Inspiration
We wanted to solve the problem of reading and understanding large PDF documents quickly. Many students and professionals waste time manually searching through PDFs. This inspired us to build an AI-powered PDF assistant that can instantly answer questions from any document.
What it does
Users can upload a PDF and ask natural language questions. The system extracts text from the PDF and uses AI to generate accurate, context-aware answers in real time.
How we built it
We built this project using Python Flask for the backend and a simple HTML/CSS/JavaScript frontend. PDF text extraction is handled using pdfplumber. We integrated an LLM API (Gemini / AI model) to process user queries and generate responses.
Challenges we ran into
We faced issues with API integration, model compatibility errors, and handling large PDF text efficiently. Debugging API errors and switching models helped us stabilize the system.
Accomplishments that we're proud of
We successfully built a working end-to-end AI system that reads PDFs and answers questions accurately with a clean user interface.
What we learned
We learned how to integrate LLM APIs, handle file uploads in Flask, and build a full-stack AI application from scratch.
What's next
We plan to add support for multiple documents, better UI, faster responses, and voice-based interaction.
Log in or sign up for Devpost to join the conversation.