ai-chat-example

The AI Chat Application with RAG and MCP Servers is a .NET Aspire-based solution that allows users to interact with AI models using their own data sources. It leverages Retrieval-Augmented Generation (RAG) for event-driven interactions and Model Context Protocol (MCP) servers for context extensions. The application supports multiple AI providers, including GitHub Models and OpenAI endpoints, and uses Qdrant as the vector store. The solution is structured to include web applications for chat and administration, an MCP server, and a functions app, all designed to be deployed as Azure Container Apps. The application is designed to be flexible, allowing for the integration of various AI models and data sources, making it suitable for a wide range of use cases.

Features

• Interact with AI models using template provided PDFs
• MCP Server WhoIs tool
• MCP Server GitLab SearchGroups tool
• Upload prewritten PDFs for AI interaction
• Dynamically create PDFs from markdown for AI interaction

MCP Tools

• {'WhoIs': 'A tool for querying identity information.'}
• {'GitLab SearchGroups': 'A tool for searching GitLab groups using user secrets.'}

Usage with Different Platforms

dotnet

bash
dotnet new install Microsoft.Extensions.AI.Templates

npx

bash
npx @modelcontextprotocol/inspector dotnet run