The problem Edu Quest AI solves

1. Enhanced Personalization: Traditional study methods often lack personalization, leading to a generic approach that may not cater to individual learning needs. This app addresses this by providing tailored quizzes and flashcards based on users' study materials and performance. It ensures that learning is customized to each student's pace and understanding, enhancing both engagement and retention.

2. Continuous Learning Flexibility: Students frequently face interruptions in their learning due to varying access to resources. The app resolves this by offering an offline mode specifically for text-based chatbot interactions. This ensures that users can continue to get help and clarify concepts even without internet access. For other features such as DOC Chat, Image Chat, QR code functionality, and personalized quizzes and flashcards, the app operates online, allowing for a rich, interactive learning experience.

3. Efficient Study Tools: Manual study methods like note-taking and flashcards can be time-consuming and less interactive. Our app automates the creation of quizzes and flashcards from study materials, streamlining the review process. It also offers dynamic interaction with study documents and images, making it easier to understand complex concepts.

4. Real-Time Interaction: Understanding and engaging with complex documents and images can be challenging with conventional tools. The app's DOC Chat and Image Chat features allow users to interact directly with their study materials, providing real-time answers and clarifications, thereby making learning more intuitive and effective.

5. Comprehensive Progress Tracking: Tracking learning progress and revisiting past content can be difficult with traditional methods. The app's history and progress tracking features keep a detailed log of study sessions, quizzes, and flashcards. This ensures that users can monitor their learning journey, revisit past content, and measure their improvement over time.

Challenges we ran into

1. Offline Chatbot: Integrating an AI chatbot for offline use in a Flutter app presented significant hurdles, primarily due to the compatibility of AI models with offline environments. To address this, we utilized the Gemma model, specifically optimized for offline functionality. This model required careful adaptation to ensure it could efficiently handle diverse user queries without needing an internet connection. We implemented rigorous testing to confirm that the chatbot could deliver accurate and responsive answers even when offline.

2. QR Code Implementation: Implementing QR code functionality for extracting content from textbooks involved complex web scraping tasks. Ensuring that the QR codes linked to relevant and accurate content demanded the development of sophisticated algorithms. We built and refined these algorithms to handle various data formats and integrated robust error-handling mechanisms to address any discrepancies or failures in content retrieval.

3. History in Hive Storage: Managing detailed history and progress data locally using Hive posed challenges related to data integrity and synchronization. To overcome this, we designed a schema that allowed for efficient and reliable storage of study logs, quizzes, and flashcards. We also implemented mechanisms for real-time synchronization and integrity checks to ensure that users' progress was accurately tracked and maintained.

4. Local Storage in Hive: Efficiently handling large amounts of local data required significant optimization. Using Hive for local storage, we focused on minimizing performance bottlenecks by implementing data compression and indexing strategies. These optimizations were crucial to maintaining app responsiveness and ensuring quick access to stored study materials.

5. Module Integration: Integrating diverse features—offline chatbot, QR code funct