Multi-Modal RAG for .NET — query databases, documents, images & audio in natural language

dotnet add package SmartRAG

builder.Services.UseSmartRAG(builder.Configuration,
    aiProvider: AIProvider.OpenAI,
    storageProvider: StorageProvider.InMemory
);

{
  "SmartRAG": {
    "DatabaseConnections": [
      {
        "Name": "Sales",
        "ConnectionString": "Server=localhost;Database=Sales;...",
        "DatabaseType": "SqlServer"
      }
    ]
    }
}

// Upload document
var document = await documentService.UploadDocumentAsync(
    fileStream, fileName, contentType, "user-123"
);

// Query across databases and documents
var response = await searchService.QueryIntelligenceAsync(
    "Show me all customers who made purchases over $10,000 in the last quarter, their payment history, and any complaints or feedback they provided"
);
// → AI automatically queries SQL Server (orders), MySQL (payments), PostgreSQL (customer data), 
//   analyzes uploaded PDF contracts, OCR-scanned invoices, and transcribed call recordings

Want to test SmartRAG immediately? → Jump to Examples & Testing

🎯 Multi-Database RAG - Query multiple databases simultaneously with natural language

🧠 Multi-Modal Intelligence - PDF, Word, Excel, Images, Audio, and more

🏠 100% Local Processing - GDPR, KVKK, HIPAA compliant

🚀 Production Ready - Enterprise-grade, thread-safe, high performance

var answer = await searchService.QueryIntelligenceAsync(
    "Which customers have overdue payments and what's their total outstanding balance?"
);
// → Queries Customer DB, Payment DB, Account DB and combines results
// → Provides comprehensive financial risk assessment for credit decisions

var answer = await searchService.QueryIntelligenceAsync(
    "Show me all patients with diabetes who haven't had their HbA1c checked in 6 months"
);
// → Combines Patient DB, Lab Results DB, Appointment DB and identifies at-risk patients
// → Ensures preventive care compliance and reduces complications

var answer = await searchService.QueryIntelligenceAsync(
    "Which products are running low on stock and which suppliers can restock them fastest?"
);
// → Analyzes Inventory DB, Supplier DB, Order History DB and provides restocking recommendations
// → Prevents stockouts and optimizes supply chain efficiency

• Only .NET library with native multi-database RAG capabilities
• Automatic schema detection across different database types
• 100% local processing with Ollama and Whisper.net
• Enterprise-ready with comprehensive error handling and logging
• Cross-database queries without manual SQL writing
• Multi-modal intelligence combining documents, databases, and AI

SmartRAG provides comprehensive example applications for different use cases:

examples/
├── SmartRAG.API/          # Complete REST API with Swagger UI
└── SmartRAG.Demo/         # Interactive console application

Want to see SmartRAG in action immediately? Try our interactive console demo:

# Clone and run the demo
git clone https://github.com/byerlikaya/SmartRAG.git
cd SmartRAG/examples/SmartRAG.Demo
dotnet run

Prerequisites: You need to have databases and AI services running locally, or use Docker for easy setup.

📖 SmartRAG.Demo README - Complete demo application guide and setup instructions

For the easiest experience with all services pre-configured:

# Start all services (SQL Server, MySQL, PostgreSQL, Ollama, Qdrant, Redis)
docker-compose up -d

# Setup AI models
docker exec -it smartrag-ollama ollama pull llama3.2
docker exec -it smartrag-ollama ollama pull nomic-embed-text

📚 Complete Docker Setup Guide - Detailed Docker configuration, troubleshooting, and management

🔗 Database Management:

• Step 1-2: Show connections & health check
• Step 3-5: Create test databases (SQL Server, MySQL, PostgreSQL)
• Step 6: View database schemas and relationships

🤖 AI & Query Testing:

• Step 7: Query analysis - see how natural language converts to SQL
• Step 8: Automatic test queries - pre-built scenarios
• Step 9: Multi-database AI queries - ask questions across all databases

🏠 Local AI Setup:

• Step 10: Setup Ollama models for 100% local processing
• Step 11: Test vector stores (InMemory, Redis, SQLite, Qdrant)

📄 Document Processing:

• Step 12: Upload documents (PDF, Word, Excel, Images, Audio)
• Step 13: List and manage uploaded documents
• Step 14: Multi-modal RAG - combine documents + databases
• Step 15: Clear documents for fresh testing

Perfect for: Quick evaluation, proof-of-concept, team demos, learning SmartRAG capabilities

📚 Complete Examples & Testing Guide - Step-by-step tutorials and test scenarios

📊 Databases: SQL Server, MySQL, PostgreSQL, SQLite
📄 Documents: PDF, Word, Excel, PowerPoint, Images, Audio
🤖 AI Models: OpenAI, Anthropic, Ollama (local), LM Studio
🗄️ Vector Stores: Qdrant, Redis, SQLite, InMemory

SmartRAG Exclusive Features (*):

• Fallback Providers: Automatic failover to backup AI providers when primary fails
• Retry Policies: Configurable retry with FixedDelay, LinearBackoff, ExponentialBackoff
• Batch Embeddings: Efficient batch processing for multiple texts simultaneously
• Hybrid Search: Semantic + keyword hybrid algorithm (80% semantic, 20% keyword)
• Session Management: Persistent conversation continuity across app restarts
• Cross-DB JOIN: AI-powered intelligent joins across different databases
• Multi-DB RAG: Native multi-database query coordination
• Databases: Native support for SQL Server, MySQL, PostgreSQL, SQLite

This project is licensed under the MIT License - see the LICENSE file for details.

Built with ❤️ by Barış Yerlikaya

Made in Turkey 🇹🇷 | Contact | LinkedIn