This project provides an educational, step-by-step guide to building a production-ready Retrieval-Augmented Generation (RAG) application. It targets developers seeking to understand the practical implementation of RAG systems, offering detailed explanations through Arabic YouTube videos and accompanying code branches.

How It Works

The project guides users through building a RAG pipeline that integrates FastAPI for the backend, MongoDB for data storage, and potentially PostgreSQL with PgVector for semantic search. It covers essential components like file processing, data ingestion, LLM integration (including local Ollama), and database migrations using SQLAlchemy and Alembic. The architecture emphasizes modularity and clear explanations for each stage of development.

Quick Start & Requirements

• Install: pip install -r requirements.txt
• Prerequisites: Python 3.10, libpq-dev, gcc, python3-dev (for PostgreSQL integration). Docker is used for running MongoDB and other services.
• Setup: Requires setting environment variables (e.g., OPENAI_API_KEY) via a .env file. Docker Compose is used to launch services.
• Docs: YouTube Playlist (Note: The provided link is a placeholder and may not be the actual playlist). The POSTMAN collection is available at /assets/mini-rag-app.postman_collection.json.

Highlighted Details

• Comprehensive coverage from basic setup to advanced features like vector databases and local LLM integration.
• Step-by-step video explanations in Arabic.
• Demonstrates migration from MongoDB to PostgreSQL with PgVector.
• Utilizes FastAPI for building the API.

Maintenance & Community

The project is maintained by bakrianoo. Further community or roadmap information is not detailed in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not addressed.

Limitations & Caveats

The project is described as educational, and the primary content (video explanations) is in Arabic. The README does not provide benchmarks or performance metrics.