goobolabs/dastuur-agent

An intelligent AI-powered assistant that helps users understand and navigate the Somali Provisional Constitution. # 🇸🇴 Dastuur Agent - Somali Constitution AI Assistant An intelligent AI-powered assistant that helps users understand and navigate the Somali Provisional Constitution. Built with Next.js, Google Gemini, and Memvid AI. --- ## ✨ Features ### 🤖 **AI-Powered Constitutional Assistant** - Natural language understanding in Somali - Accurate answers based on the Somali Provisional Constitution - Context-aware responses using RAG technology ### 💬 **Advanced Chat Interface** - **Multi-chat support** - Create and manage multiple conversation threads - **Chat history** - Persistent storage using localStorage - **Sidebar navigation** - Easy access to all your conversations - **Real-time responses** - Streaming AI responses with loading indicators - **Markdown support** - Rich text formatting in responses ### 🎨 **Premium UI/UX** - Modern, glassmorphic design - Smooth animations and transitions - Responsive layout for all devices - Dark mode ready - Accessible and user-friendly interface ### 🔍 **Intelligent Search** - Hybrid search combining vector embeddings and keyword matching - Special optimization for article number queries (e.g., "Qodobka 3aad") - Contextual relevance scoring - Top-K retrieval for accurate results --- ## 🚀 Getting Started ### Prerequisites - **Node.js** 18.x or higher - **npm** or **yarn** - **Google Gemini API Key** (Get one here) ### Installation 1. **Clone the repository** ```bash git clone github.com cd Dastuur-agent- ``` 2. **Install dependencies** ```bash npm install ``` 3. **Set up environment variables** Create a `.env` file in the root directory: ```env GEMINI_API_KEY=your_gemini_api_key_here ``` 4. **Prepare the knowledge base** Place your Somali Constitution PDF in the `pdf/` directory: ``` pdf/Dastuurka_KMG_Soomaaliya.pdf ``` 5. **Generate embeddings** Run the ingestion script to process the PDF and create embeddings: ```bash npm run ingest ``` This will: - Extract text from …