AI Chat Application with RAG and MCP Servers
@garrardkitchen
An .NET Aspire AI chat application that demonstrates how to chat with custom data (RAG - Event Driven) and context extensions (MCP Server) using an AI language model. .NET Aspire, RAG, Qdrant and MCP Server returning GitLab Groups based on search pattern
Overview
What is AI Chat Application with RAG and MCP Servers?
A .NET Aspire chat application that demonstrates chatting with custom data using event-driven RAG and MCP Server context extensions. It integrates AI language models with Qdrant as the vector store and supports GitHub Models and OpenAI endpoints. Designed for developers exploring AI chat, RAG patterns, and MCP tool integration in .NET.
How to use AI Chat Application with RAG and MCP Servers?
Clone the repository, restore dependencies, and configure user secrets for your chosen AI provider (GitHubModels:Token or ConnectionStrings:openai) and optionally for the GitLab tools (GitLab:Token, GitLab:domain). Run the application from Visual Studio or Visual Studio Code using the provided solution file.
Key features of AI Chat Application with RAG and MCP Servers
- Chat with custom data via RAG and MCP Server tools.
- Supports GitHub Models and OpenAI as AI providers.
- Includes MCP WhoIs and GitLab SearchGroups tools.
- Upload PDFs to use as context for the AI model.
- Dynamically create PDFs from markdown content.
- Uses Qdrant as vector store for event-driven RAG.
Use cases of AI Chat Application with RAG and MCP Servers
- Query an AI model about uploaded PDF documents
