RAG Chat Block
- from @localmode
- by LocalMode
Streaming grounded RAG over its OWN text/PDF corpus — token-by-token answers through the engine-owned generator (granite-4.0-350M) with [n] markers upgraded to hover-card inline citations resolved to retrieved sources (PDF page attribution + similarity), wall-clock duration, and cancel — carrying the core-pipeline ⇄ LangChain engine toggle. Split from ui/blocks/knowledge-base (Ask tab RAG lane; absorbs langchain-rag).
Install
New to shadcn? Set up your project
If your project already has a shadcn components.json, skip initialization. Otherwise, run this once from your project root.
pnpm dlx shadcn@latest initpnpm dlx shadcn@latest add @localmode/ui/blocks/knowledge/rag-chatRegistry dependencies11
- @localmode/ui/lib/utils
- @localmode/ui/local-first/model-downloader
- @localmode/ui/data-documents/chunk-boundary-visualizer
- @localmode/ui/data-documents/file-dropzone
- @localmode/ui/data-documents/indexed-document-card
- @localmode/ui/input-controls/segmented-mode-picker
- @localmode/ui/input-controls/parameter-slider
- @localmode/ui/conversation/pipeline-tracker
- @localmode/ui/conversation/sources
- @localmode/ui/conversation/source-citation-list
- @localmode/ui/conversation/inline-citation
