1. Documents
Three sample documents are loaded. Drop a .md or .txt file
anywhere on this page — or paste your own below — to search something else.
Ask a question about a document set, get the exact passages that answer it — with the source. The chunking, the embedding model and the ranking all run in this tab. No server, no API key, nothing uploaded.
Loading the embedding model…
Three sample documents are loaded. Drop a .md or .txt file
anywhere on this page — or paste your own below — to search something else.
Retrieval above needs no key at all. If you want a generated paragraph on top of the passages, point this at any OpenAI-compatible endpoint. The key stays in this tab and is sent only to the URL you type here — it is never stored or logged. Default model is deliberately small, because 0.5B-class local models hallucinate more than the passages above do.
Generation is off — you will get passages and sources only.