Final submission

README.md

@@ -28,45 +28,50 @@ This project showcases **an intelligent multi-agent educational system** powered
 
 ---
 
-## 🌐 Project Overview
+## 📝 What I want to showcase
 
-This system leverages specialized AI agents that collaborate to create an immersive learning experience:
+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:
 
-- 🛡️ **Validator Agent**: Ensures all queries are strictly anatomy-related using **Hyperbolic AI**.
-- 🖼️ **Visual Agent**: Instantly fetches and filters high-quality anatomical diagrams via **SERPAPI**.
-- 👨‍⚕️ **Professor Agent**: Conducts oral VIVA exams, generating questions and vocalizing them using **ElevenLabs**.
-- 🧠 **Analyst Agent**: Reads and interprets uploaded textbook pages to generate summaries and quizzes.
+-   **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.
 
 ---
 
-## 🗂️ Data Sources & External APIs
+## �️ What I've built so far
 
-Our platform relies on **state-of-the-art AI models and real-time data**. Each component is powered by a dedicated API to ensure accuracy and engagement.
+I have built a fully functional **Gradio** web application that integrates multiple powerful AI services:
 
-**Here is a detailed overview of the APIs and data sources leveraged by the agents:**
+### 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).
 
-1.  **Hyperbolic AI (Llama 3.3 70B)** – *The Brain*
-    *   Used for query validation, educational content generation, and student answer evaluation.
-2.  **SERPAPI (Google Images)** – *The Eyes*
-    *   Provides real-time access to high-quality medical diagrams and illustrations.
-3.  **ElevenLabs** – *The Voice*
-    *   Powers the "Professor Agent" to speak VIVA questions, simulating a real oral exam.
+### 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.
 
-## 🧩 Core Components
+### 4. Student System
+*   Includes a registration system (SQLite backend) to track student details (Name, Medical School, Year).
 
-### 🎨 User Interface (`app.py`)
--   **Interactive Gradio Interface**: A clean, tabbed UI optimized for learning.
--   **Real-time Feedback**: Instant visual and audio responses.
--   **Navigation**: Seamless switching between Learning, VIVA, and Book modes.
+---
 
-### 🧠 Logic & Agents (`capp.py`)
--   **Agent Definitions**: Contains the logic for the Validator, Visual, and Professor agents.
--   **State Management**: Handles user sessions, VIVA progress, and PDF processing.
+## � Tech Stack
 
-### 💾 Data Persistence (`students.db`)
--   **Student Records**: SQLite database to track registered students (Name, Medical School, Year).
+*   **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)
+*   **Database**: SQLite (for user management)
+*   **Image/PDF Processing**: Pillow, PyPDF2, pdf2image
+*   **Environment**: Python, Hugging Face Spaces
 
 ---