📌 Rendezvous Radar

This app allows users to search for activities. Users can manually select activity categories or input a text prompt, which is analyzed by a large language model to generate relevant results.

This app gets POIs, its data, and creates the map using the OpenStreetMap (OSM) API, geocodes and reverse geocodes using the Nominatim API, and utilizes trained DistilGPT2 large language model to predict points of interest via natural language prompts.

🪄 Features

Users can:

• Search for POIs within a range of an address
• Type in a prompt to have the LLM predict the POIs of interest
• Interact with the map and see information about each POI

📸 Screenshots

Run Locally

Install Git LFS

  git lfs install

Clone the project

  git clone git@github.com:rendezvous-radar/RendezvousRadar.git

Go to the project directory

  cd RendezvousRadar

Go to the frontend directory

  cd frontend

Install dependencies

  npm install

Start the server

  npm run dev

In another window in the project open the backend directory

  cd backend

Create a virtual environment

  python -m venv venv

Activate the virtual environment

  # Linux/Mac
  source venv/bin/activate
  # Windows
  venv\Scripts\activate

Install dependencies

  pip install -r requirements.txt

Apply migrations

  python manage.py migrate

Run the dev server

  python manage.py runserver

🔗 Links

Jinha Kim

Jerry Chen

License

MIT