hassetshi/amharic-chatbot

# 🇪🇹 Multimodal Amharic Chatbot A beautiful web application that combines **YOLOv8 object detection** with **Google Gemini AI** to create an intelligent chatbot that understands and responds in **Amharic (አማርኛ)** using Ge'ez script. ## ✨ Features - 🖼️ **Image Upload & Object Detection**: Upload images and detect objects using YOLOv8 - 🔍 **Real-time Object Detection**: Powered by state-of-the-art YOLOv8 model - 💬 **Amharic Chat Interface**: Full support for Amharic text in Ge'ez script - 🤖 **AI-Powered Responses**: Google Gemini generates fluent, natural Amharic responses - 🎨 **Beautiful UI**: Clean, modern Streamlit interface with Ethiopian colors - 🌐 **Multimodal Understanding**: Combines visual and textual information ## 🎯 Use Cases - Educational tool for Ethiopian students learning about AI - Accessibility tool for Amharic speakers - Object recognition with Amharic descriptions - Cultural heritage preservation through language technology - Research and development in low-resource language NLP ## 📋 Prerequisites - Python 3.8 or higher - Google API Key (for Gemini) - Webcam or image files for testing ## 🚀 Installation ### 1. Clone or download this project ```bash cd amharic-chatbot ``` ### 2. Create a virtual environment ```bash # Create virtual environment python -m venv venv # Activate virtual environment # On macOS/Linux: source venv/bin/activate # On Windows: venv\Scripts\activate ``` ### 3. Install dependencies ```bash pip install -r requirements.txt ``` ### 4. Get Google API Key 1. Go to Google AI Studio 2. Sign in with your Google account 3. Create a new API key 4. Copy the API key ### 5. Configure environment variables ```bash # Copy the example environment file cp .env.example .env # Edit .env and add your Google API key # Replace 'your_google_api_key_here' with your actual API key ``` Your `.env` file should look like: ``` GOOGLE_API_KEY=AIzaSyD...your_actual_k …