addo112/afrisearch-scholar

The World's Largest Search Engine for African Research, Innovation, and Knowledge # AfriSearch Scholar AfriSearch Scholar is an AI-powered search engine dedicated to African research, patents, datasets, and grants. It leverages modern web technologies, hybrid search, and LLM-based reranking to provide the most relevant and accurate results for researchers. ## Features - **Hybrid Search**: Combines full-text search with semantic vector search via OpenSearch. - **AI Reranking**: Re-ranks search results using advanced language models to ensure high relevance. - **Comprehensive Data Types**: Search across academic journals, university repositories, patents, datasets, and funding grants. - **Interactive UI**: A highly responsive, modern interface built with Next.js and React. - **Scalable Architecture**: Dockerized and Kubernetes-ready for massive scale. ## Screenshots *(Placeholder for screenshots)* ## Quick Start ### Prerequisites - Node.js 20+ - Python 3.11+ - Docker & Docker Compose ### Local Development Setup 1. **Clone the repository:** ```bash git clone github.com cd afrisearch-scholar ``` 2. **Run the setup script:** - Windows: `.\scripts\setup.ps1` - Linux/Mac: `./scripts/setup.sh` 3. **Start the infrastructure (databases, OpenSearch):** ```bash docker compose up -d ``` 4. **Seed the database:** ```bash ./scripts/seed-data.sh ``` 5. **Open your browser:** Navigate to localhost ## Architecture Overview See Architecture Documentation for detailed information. ## Tech Stack | Component | Technology | | --------- | ---------- | | Frontend | Next.js, React, Tailwind CSS | | Backend | Node.js, Express, Prisma ORM | | AI Service | Python, FastAPI, HuggingFace | | Databases | PostgreSQL, Redis, MongoDB | | Search Engine | OpenSearch | | Infrastructure | Docker, Kubernetes, Vercel, GCP | ## Documentation - API Reference - Deployment Guide - Admin Guide ## Contributing We welcome contributions! Please see our Contributing Guidelines for details on how to get started. ## L …