Medical Q&A Assistant

Medquery is designed to help healthcare professionals access accurate, up-to-date medical information quickly and efficiently, and receive patient-specific, evidence-based guidance that supports informed decision-making.

📚Table of Contents

• Project Overview
• Project Documents
• Tech Stack
• Architecture
• Getting Started
• Components
  • Infrastructure
  • Backend
  • Frontend
• Deployment

🎯Project Overview

Medquery is an AI-powered healthcare solution that combines:

• Real-time medical knowledge access
• Patient-specific data integration
• Evidence-based decision support
• Secure healthcare data handling
• FHIR-compliant interoperability

📄Project Documents

PRD

• Product Requirements Document.
  • Product vision and goals
  • User stories and requirements
  • Feature specifications
  • Success metrics

SDD

• Software Design Document.
  • System architecture
  • Technical specifications
  • API documentation

🛠️Tech Stack

Core Technologies

• Frontend: React, TypeScript, Tailwind CSS
• Backend: FastAPI, Python, LangChain
• AI/ML: Google Gemini 2.0 Flash
• Database: PostgreSQL, Firebase
• Infrastructure: GCP, Terraform
• Healthcare: FHIR, HAPI FHIR

🏗️Architecture

High-Level Architecture

Cloud Architecture

🚀Getting Started

Prerequisites

• Python 3.9+
• Node.js 18+
• Google Cloud SDK
• Terraform
• Docker

Quick Start

1. Clone the repository

   git clone https://github.com/your-org/medical-assistant-chatbot.git
   cd medical-assistant-chatbot

2. Set up environment variables

   cp .env.template .env
   # Configure your .env file

3. Start development environment

   # Start infrastructure
   cd infrastructure
   terraform init
   terraform apply
   
   # Start backend
   cd backend
   uv venv
   uv sync
   uvicorn app.main:app --reload
   
   # Start frontend
   cd frontend
   npm install
   npm run dev

🏗️Components

Infrastructure

The infrastructure is hosted on Google Cloud Platform (GCP), designed to ensure scalability, reliability, and healthcare compliance.

Key features:

• Terraform-managed infrastructure
• Multi-environment support
• Automated CI/CD pipelines
• Healthcare compliance

Detailed Infrastructure Documentation

Backend

The backend is a LangChain-powered system providing evidence-based medical answers tailored to individual patients' data.

Key features:

• FHIR integration for patient records
• Real-time medical insights
• Structured and unstructured query support
• Secure data handling

Detailed Backend Documentation

Frontend

A modern, responsive web application built with React and TypeScript.

Key features:

• Real-time chat interface
• Patient data visualization
• Responsive design
• Accessibility compliance

Detailed Frontend Documentation

🚀Deployment

Environments

• Development
• Staging
• Production

Deployment Process

1. Infrastructure deployment
2. Backend deployment
3. Frontend deployment
4. Health checks

Code Standards

• Follow PEP 8 for Python
• Follow ESLint rules for TypeScript
• Write unit tests
• Update documentation