Ragchatbot MCPServer

🚀 Building a RAG Chatbot with a Local MCP Server

This project implements a Retrieval Augmented Generation (RAG) based chatbot using Streamlit and an MCP server. Users can upload PDF files, and the chatbot extracts relevant information from the PDFs to answer natural language questions. The system leverages OpenAI models, LangChain tools, and an in-memory vector store for efficient document retrieval.

🚀 Quick Start

The project is designed to create a chatbot that can answer questions based on the content of uploaded PDF files. It combines various technologies to achieve efficient document retrieval and answer generation.

✨ Features

• MCP Tool Integration: Utilize MCP for tool orchestration to ensure smooth communication between document indexing, retrieval, and answer generation. Backend tools can be easily extended or replaced with new functionalities.

• PDF Upload and Parsing: Users can upload PDF files, and the system uses PDFPlumberLoader to extract text content.

• Text Chunking: Use RecursiveCharacterTextSplitter to divide the extracted text into smaller parts for efficient indexing and retrieval.

• Document Indexing: Text chunks are indexed into an in-memory vector store, generating embeddings using OpenAIEmbeddings.

• Similarity Search (Cosine Similarity): When a user submits a query, the chatbot performs a similarity search to retrieve the document chunks most relevant to the query.

• Prompt-based Answer Generation: A custom prompt template combines the user's question and the retrieved context, and uses a GPT - 4 powered LLM (via ChatOpenAI) to generate the final answer.

• Interactive Interface: The application uses Streamlit to provide an interactive chat interface, displaying user questions and robot answers.