[LocalMode] Extractive question answering (Xenova/distilbert-base-cased-distilled-squad, grounding corpus context via engine.search topK 1, High/Medium/Low confidence tiers) over its OWN text/PDF corpus, plus Donut (Xenova/donut-base-finetuned-docvqa) document/invoice QA on an uploaded image (~800 MB, gated). C
pnpm dlx shadcn@latest add "https://registry.directory/r/localmode-ai/ui/blocks/knowledge/document-qa.json"