9a17ff7457
The modal listed every document and mounted a checkbox per document, so a corpus of tens of thousands never finished rendering: 67k sequential mounts across two databases, and the same for one database that size. Titles repeat at that scale too, and the ids were derived from the title, so they collided. It shows a page of 200 now, mounted in one call and identified by position, and the search box asks the database for the rest on enter, matching titles and URIs. Typing still narrows the page on screen, for feedback while typing. `search_filter` escapes the term, which is whatever was typed. A federated listing takes its window across the databases rather than filling it from the first one: concatenating hid every database after whichever was listed first, which for a set of a thousand papers and sixty thousand articles meant a page of papers alone. Sorting would not have helped, since document ids and article titles sort into separate runs, so the page is picked by interleaving and the modal sorts it for display. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_chat_app.py | ||
| test_image_input.py | ||