Mohammad Sharafat Alam Saki@sharafat_alam875

DocuMind AI is an intelligent PDF RAG assistant designed to make information retrieval from documents faster, easier, and more natural. Reading lengthy PDF documents and manually searching for specific information can be time-consuming, especially for students, researchers, professionals, and anyone who regularly works with large amounts of documentation. DocuMind AI addresses this problem by allowing users to upload a PDF document and ask questions about its content. Instead of searching through pages manually, users can ask questions in natural language and receive context-aware answers based on the uploaded document. The system processes the document, divides its content into meaningful chunks, generates embeddings, stores them in a vector database, and retrieves the most relevant information when a question is asked. A language model then uses the retrieved context to generate a grounded response. The application is designed to provide a simple and accessible interface for document-based question answering. Users do not need to understand the underlying RAG pipeline or vector search process. They simply upload a document, enter their question, and receive an answer based on the available document context. What makes DocuMind AI useful is the combination of document understanding, semantic retrieval, and generative AI in a single workflow. By retrieving relevant information before generating an answer, the system aims to keep responses focused on the user's document rather than relying only on general model knowledge. The project is particularly useful for students, researchers, developers, professionals, and organizations that need to quickly extract information from technical documents, reports, manuals, research papers, and other PDF-based resources. DocuMind AI turns static documents into an interactive knowledge source and provides a practical demonstration of how Retrieval-Augmented Generation can improve document-based AI applications.

DocuVoice RAG is a voice-powered document question-answering system that makes it easier to interact with long and complex documents. Instead of manually searching through pages, users can upload a document and simply ask questions using their voice. The system converts speech into text using AssemblyAI, retrieves the most relevant information from the uploaded document through a Retrieval-Augmented Generation (RAG) pipeline, and generates a contextual answer. This approach helps reduce the time and effort required to find information while keeping responses grounded in the document’s content. DocuVoice RAG combines voice interaction, document retrieval, and AI-generated responses into a simple conversational experience. The project demonstrates how speech AI and RAG can work together to make document-based knowledge more natural, accessible, and user-friendly

Mushaki is an AI-powered voice assistant designed to provide a more natural and practical way for users to interact with AI. Unlike a basic chatbot, Mushaki combines conversational AI with voice interaction, desktop automation, and a web-based interface. The project has two editions: a Desktop Assistant and a Web Application. The desktop edition allows users to communicate through voice, receive spoken AI responses, perform web searches, open applications, and automate everyday computer tasks using natural-language commands. The web edition, built with Streamlit, provides an accessible interface where users can interact with Mushaki through both text and voice from a browser. Mushaki uses Google Gemini for intelligent responses and integrates speech-to-text and text-to-speech technologies to create a more interactive experience. The project focuses on making AI more accessible, useful, and action-oriented by connecting natural conversation with real-world tasks. Our vision is to evolve Mushaki into a versatile personal AI assistant that can understand users, assist with their workflows, and help them get things done faster.

🌎 Online Hackathon | 💻 Online Build: Sept 26 - Oct 5, 2026 A virtual, global hackathon. Build from anywhere in the world. Dark Factory is the official hackathon of WeAreDevelopers World Congress North America, presented by BAND, but you don't need to be in San Jose to take part. For one week, you build a software factory in BAND Desktop: a band of coding agents that plans work, implements it and checks its own results. 🎟️ Bonus for sign-ups: you are eligible for a free ticket to WeAreDevelopers World Congress North America in San Jose (Sep 23–25). If you do go, stop by the BAND booth: a surprise is waiting for you.

💻 Online Hackathon | ⏳ Build: 48 hours | 📅 September 25–27, 2026 The official IBM Bob 2.0 hackathon. Build what's next in AI-assisted development, alongside the developers and experts shaping it. ⭐ Get help from experts throughout the event 🤝 Join a team or build solo 💰 Prize pool: $12,000 🧑🏻‍💻 Register before the Kick-Off Stream to start building with Bob

🌎 Hybrid Hackathon | 💻 Online Build: September 10–16, 2026 | 📍 On-site: September 15–17, 2026 The official hackathon of AI Infra Summit — co-organized by Kisaco Research and lablab.ai. Build production-grade AI applications on the modern AI infrastructure stack, alongside 8,000+ attendees, researchers, founders, and infra leaders. 📍 On-site Venue (September 15–17): Santa Clara Convention Center 5001 Great America Pkwy, Santa Clara, CA 📍 On-site participation is by invitation only. Travel and accommodation expenses will not be covered.