A transparent RAG system over a curated corpus of papers on physics-informed neural networks, neural operators, model compression, and LLM inference, the literature I actually use day-to-day. BM25 retrieval runs client-side, and answers work instantly with no setup (extractive mode), or plug in any OpenAI-compatible LLM for generative answers. The behind-the-scenes panel shows retrieved chunks, scores, and the exact prompt: if retrieval fails, you can see why.
Retrieval is instant and local. Try one of these, no API key required:
Most "chat with your PDFs" demos hide retrieval behind a black box. This one shows everything: the chunks pulled, their scores, and the exact prompt. That transparency is the point, when retrieval fails, you can see why.
localStorage and is sent only to the endpoint you configure.A focused corpus is the whole point. The system is good at scientific ML because the chunks are tagged, sectioned, and curated. Throw 10,000 random PDFs at the same architecture and recall collapses. Choosing a scope is a real engineering decision, and more interesting to me than another generic Q&A bot.
Optional, extractive mode already works with no setup. Bring your own key for fluent generative answers; it stays in localStorage and is only sent to the endpoint below.
console.groq.com, create a key, pick the
Groq preset, paste it here.ollama serve and use http://localhost:11434/v1/chat/completions.