Document Q&A with GPT: web, .pdf, .docx, etc.
Hello fellow hackers, we made a site that gets GPT to answer your question using the info on a webpage you specify or document you upload (e.g., a large textbook .pdf file). Background: When ChatGPT came out, I had the idea of having it pull answers from my stereo receiver's annoyingly dense 32 page manual. My weekend project prototype proceeded to surprise with great answers—just like what we've all experienced by now. My co-founder thought we should productize it, and make it easy to use online. So here we are with a very early beta! (Try it on a HN thread...)
In plain words
Document Q&A with GPT is an early-stage tool that uses GPT to answer questions based on content users provide—either by specifying a webpage URL or uploading documents like PDFs and Word files. Designed for anyone needing quick answers from large or complex documents, it lets users query dense manuals, textbooks, and web pages without reading through all the material themselves. The tool works across multiple document formats and web content.
written from the facts on this page · September 2026
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2023
the whole month →
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io