@namdeoshreyaslink36461

Most documentation is either out of date, buried in the wrong folder, or just doesn't exist. DocuMind lets you talk to your codebase instead. You connect it to a GitHub repo or Notion workspace. It reads the files, chunks them, generates vector embeddings, and stores everything in Qdrant. When you ask a question, it searches semantically rather than by keyword, pulls the most relevant chunks, and passes them to an LLM that writes an actual answer with source links attached. The frontend is a chat interface built in React. Responses stream in real time over server-sent events, so you're not waiting for a spinner to dump a wall of text. Sources show up alongside the answer so you can check what the model is actually citing. The backend runs on FastAPI with a multi-agent setup. A query agent handles search and response generation. The embedding layer uses sentence-transformers, so you're not locked into one LLM provider for that part. The LLM connects through Ollama, which means you can swap models depending on what you need. The whole stack is self-hostable. You bring your own keys and run it on your own infra. Nothing routes through a third party except the model endpoint you configure. In practice it's useful for three things: onboarding new engineers (let them ask "how does auth work" instead of interrupting someone), debugging (ask where a particular error gets thrown and which file handles it), and navigating large codebases that nobody fully understands anymore. That last one comes up more than you'd expect.

Build solutions that improve how software is built. Work with an AI that understands your codebase, helping you reduce repetitive work and build with real context. ⏳ Build your project in 48 hours. 🚀 Get hands-on with IBM Bob and explore how AI fits into real development workflows before it becomes standard. 💡 Build tools and workflows that developers would actually use. ⭐ Learn directly from experts throughout the event. 🤝 Join a team or build solo. 💰 Prize pool: $10,000 🧑🏻‍💻 Register before the Kick-Off Stream and start building with Bob.

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.