mcpField
R
RAG Application

RAG Application

Local
github.com/hulk-phamMemory & Knowledge1Updated 81w ago
Repository

About RAG Application

RAG Application is a demo of retrieval-augmented generation that combines ChromaDB vector search, context-aware prompt generation, and LLM APIs. Users can query company-related content through an MCP client.

Key features

  1. 01Retrieve documents with ChromaDB vector search
  2. 02Generate context-aware prompts
  3. 03Integrate LLM APIs
  4. 04Provide a process_query query tool

Use cases

  1. 01Ask natural-language questions about company documents
  2. 02Generate contextual prompts from retrieved content

MCP support

The application integrates an MCP server and provides a process_query tool for client queries. The README names Claude Desktop, Cursor, and other IDEs as connection options.

#rag#chromadb#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

RAG Application

A demo of Retrieval-Augmented Generation (RAG) application with MCP server integration.

Screenshot

Features

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

Installation

pip install -r requirements.txt

Usage

Connect to the MCP server with Claude Desktop, Cursor, or your preferred IDE.

Use the process_query tool to ask questions about the company.

Configuration

Set up your environment variables in .env:

OPENAI_API_KEY=your_api_key

Project Structure

app/retrieval.py: Document retrieval functionality app/context.py: Context management app/llm_client.py: LLM API integration app/prompt_builder.py: Prompt construction

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.