

πŸ‘©β€πŸ’» Implementation

As a data scientist, I work with Python everyday, so the choice became easy. I also wanted to test some new features of Streamlit, such as the multipage and hosting a dashboard in Streamlit Cloud. ChatGPT has shown us that the UI is key for people to actually use and benefit from the techonology, then Streamlit makes even more sense. Let's go πŸš€

πŸ€– Features

πŸ‹οΈ Crossfit

generate your workout of the day. "For time" means you need to complete the workout in the minimum amount of time. "AMRAP" = "As many repetitions as possible" means you have a fixed amount of time and need to complete as many rounds and/or repetitions possible.

πŸƒβ€β™€οΈ Running

generate a training plan for a specific distance and calendar

🧘 Yoga

generate a yoga workout by choosing your favorite type of yoga and the ideal time frame

πŸƒβ€β™€οΈ (literally) running it

Local Setup

  1. Clone the repo git clone https://github.com/filipafcastro/move-me.git

  2. Create a virtual environment

python -m venv env
  1. Activate your virtual environment
# Linux:

source env/bin/activate

# Windows

env\Scripts\activate.bat
  1. Install the requirements pip install -r requirements.txt

  2. Fill the file .streamlit/credentials.toml with your own OpenAI API Key

  3. Run streamlit streamlit run πŸ‹οΈ_crossfit.py

Streamlit Cloud

  1. Fork the repo to your github account

  2. Follow the steps to create a Community Cloud account in Streamlit and connect it to your GitHub: https://docs.streamlit.io/streamlit-community-cloud/get-started

  3. Set up the OpenAI API Key in the Cloud app: https://docs.streamlit.io/streamlit-community-cloud/get-started/deploy-an-app/connect-to-data-sources/secrets-management

  4. Launch the app πŸš€

πŸ“ˆ Improvements

  • Prompt engineering to get better answers
  • Finetuning on known wods
  • Additional sports

move-me's People

Contributors

filipafcastro avatar

Watchers

 avatar

move-me's Issues

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.