Skip to content

MANVITH7/Realibot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🏠 RealiBot – AI-Powered Real Estate Assistant

RealiBot is a full-stack AI chatbot web application built using Python (Flask) and JavaScript. It helps first-time homebuyers and property investors get real estate insights, such as:

  • Median home prices and rent yields (by U.S. state or city)
  • Profit/loss and ROI estimates
  • Financing, legal, and tax advice
  • General real estate Q&A

The AI model is powered by OpenAI’s GPT API, wrapped with custom prompts.


📁 Project Structure

Realibot/
├── backend/
│   └── app.py               # Flask backend
├── public/
│   └── index.html           # Landing page
│   └── chat.html            # Chat UI
├── .gitignore
├── README.md
├── package.json             # Frontend dependencies (optional)

⚙️ Features

  • Ask questions about real estate (e.g., prices, taxes, ROI)
  • AI-powered responses via OpenAI GPT
  • Lightweight frontend (HTML/CSS/JS)
  • Backend using Flask API
  • Fully deployable to Render or Netlify + Render combo

Getting Started (Local Setup)

1. Clone the Repository

git clone https://github.com/MANVITH7/Realibot.git
cd Realibot

2. Set Up the Backend

cd backend
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

3. Add Your .env File

Inside the backend/ folder, create a .env file:

OPENAI_API_KEY=sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXX
OPENAI_MODEL=gpt-4

⚠ Never commit .env to GitHub.

4. Run the Flask Server

python app.py

Backend will run at http://127.0.0.1:5000

5. Open Frontend

Open public/index.html directly in your browser or serve using any static server.


Tech Stack

  • Frontend: HTML, CSS, JavaScript
  • Backend: Python Flask
  • AI: OpenAI GPT-4 API

License

This project is open-source and free to use.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published