CoolFace
Apppublic

samueldario/realestate_ai_automated_system

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes
App README

RealEstate Agentic Chat - Backend System

RealEstate AI

A conversational AI backend for NYC real estate, featuring adaptive conversation flows, deterministic slot-filling, and humanized interactions. This system powers a React frontend via HTTP streaming.

Features

  • —🗽 NYC-focused real estate conversations
  • —🤖 Adaptive policy engine for natural interactions
  • —🔍 Slot extraction for multi-field input
  • —💬 Humanized microcopy system
  • —📦 Redis session management
  • —📈 Structured JSON logging

Tech Stack

  • —Backend: Python 3.11, FastAPI
  • —AI: DeepSeek API (OpenAI SDK compatible)
  • —Data: NYM Listings API
  • —Infra: Redis, Docker, AWS ECS
  • —Frontend: React + HTTP Streaming

Getting Started

Prerequisites

  • —Python 3.11+
  • —Redis server
  • —DeepSeek API key

Installation

bash
git clone https://github.com/yourorg/realestate_ai_automated_system.git
cd backend
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Configuration

Create .env file:

env
DEEPSEEK_API_KEY=your_api_key
REDIS_URL=redis://localhost:6379
NYM_API_KEY=your_nym_key
LOG_LEVEL=INFO

Running Locally

bash
uvicorn src.app_factory:create_app --reload

Testing

bash
pytest tests/

Documentation

  • —Architecture Overview
  • —Project Context
  • —Technical Stack
  • —Project Log

Deployment

bash
docker build -t realestate-backend .
docker run -p 8000:8000 realestate-backend

Contributing

  1. 1.Fork the repository
  2. 2.Create your feature branch (git checkout -b feature/amazing-feature)
  3. 3.Commit your changes (git commit -m 'Add some amazing feature')
  4. 4.Push to the branch (git push origin feature/amazing-feature)
  5. 5.Open a pull request

License

MIT License - see LICENSE for details