byerlikaya/SmartRAG
Multi-Modal RAG for .NET — query databases, documents, images and audio in natural language. Production-ready with multi-AI support, vector storage, and multi-database coordination.
Implements intelligent query routing that analyzes intent to determine whether to search databases, documents, or both—merging results across SQL Server, MySQL, PostgreSQL, and document stores with OCR and speech-to-text capabilities. Integrates Model Context Protocol (MCP) servers for external tool extensibility and file watchers for automatic document indexing, while the modular Strategy Pattern architecture supports pluggable SQL dialects and scoring algorithms. Built on .NET 6+ with a bundled production-ready dashboard and 100% local processing for regulatory compliance (GDPR, HIPAA, KVKK).
Stars
21
Forks
7
Language
C#
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/byerlikaya/SmartRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yichuan-w/LEANN
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast,...
mrutunjay-kinagi/ragsearch
This project aims to build a Retrieval-Augmented Generation (RAG) engine to provide...
aws-samples/layout-aware-document-processing-and-retrieval-augmented-generation
Advanced document extraction and chunking techniques for retrieval augmented generation that is...
Omkar-Wagholikar/adora
Python package that makes it easy to spin up a custom Retrieval-Augmented Generation (RAG) pipeline.
leewaay/ragcar
RAGCAR: Retrieval-Augmented Generative Companion for Advanced Research