Valetudo AI is a Perplexity Sonar-powered assistant that delivers science-backed, fast, and clear medical answers. It helps reduce misinformation by providing citations from verified sources — with support for filters by date, country, and even image upload.

The name Valetudo comes from Latin and means “health” 🩺. The project is designed for conscious users seeking reliable medical information: caring parents, patients, and medical students. Ask about symptoms, drug interactions, or safe alternatives — and get trustworthy answers instantly.

Watch Valetudo AI in action 👇:

• Chat with AI using Perplexity Sonar Pro
• Answers with numbered scientific citations
• Limited to 10 trusted sources for clarity
• Filters by date and user location
• Image upload for visual context (e.g. meds or conditions)
• Prompt templates (7 categories) for common medical queries:
  • Symptom-based advice
  • Drug interaction checks
  • Safety timing
  • Safer treatments
  • Compare effectiveness
  • Recommended exercises
  • Latest research
• Follow-up input to clarify or expand your question
• Prioritization of local sources when a country is selected
• Markdown formatting and clean tables
• Easily copy and open source links
• Simple and user-friendly interface

Ask questions. Get trusted answers in seconds.

Upload an image — AI will analyze it too.

• Frontend: React, Vite, Tailwind CSS
• AI Integration: Perplexity Sonar Pro API
• Markdown Renderer: React Markdown, rehype-raw
• UI Framework: React Select, React Icons, React Datepicker
• Image handling: base64 encoder and preview
• Backend: Python, Flask (proxy for API calls)

git clone https://github.com/vero-code/valetudo-ai.git
cd valetudo-ai

Create a .env file inside the /backend folder:

PERPLEXITY_API_KEY=your_api_key_here

🔒 Refer to /backend/.env.example

📘 How to get your API key

⚠️ Never commit your .env file to version control.

npm install 
npm run dev

cd backend
python -m venv venv
venv\Scripts\activate     # On Windows
# OR
source venv/bin/activate  # On macOS/Linux

pip install -r requirements.txt
python app.py

The app will be available at http://localhost:5173

• Example: What to do if a 5-year-old has a fever?
• Click "Ask AI" and expand the full answer
• Hover over citation numbers to preview and copy links

• Click "Show advanced options"
• Set a custom date range
• Choose a country for localized results

• Drag and drop an image or upload manually
• Ask: What is this medication?
• The AI will include visual analysis

• Click "Try Prompts"
• Choose a category, fill in the fields, and generate a ready-to-send query
• Use the Follow-up input to deepen the conversation

Save time with prompts and follow-up questions.

valetudo-ai/

├── backend/         # Flask backend API
├── public/          # Static files
├── screenshots/     # UI Images
├── src/
│ ├── assets/        # Media resources
│ ├── components/    # React components
│ ├── constants/     # Mock data and templates
│ ├── hooks/         # Custom React hooks
│ ├── utils/         # Helper functions
│ ├── App.jsx        # Routes
│ ├── index.css      # Styles
│ └── main.jsx       # App entry point
├── index.html       # Main HTML file
├── LICENSE          # License file
├── package.json     # Dependencies
├── README.md        # Documentation
└── vite.config.js   # Vite config

• HeroSection — landing section with input, filters, and image upload
• AskPage — category-based prompt system with follow-up form
• QuickAnswerBox — renders AI response with Markdown + citation links

• No user data is stored
• .env securely manages API key
• Rate limits and usage caps can be added in production

• Not a diagnostic tool — for informational use only
• Response time may vary with filters or image uploads
• Mobile layout is simplified (desktop-first)

Disclaimer: This is not a medical device. Always consult a doctor for clinical decisions.

MIT License — free to use, modify, and distribute, with attribution.

Built with ❤️ for the Perplexity Global Hackathon

Powered by the Sonar API