A basic semantic search app based on 133.952 public pdfs (~400GB) from CORDIS chunked and indexed (mean embedding of all chunks) in a ~38MB gzipped json with all-MiniLM-L6-v2. Enter any query and hit submit or enter. App loads ~50Mb of resources of data and scripts. More information on GitHub. Currently only working on Chromium-based browsers (e.g. Chrome & Edge).