Logo Lanfrica

DRAVIS55/Ubuntu-News-Intelligence

Domaine:

natural language processing

Type de record:

software
Créateur:
DRA
Hôte:
An AI-powered African news intelligence platform that transforms news into contextual insights using Retrieval-Augmented Generation (RAG), semantic search, knowledge graphs, trend detection, and historical analysis. Built for journalists, researchers, policymakers, and media organizations. # African News Intelligence Platform > A sovereign, Africa-native AI system that understands news the way an African journalist thinks — with historical memory, regional context, and the ability to connect dots across time, countries, and economic realities. --- ## Quick Start ### Prerequisites - Python 3.10+ - 8GB RAM minimum (16GB recommended for local model) - Optional: CUDA GPU for faster inference ### Installation ```bash # Clone the repo git clone github.com cd african-news-intel # Create virtual environment python -m venv venv source venv/bin/activate # Linux/Mac # venv\Scripts\activate # Windows # Install dependencies pip install -r requirements.txt # Download spaCy model python -m spacy download en_core_web_sm # Set up environment cp .env.example .env # Edit .env with your API keys (see Configuration section) # Initialize the database python scripts/init_db.py # Seed sample data python scripts/seed_data.py # Start the platform python run.py ``` Open localhost --- ## Architecture ``` african-news-intel/ ├── ingestion/ # Layer 1: Data ingestion & archive │ ├── scraper.py # RSS + web scraper │ ├── embedder.py # Vector embedding generator │ └── scheduler.py # Cron-based ingestion scheduler │ ├── intelligence/ # Layer 2: AI Intelligence Core │ ├── rag.py # Retrieval-Augmented Generation engine │ ├── relations.py # Relation & knowledge graph engine │ ├── comparisons.py # Peer country comparison engine │ ├── patterns.py # Trend & pattern detection │ └── llm.py # LLM abstraction layer │ ├── core/ # Shared utilities │ ├── database.py # PostgreSQL + ChromaDB connectors │ ├── models.py # SQLAlchemy data models │ └── config.py # Configuration management │ ├── api/ # Layer 4: REST API │ ├── routes.py # All API endpoints │ └── middleware.py # Auth, rate limiting, …