RAG Application
A demo of Retrieval-Augmented Generation (RAG) application with MCP server integration.
what is MCP-RAG?
MCP-RAG is a demo application showcasing Retrieval-Augmented Generation (RAG) with integration to the MCP server, designed to enhance document retrieval and context-aware prompt generation.
how to use MCP-RAG?
To use MCP-RAG, connect to the MCP server using Claude Desktop, Cursor, or your preferred IDE, and utilize the process_query tool to ask questions about the company.
key features of MCP-RAG?
- Integration with MCP server for enhanced functionality
- Document retrieval using vector search with ChromaDB
- Context-aware prompt generation for improved responses
- Integration with LLM APIs for advanced language processing
use cases of MCP-RAG?
- Retrieving relevant documents based on user queries.
- Generating context-aware prompts for better interaction with LLMs.
- Enhancing data retrieval processes in research and data analysis.
FAQ from MCP-RAG?
- What is the purpose of MCP-RAG?
MCP-RAG is designed to demonstrate the capabilities of RAG in conjunction with the MCP server for efficient document retrieval and prompt generation.
- How do I install MCP-RAG?
You can install MCP-RAG by running
pip install -r requirements.txtin your terminal.
- Is there a license for MCP-RAG?
Yes, MCP-RAG is licensed under the MIT License.
RAG Application
A demo of Retrieval-Augmented Generation (RAG) application with MCP server integration.
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
