A Blazor Web App and Minimal API for performing RAG (Retrieval Augmented Generation) and vector search using the native VECTOR type in Azure SQL Database and Azure OpenAI.

Lightweight, In-memory, Semantic Search, Text Vector Database to embed in any .NET Application

Semantic search in Unity!

A lightweight implementation of Kernel Memory as a Service

Local Vector Database coded in c# supports Cosine Similarity, Jaccard Dissimilarity as well as Euclidean , Manhattan, ChebyShev and Canberra distances

RAG/StructRAG using SQLite, C# and Ollama

HyperVectorDB – simple. powerful. A local vector database built in C#, engineered for effortless precision. Explore your data using Cosine, Jaccard, Euclidean, Manhattan, Chebyshev, and Canberra distances.

Retrieval Augmented Generation (RAG) using Azure Cognitive Search

🤖 Universal RAG Assistant - A flexible AI knowledge platform powered by Azure OpenAI & Cognitive Search. Instantly customizable for any domain by changing data files. Currently configured as a Belgian Food Pricing Assistant with advanced console UX.

A lightweight, cross-platform .NET library for building RAG (Retrieval-Augmented Generation) pipelines with local embedding models and SQLite vector storage. Perfect for developers who need privacy-focused, offline-capable document search and AI-powered question answering without external API dependencies.

Using Azure OpenAI to demo RAG pattern with Azure Search as storage

SmartRAG is a production-ready .NET 9.0 library that provides a complete Retrieval-Augmented Generation (RAG) solution. Features include multi-provider AI support (OpenAI, Anthropic, Gemini), enterprise vector storage (Qdrant, Redis, SQLite), and intelligent document processing (PDF, Word, Text).

AI-powered RAG assistant, built using a Domain-Driven Design (DDD) approach, helping candidates respond effectively to recruiter AI systems.