Progress: currently working on it and due to our limited quota in Azure, I will close the server on 25/2/2025

Frontend repo

APK Link

View Demo

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Progress
4. Contact

About The Project

This project is a chatbot for furniture recommendation using multi-agents. It integrates multiple AI technologies to provide an intelligent and interactive experience for users. The recommendation system works through both text and image inputs, allowing users to describe their preferences or upload images to receive personalized furniture suggestions.

Built With

Getting Started

Prerequisites

Ensure you have the following installed:

• Python 3.12
• FastAPI
• Uvicorn
• Pinecone client
• Kotlin (for mobile app development)

Installation

1. Clone the repository:

   git clone https://github.com/MohamedSameh410/AI-driven-furniture-recommendation.git
   cd AI-driven-furniture-recommendation

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install dependencies:

   pip install -r requirements.txt

4. Run the FastAPI backend:

   uvicorn main:app --host 0.0.0.0 --port 8000

Progress

• Scrape IKEA data
• Implement image captioning with Florence-2-large
• Convert images to 3D models with TRELLIS
• Integrate embedding search using Pinecone
• Develop AI agents with CrewAI
• Recommend an item from an image.
• Deploy backend on Azure
• Develop Kotlin mobile app
• Improve chatbot responses with fine-tuned Gemini LLM
• Add multilingual support
  • Arabic

Project Link