ROHITH M@ROHITH

RocDoc is an AI-powered document intelligence platform built during the AMD Developer Hackathon to simplify document understanding and knowledge retrieval. The project allows users to upload PDFs, Markdown files, and text documents, then interact with them using natural language queries through a conversational AI interface. Instead of manually searching through large documents, users can ask questions directly and receive contextual, citation-based answers generated from the uploaded content. One of the core goals of RocDoc was to create a practical and privacy-focused Retrieval-Augmented Generation (RAG) application with a clean developer-friendly user experience. The platform processes uploaded documents, manages source references, and generates grounded responses while maintaining a responsive and modern interface. The frontend was built using Next.js and TypeScript with a dark-themed modern UI optimized for usability and readability. The application includes: Document ingestion pipeline AI-powered contextual Q&A Citation-based answer rendering Source management system Live telemetry dashboard Multi-document support Interactive chat interface During development, we focused heavily on stability, frontend optimization, and backend workflow improvements. Multiple build issues, dependency conflicts, and ingestion challenges were resolved while refining the overall architecture of the project. The telemetry panel provides real-time system monitoring, giving users insight into system performance and resource utilization during AI inference workflows. This aligns with the AMD Developer Hackathon’s focus on high-performance AI systems and modern AI infrastructure. RocDoc demonstrates how AI can improve productivity, document comprehension, and information retrieval for students, developers, researchers, and technical teams. The project combines modern web technologies with AI-powered workflows to deliver a fast, interactive, and scalable document assistant experience.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.