PDF Genie is a web-based tool that lets users upload a PDF file and interact with its content using natural language queries β just like chatting with your document!
Built using the MERN Stack and powered by Google Cloud tools, PDF Genie is a personal project inspired by platforms like AskMyPDF, aiming to simplify information extraction from documents.
- π Upload any PDF file
- π¬ Ask questions related to the content
- π€ Get accurate and contextual answers instantly
- π Works securely with file isolation and cleanup
Frontend: React.js
Backend: Node.js, Express.js
Database: MongoDB (Mongoose ODM)
Cloud & NLP: Google Cloud Tools (Vertex AI, Document AI, Gemini API)
Storage: Google Cloud Storage
Authentication: JWT (optional phase)
- π Upload and parse PDFs in real time
- π¬ Ask questions using a chat UI
- π Summarize, extract sections, or find specific answers from the document
- π‘οΈ Secure PDF processing with file cleanup
- π User-friendly interface with responsive design
- User uploads a PDF
- Backend extracts and stores text
- Question is processed using Google Cloud LLM or NLP API
- Answer is generated and displayed in chat
β
Completed as a personal AI utility project
π οΈ Built to explore GenAI + Cloud + Fullstack synergy
π Currently supports text-based PDFs only (can be extended to OCR)
- π Add user authentication and history tracking
- π Multi-PDF comparison support
- π§ Better context caching for longer PDFs
- π² Export chat summary to text or PDF
Manikanta Sandula
A project that reflects my love for building useful tools with AI, fullstack tech, and cloud integration. PDF Genie is one step closer to making document reading smarter.