HealthcareRAGTools

What is HealthcareRAGTools about?

HealthcareRAGTools provides an agentic AI assistant for healthcare professionals. It captures patient symptom entries, compares them with previously logged cases, and searches a curated collection of medical documents. The system leverages Retrieval‑Augmented Generation (RAG) with a Groq‑hosted Llama 3.3 model and stores embeddings in a Chroma vector database.

How to use HealthcareRAGTools?

1. Prerequisites – Windows 10/11, Python 3.8+, UV (pip install uv), and a Groq API key.
2. Create a virtual environment

   uv venv
   ragmcp\Scripts\activate
   

3. Install dependencies

   set UV_LINK_MODE=copy
   uv pip install -r requirements.txt
   

4. Configure the Groq key – add GROQ_API_KEY=your‑groq‑api‑key to the .env file.
5. Initialize the Chroma database

   uv run python setup_db.py
   

6. Run the terminal client

   uv run python healthcare_client.py
   

   Interact with the chat interface to log symptoms or search documents.
7. Optional – run the MCP server for IDE integration

   uv run python server.py
   

   Copy the generated JSON configuration into Cursor → Settings → MCP/MCP Tools.

Key Features

• Symptom logging with severity levels and automatic retrieval of similar past cases.
• Document search across medical PDFs/TXTs using RAG to provide concise, context‑aware answers.
• Groq Llama‑3.3‑70B model integration via LangChain‑Groq for high‑quality language generation.
• Chroma vector store for fast similarity search on embeddings generated by Sentence‑Transformers.
• Terminal‑based client for quick queries and a Cursor IDE agent‑chat integration.
• Configurable via healthcare.json allowing easy adaptation to different datasets or models.

Use Cases

• Clinical decision support: A doctor logs a patient’s fever and cough, receives similar historic cases, and gets relevant guideline excerpts.
• Medical education: Trainees query symptom patterns and instantly retrieve textbook passages.
• Telemedicine triage: Remote clinicians input symptom data and obtain evidence‑based recommendations.
• Research data curation: Researchers add new case reports to the database and instantly make them searchable.

FAQ

• How do I add new medical documents? Place .txt (or supported) files in the documents/ folder and re‑run setup_db.py to refresh the vector store.
• Can I switch to a different LLM? Yes, update the model identifier in healthcare.json and ensure the corresponding API key is available.
• Is my Groq API key secure? The key is stored only in the local .env file, which is excluded via .gitignore.
• What if I need more than the sample data? Populate patient_records.json with additional entries; the server will automatically index them on startup.
• Can I use this on Linux/macOS? The instructions target Windows, but the same steps work on Unix‑like systems with minor path adjustments.

HealthcareRAGTools Project

Overview

The HealthcareRAGTools project is an agentic AI system designed to assist healthcare professionals by leveraging Retrieval-Augmented Generation (RAG) techniques. This project integrates a Model Context Protocol (MCP) server with a Chroma vector database to log patient symptoms, retrieve similar cases, and search medical documents. It supports interactive queries via a terminal-based client and can also be used within the Cursor IDE’s agent chat interface.

Project Description

This project enables the following key functionalities:

1. Log Patient Symptoms: Logs patient symptoms (e.g., "fever and cough") with severity levels (e.g., "Moderate") and retrieves similar cases from a database for comparison.
2. Search Documents: Searches a collection of medical documents (e.g., flu or asthma symptom descriptions) to provide relevant information based on user queries. The system uses the Groq API for natural language processing, with the llama-3.3-70b-versatile model. It is built to support real-time healthcare data management and retrieval, making it a valuable tool for clinical decision support.

Tools Used

The project relies on the following tools and technologies:

Python 3.8+: The primary programming language for scripting and server logic. FastMCP: A modular compute platform framework for building and running agentic systems. LangChain: A library for building context-aware language models and agents. LangChain-Groq: Integration with Groq’s API for advanced language model capabilities. Chroma: An open-source vector database for storing and retrieving embeddings of medical documents and patient data. Sentence-Transformers: Used to generate embeddings for text data in the Chroma database. HTTpx: For handling HTTP requests within the system. Python-Dotenv: Manages environment variables, such as the Groq API key. LangChain-Community: Additional community-supported LangChain tools. Requests: For making HTTP requests to external services. UV: A package and virtual environment manager for dependency management. Cursor IDE: The development environment, with plans to enable agent chat functionality.

Directory Structure

The project is organized as follows:

\Desktop\mcpserver\ragmcp
├── .env # Stores the GROQ_API_KEY environment variable ├── .gitignore # Excludes venv, chroma_db, and .env from version control ├── server.py # Main MCP server script with HealthcareRAGTools logic ├── setup_db.py # Script to initialize the Chroma vector database ├── healthcare_client.py # Terminal-based client for interactive queries ├── healthcare.json # Configuration file for the MCP server ├── requirements.txt # Lists project dependencies ├── documents\ # Directory for sample medical documents │ ├── doc1.txt # Example document: Flu symptoms │ ├── doc2.txt # Example document: Asthma symptoms ├── patient_records.json # JSON file storing patient symptom data ├── chroma_db\ # Directory for the Chroma vector database └── ragmcp\ # Virtual environment directory

Setup and Installation

To set up the project on your local machine, follow these steps:

Prerequisites Windows 10/11 with Command Prompt. Python 3.8+ installed. UV (Universal Virtual Environment) installed: pip install uv. A Groq API key from console.groq.com. Steps Create and Activate the Virtual Environment: uv venv ragmcp\Scripts\activate Confirm the prompt shows (ragmcp). Install Dependencies: Ensure requirements.txt exists with the listed dependencies: set UV_LINK_MODE=copy uv pip install -r requirements.txt Configure Environment Variables: Create or edit .env with your Groq API key: GROQ_API_KEY=your-groq-api-key Initialize the Database: Run the setup script to populate the Chroma database with sample documents: uv run python setup_db.py Expected output: Vector database initialized with sample medical documents. Running the Project Terminal-Based Client Start the Client: uv run python healthcare_client.py Expected Output: Loading environment variables... Loading config file: C:\Users\sniki\OneDrive\Desktop\mcpserver\ragmcp\healthcare.json Initializing HealthcareRAGTools chat... MCPClient initialized ChatGroq initialized

===== Interactive HealthcareRAGTools Chat ===== Type 'exit' or 'quit' to end the conversation Type 'clear' to clear conversation history Example queries:

• Log symptoms for patient P123: fever and cough, severity Moderate, show similar cases
• Search documents for flu symptoms ==================================

You:

Test a Query: Type: Log symptoms for patient P123: fever and cough, severity Moderate, show similar cases Expected response: Assistant: Symptoms logged for Patient P123: 'fever and cough' (Moderate). Similar cases: None Exit: Type exit or quit.

To run it in Cursor's Agent chat:

Copy the json code into File>Preferences>Cursor Settings>MCP/MCP Tools and run the server as follows:

uv run python server.py

You can use the same queries here as well.