🏛️ KEMET is an AI-powered smart tourism platform for Egypt. It features a Voice-to-Booking AI agent, real-time translation, and an intelligent monument identification system built to provide a seamless travel experience.
# 🏺 KEMET: Voice-to-Booking AI Assistantِ
### *Intelligent Conversational Agent for Smart Egyptian Tourism*
---
## 📖 Overview
**KEMET** (كيميت) is a sophisticated **Voice-First AI Agent** designed to modernize the tourism experience in Egypt. Built with **Cohere's Command-R+** and **OpenAI's Whisper**, the system acts as a digital concierge that understands natural voice commands to recommend hotels, provide historical context, and automate the entire booking process from voice to email voucher.
### 🎙️ The Voice-First Revolution
Unlike traditional booking apps, Kemet focuses on **Natural Human Interaction**:
* **Zero-UI Dependency**: Users can complete a full booking cycle just by speaking.
* **Context-Aware Reasoning**: The system doesn't just search; it "reasons" why a specific hotel fits the user's spoken request.
---
github.com
## 🏗️ Project Structure
```bash
kemet/ # Root Directory
├── 📂 venv/ # Virtual Environment
├── 🐍 app.py # Main Streamlit UI & Session Management
├── 🐍 logic.py # Core AI Pipeline (Whisper & LLM Logic)
├── 📄 hotels.json # Structured Database of Egyptian Tourism
├── 📄 .env # Secret Configuration (API Keys & SMTP)
├── 📄 .gitignore # Git Exclusion Rules
├── 📄 README.md # Professional Documentation
└── 📦 requirements.txt # Project Dependencies Manifest
```
---
## 🧠 Advanced AI Pipeline
The system ensures a seamless user journey through a multi-stage intelligent workflow:
1. **Acoustic Processing**: Utilizes `OpenAI Whisper (Base)` to transcribe live microphone input into high-quality text, handling diverse accents and background noise.
2. **Intent & Entity Extraction**: Employs `Cohere's Command-R` to parse the user's speech and extract key entities like **Location**, **Hotel Category**, and **Preferences**.
3. **Reasone …