ReConECT_UI

Re-ConECT: text-based Rehabilitation AI Chatbot for Continuous function evaluation & customized training



This repository shows methods to make chatbot UI based on Upstage APIs, Flask backend and React frontend.
3rd Prize winning project in 2024 Upstage Hackathon.
contact [email protected] if you have any questions or request for RAG database (db_data, rag_data, diagnosis_json_data folder).

Model development by @SeungHoJUN (NLP researcher)
Web design and Domain knowledge application by @yunnii-c (M.D.)
Web development and Domain knowledge application by @oskumd2 (M.D.)

How to develop the app in your local environment

Dowload db_data, rag_data, diagnosis_json_data folder on your root directory

Manually set virtual environment in folder venv by running the following code in your terminal:
Mac: python3 -m venv venv
Windows: python -m venv venv

Activate virtual environment in your terminal (may have to change Setting in Powershell to execute):
Mac: source venv/bin/activate
Windows: .\venv\Scripts\activate

Install requirements by running pip install -r requirements.txt on your terminal.

Create "chatbot-ui" directory to manage React frontend
npx create-react-app chatbot-ui

migrate /src folder under ./chatbot-ui/src/ and put package.json under ./chatbot-ui
Add app.py backend file, ReConECT_v2.py, .nev, Procfile under root directory

How to deploy on server

under virtual environment run following code:

[backend terminal]
heroku login
git init
git add .env app_v2.py Procfile Re_ConECT_v2.py requirements.txt db_data rag_data
git commit -m 'ReConECT'
heroku git:remote -a reconect
heroku buildpacks:set heroku/python
git push heroku master

[frontend terminal]
(exit from venv) cd chatbot-ui
(add newly created heroku app link to constant variable 'herokulink' in Chatbot_v2.py)
npm run build
copy all files in ./chatbot-ui/build/ to oskumd2.github.io repository (or own own Github pages repository)