README.md

metadata

title: AnatomyBot - MBBS Anatomy Tutor
hackathon: https://huggingface.co/MCP-1st-Birthday
emoji: 🩺
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 6.0.0
app_file: app.py
pinned: false
license: mit
short_description: AnatomyBot - Interactive AI-powered MBBS anatomy tutor.
tags:
  - building-mcp-track-enterprise
  - building-mcp-track-customer
  - building-mcp-track-creative
  - mcp-in-action-track-creative
  - mcp-in-action-track-consumer

🩺 AnatomyBot – MBBS Anatomy Tutor

Welcome to our submission for the Hugging Face MCP 1st Birthday Hackathon!
This project showcases an intelligent multi-agent educational system powered by Gradio, designed to revolutionize how medical students learn anatomy through visuals, voice interaction, and active recall.

Link to demo: https://huggingface.co/spaces/gladguy/SimpleProject
YouTube Video: https://www.youtube.com/watch?v=5L5suQMTd5I

---

📝 What I want to showcase

I want to showcase an intelligent, interactive educational platform designed specifically for MBBS (medical) students. The goal is to bridge the gap between static textbooks and active learning by providing:

• Visual & Contextual Learning: Instantly fetching relevant anatomical diagrams alongside AI-generated educational summaries.
• Active Recall & Simulation: A "VIVA Mode" that simulates an oral anatomy exam with a strict but fair AI professor, complete with voice interaction.
• Resource Augmentation: A "Book Mode" that allows students to upload their own textbooks and get AI-powered analysis and quiz questions for specific pages.

---

🛠️ What I've built so far

I have built a fully functional Gradio web application that integrates multiple powerful AI services:

1. Smart Query Engine

• Uses Hyperbolic AI (Llama 3.3 70B) to validate if questions are strictly anatomy-related.
• Fetches high-quality diagrams using SERPAPI (Google Images), filtering out non-diagrammatic results.
• Generates structured, emoji-rich educational content (Location, Features, Clinical Significance).

2. VIVA Training Mode

• Simulates a real oral exam environment.
• Generates progressive questions (from basic relations to clinical scenarios).
• Voice Interaction: Uses ElevenLabs to vocalize questions, making the experience immersive.
• AI Evaluation: Grades student answers (Distinction, Pass, Borderline, Fail) and provides detailed feedback with reference answers.

3. Book Learning Mode

• Allows PDF textbook uploads.
• Extracts and displays specific pages.
• Analyzes page content to generate summaries, clinical points, and self-test questions.

---

💻 Tech Stack

• Frontend/UI: Gradio (Python)
• LLM Intelligence: Hyperbolic AI API (Meta Llama 3.3 70B Instruct)
• Image Search: SERPAPI (Google Images Engine)
• Voice Synthesis: ElevenLabs API (Text-to-Speech)
• Image/PDF Processing: Pillow, PyPDF2, pdf2image
• Environment: Python, Hugging Face Spaces

---

🔗 Quick Links

• 🏆 Hackathon: MCP 1st Birthday Hackathon
• 📺 YouTube Demo: Watch Video
• 🚀 Live Demo: Try AnatomyBot
• 💼 LinkedIn Post: View Post

---

🛠️ Installation & Setup

Prerequisites

• Python 3.8 or higher
• API Keys for SERPAPI, Hyperbolic, and ElevenLabs.

Steps

1. Clone the repository:

   git clone https://huggingface.co/spaces/gladguy/SimpleProject
   cd SimpleProject
   

2. Install dependencies:

   pip install -r requirements.txt
   

3. Set up your .env file:

   SERPAPI_KEY=your_key
   HYPERBOLIC_API_KEY=your_key
   ELEVENLABS_API_KEY=your_key
   

4. Run the app:

   python app.py or uv run app.py
   

---

🧑‍💻 Authors

• Waheed – Lead Developer & AI Architect
• HF Username : gladguy
• Profile : https://huggingface.co/spaces/gladguy

---

📝 License

This project is licensed under the MIT License.