{"id":"documents","type":"module","title":"Documents","status":"ga","audience":["consultant","bid-manager","org-admin"],"scope":"both","tier_min":"basic","aliases":["7","library","viewer"],"summary":"Klarum's central document library and reader, where every file the platform touches becomes parsed, chunked, embedded, citable evidence rather than an opaque blob in a bucket.","keywords":["documents","s3","parsing","chunking","embeddings","citations","heatmap","rag"],"body":{"what_it_is":"Klarum's central document library and reader. The single place where every\ndocument the platform touches comes together: firm uploads (profiles,\nreference lists, PDS, capability statements), cloud-drive imports (Google\nDrive, OneDrive, SharePoint), workspace attachments, and Klarum-*generated*\ndocuments (EOIs/proposals). Two scopes share one UI: **firm-wide** (durable\nknowledge base) and **workspace-scoped** (bid attachments). The detail route\nintelligently picks the right reader: a generic **citation viewer**, a\n**tender-match heatmap viewer**, or a **recording viewer**.\n","what_it_helps_users_do":"Keep one source of truth for firm credentials (upload once, indexed for reuse\nand auto-citation); bring documents in from where they already live; see how\neach document is actually used (\"times used\", \"last used\", citing\nEOIs/sections, average relevance); understand *why* a document supports a\ntender (a heatmap over sections - the brightest passages are what the engine\nleaned on, making match scores auditable at the passage level); find anything\nfast; download generated artifacts as PDF/DOCX.\n"},"engines":[],"integrations":[{"id":"aws-s3-documents","type":"integration","title":"Amazon S3","summary":"Object storage for raw document bytes under a deterministic key, with a metadata-only DB row.","category":"storage"},{"id":"llamaparse","type":"integration","title":"LlamaParse","summary":"Cloud layout-preserving PDF and DOCX to markdown parsing, the default rich parser.","category":"parsing"},{"id":"gemini-document-ai","type":"integration","title":"Google Gemini document parsing","summary":"Alternative vision-grade parser prompted for clean structured markdown, the route for image-heavy and scanned PDFs.","category":"parsing"}],"capabilities":[{"id":"document-ingest-path","type":"capability","title":"One ingest path","summary":"Every source, upload or cloud import or generated artifact, takes the same route to S3 plus a metadata row plus an async parse, chunk and embed pass with an explicit parse status.","status":"ga","scope":null,"keywords":["ingest","s3","parse-status"],"body":null},{"id":"document-match-heatmap","type":"capability","title":"Tender-match heatmap","summary":"Embeds the tender text and scores every chunk of a document against it, rendering a per-section heat score so the passages that drove a match score are visible.","status":"ga","scope":null,"keywords":["heatmap","auditability","cosine"],"body":null},{"id":"document-citations","type":"capability","title":"Citations and annotations","summary":"RAG citations carry title, format, page and score, and document annotations record AI audits, user notes and risk warnings against a relevance score.","status":"ga","scope":null,"keywords":["citations","annotations","provenance"],"body":null},{"id":"document-usage-loop","type":"capability","title":"Usage loop","summary":"Each document reports times used, last used, which EOIs and sections cite it and its average relevance, so a reference list earns or loses its place.","status":"ga","scope":null,"keywords":["usage","relevance","reuse"],"body":null}]}