RAG Application

What is RAG Application?

RAG Application is a demo of Retrieval-Augmented Generation (RAG) that integrates an MCP server. It retrieves relevant documents using vector search with ChromaDB, builds context-aware prompts, and sends them to an LLM API to answer questions about a company.

How to use RAG Application?

Install dependencies with pip install -r requirements.txt, set the OPENAI_API_KEY in a .env file, then connect the MCP server via Claude Desktop, Cursor, or another compatible IDE. Use the process_query tool to ask questions about the company.

Key features of RAG Application

• MCP server integration
• Document retrieval using vector search with ChromaDB
• Context-aware prompt generation
• Integration with LLM APIs

Use cases of RAG Application

• Ask questions about a company using its stored documents
• Integrate retrieval-augmented generation into MCP‑compatible tools (e.g., Claude Desktop, Cursor)
• Demonstrate a RAG pipeline with vector search and LLM API calls

FAQ from RAG Application

What does the RAG Application do?

It is a demo of Retrieval-Augmented Generation that uses an MCP server to answer questions about a company by retrieving relevant documents and generating context‑aware responses.

How do I install the RAG Application?

Run pip install -r requirements.txt in the project directory to install all dependencies.

How do I configure the RAG Application?

Create a .env file and set your OPENAI_API_KEY to authenticate with the LLM API.

How do I query the RAG Application?

Connect the MCP server to a supported client (Claude Desktop, Cursor, etc.) and use the process_query tool to ask questions about the company.

What tools or IDEs are supported?

The MCP server can be connected with Claude Desktop, Cursor, or any other IDE that supports the Model Context Protocol.