This is my submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.
🚀 What I Built
GetMyEBook-Web is a web-based eBook platform designed to make digital reading more accessible and convenient.
For this project, I am expanding the platform with a new AI-powered feature called Chat with Book AI, which uses Retrieval-Augmented Generation (RAG) to help readers interact with book content conversationally.
Instead of manually searching through hundreds of pages, readers will be able to ask questions about a book and receive answers grounded in the relevant passages retrieved from its content.
✨ Key Features
- 📚 Digital Library: Browse and discover eBooks in one place.
- 🔎 Book Discovery: Find books and explore available reading resources.
- 🤖 Chat with Book AI: Ask questions about a book using natural language.
- 🧠 RAG-Based Retrieval: Retrieve relevant book passages to provide context for AI-generated answers.
- 📖 Context-Aware Answers: Help readers understand concepts, summarize sections, and find relevant information.
- ⏱️ Save Reading Time: Reduce the effort required to locate specific information in lengthy books.
The goal is not to replace reading, but to make reading, learning, and exploring books more interactive.
🎬 Demo
🌐 Live Website: https://getmyebook.in/
The existing website is available here. The Chat with Book AI feature is currently being developed and should be demonstrated once its implementation is ready.
💻 Source Code
🔗 GitHub Repository: https://github.com/Vasanth2005kk/GetMyEBook-Web
Explore the repository to follow the project's development and future improvements.
🛠️ How I Built It
The project combines a digital library with an AI-powered question-answering workflow.
The planned Chat with Book AI feature uses Retrieval-Augmented Generation (RAG) to connect a language model with the content of a selected eBook.
🧠 How the RAG System Works
- Book Processing: Extract readable text from the selected eBook.
- Text Chunking: Divide the extracted text into smaller, meaningful chunks.
- Embedding Generation: Convert chunks into vector representations using an embedding model.
- Vector Storage: Store the embeddings in a vector database or vector index.
- Question Processing: Convert the reader's question into an embedding.
- Relevant Retrieval: Retrieve the book passages most relevant to the question.
- Answer Generation: Provide the retrieved passages as context to a language model, which generates an answer based on the available content.
🔄 RAG Architecture
Reader → Select a Book → Ask a Question → Retrieve Relevant Passages → Generate an Answer → Display the Response
This approach can make answers more relevant to the selected book and reduce unsupported responses when retrieval and prompting are implemented carefully.
The specific language model, embedding model, vector database, and application framework will be documented according to the actual implementation.
🌍 Why Does Open Innovation Matter?
Open innovation allows developers to build on shared knowledge, experiment with different technologies, and create solutions that benefit the wider community.
For Chat with Book AI, open-source AI models and frameworks can provide greater flexibility in choosing how language generation, embedding creation, and retrieval are implemented.
Potential benefits include:
- Transparency: Understand how the retrieval and answer-generation pipeline works.
- Flexibility: Experiment with different models and retrieval strategies.
- Learning: Explore practical applications of RAG, embeddings, and vector search.
- Community Collaboration: Invite contributors to improve document processing, retrieval quality, and user experience.
- Accessibility: Work toward making AI-assisted reading available to more learners and readers.
The project is an opportunity to explore how open-source AI can make existing digital resources more interactive and useful.
🤖 My Agent Session
I will share my DevRelay agent session here if I save one during the development process.
This can document the implementation steps, debugging process, and decisions made while building the RAG pipeline.
⏱️ The Lazy Payoff
Imagine studying a long technical book and needing to understand one specific concept.
Instead of repeatedly searching through chapters, a reader could ask Chat with Book AI a direct question and receive an answer based on relevant passages from the book.
This could reduce time spent locating information, simplify revision, and help readers explore unfamiliar topics.
The actual time saved and answer quality will need to be evaluated after implementation and testing.
🏆 Prize Categories
I will select the applicable partner prize categories after confirming the challenge requirements and the open-source AI technologies used in the completed implementation.
🚀 What's Next?
My next steps are to:
- Implement the complete RAG pipeline.
- Integrate an appropriate language model and embedding model.
- Add reliable book-text extraction and chunking.
- Build semantic retrieval for book-specific questions.
- Improve answer grounding and provide source-page or passage references where possible.
- Test the system with different books and questions.
- Document the architecture so other developers can contribute.
🙌 Final Thoughts
GetMyEBook-Web started as a digital reading platform. With Chat with Book AI, I want to explore how Retrieval-Augmented Generation can make reading more interactive and help people learn directly from their books.
This project is part of my journey in web development, AI engineering, and open-source contribution.
I look forward to learning, building, experimenting, and sharing improvements with the developer community.
Thanks to the Hacktoberfest and DEV Community teams for encouraging developers to build and contribute to open source!
Top comments (1)
Hello Friends 😇
GetMyEbook is an open-source project, and everyone is welcome to contribute! 🚀
Feel free to report bugs, suggest new features, improve the code, and help make GetMyEbook better for everyone. 💻
Thank You All ♥️