Islamic Scholar Agent

A production-ready Islamic knowledge agent built with Agno framework, featuring RAG (Retrieval-Augmented Generation) capabilities for answering questions based on Islamic texts and knowledge.

Project Structure

├── src/                          # Production source code
│   ├── agents/                   # Agent implementations
│   ├── knowledge/                # Knowledge base & RAG pipeline
│   ├── models/                   # LLM integrations
│   ├── api/                      # FastAPI routes
│   ├── core/                     # Core configurations
│   └── utils/                    # Utility functions
├── data/                         # Data files
│   ├── raw/                      # Original data files
│   ├── processed/                # Processed/cleaned data
│   └── embeddings/               # Pre-computed embeddings
├── scripts/                      # Utility scripts
├── tests/                        # Test files
├── config/                       # Configuration files
├── docker/                       # Docker files
└── docs/                         # Documentation

Features

• Islamic Knowledge Focus: Specialized agent for Islamic knowledge queries
• RAG Pipeline: Retrieval-augmented generation using vector databases
• Multiple Vector Stores: Support for Qdrant and PostgreSQL with PgVector
• Modular Architecture: Clean separation of concerns
• Production Ready: Docker support, health checks, logging
• Comprehensive Testing: Unit and integration tests

Quick Start

1. Setup Environment:

   cp .env.example .env
   # Edit .env with your API keys
   

2. Install Dependencies:

   pip install -r requirements.txt
   

3. Setup Vector Database:

   python scripts/setup_vectordb.py
   

4. Ingest Knowledge Data:

   python scripts/ingest_excel.py
   

5. Run Application:

   python src/main.py
   

Development

Running Tests

pytest tests/

Qdrant Connection Test

Test Qdrant vector database connectivity:

python test_qdrant_connection.py

For detailed documentation see: Qdrant Connection Test Guide

Health Check

python scripts/health_check.py

Docker Development

cd docker
docker-compose -f docker-compose.dev.yml up

API Usage

Health Check

curl http://localhost:8081/health

Chat Endpoint

curl -X POST "http://localhost:8081/chat" \
     -H "Content-Type: application/json" \
     -d '{"message": "What is the importance of Islamic knowledge?"}'

Configuration

• Development: config/development.env
• Production: config/production.env
• Models: config/models.yaml

Documentation

• Production Readiness Report
• API Documentation
• Deployment Guide

License

This project is licensed under the MIT License.