matt-bentley/LLM-RAG-Architecture
Production-grade Retrieval Augmented Generation (RAG) architecture using Open Source components
Implements hybrid search combining dense embeddings (BAAI/bge-small-en-v1.5) with BM25 sparse vectors through Reciprocal Rank Fusion in Qdrant, plus cross-encoder reranking for result quality. Built on .NET with Semantic Kernel orchestration, integrating FastAPI Python services for embeddings and reranking, with support for multiple LLM backends (Azure OpenAI, OpenAI, Ollama) and PdfPig-based document extraction strategies.
Stars
27
Forks
7
Language
C#
License
MIT
Category
Last pushed
Jan 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/matt-bentley/LLM-RAG-Architecture"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nashtech-garage/ntg-agent
A sample Chatbot in C# using Microsoft Agent Framework
shuyu-labs/AntSK
An AI knowledge base/agent built with .Net 9, AntBlazor, Semantic Kernel, and Kernel Memory,...
wisedev-code/MaIN.NET
NuGet package designed to make LLMs, RAG, and Agents first-class citizens in .NET
Azure-Samples/azure-ai-search-multimodal-sample
A sample app for the Multimodal Retrieval-Augmented Generation pattern running in Azure, using...
tryAGI/Ollama
Ollama SDK for .NET