Klarum

Documents

Generally available
Supplier and issuer
From basic

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.

Catalogue id
documents

Description

What it is

Klarum's central document library and reader. The single place where every document the platform touches comes together: firm uploads (profiles, reference lists, PDS, capability statements), cloud-drive imports (Google Drive, OneDrive, SharePoint), workspace attachments, and Klarum-generated documents (EOIs/proposals). Two scopes share one UI: firm-wide (durable knowledge base) and workspace-scoped (bid attachments). The detail route intelligently picks the right reader: a generic citation viewer, a tender-match heatmap viewer, or a recording viewer.

What it helps users do

Keep one source of truth for firm credentials (upload once, indexed for reuse and auto-citation); bring documents in from where they already live; see how each document is actually used ("times used", "last used", citing EOIs/sections, average relevance); understand why a document supports a tender (a heatmap over sections - the brightest passages are what the engine leaned on, making match scores auditable at the passage level); find anything fast; download generated artifacts as PDF/DOCX.

Capabilities

  • One ingest path

    Generally available

    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.

  • Tender-match heatmap

    Generally available

    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.

  • Citations and annotations

    Generally available

    RAG citations carry title, format, page and score, and document annotations record AI audits, user notes and risk warnings against a relevance score.

  • Usage loop

    Generally available

    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.

Integrations

  • Amazon S3 Object storage for raw document bytes under a deterministic key, with a metadata-only DB row.
  • LlamaParse Cloud layout-preserving PDF and DOCX to markdown parsing, the default rich parser.
  • Google Gemini document parsing Alternative vision-grade parser prompted for clean structured markdown, the route for image-heavy and scanned PDFs.

Keywords

documents, s3, parsing, chunking, embeddings, citations, heatmap, rag

Provenance

This page renders a published artifact. Read the same records as JSON if you would rather check the source than the page.