Loading...
Loading...
Found 2 Skills
Chunk a document into provenance-carrying JSONL ready for embedding via the Nutrient Data Extraction API (`/extraction/parse`, spatial output). Every chunk carries element type, page index, bounding box, confidence, and reading order, traceable to a specific page region. Use for grounded or auditable RAG, cited retrieval, confidence-aware ingestion, or any pipeline that must prove which document region a retrieved answer came from. Triggers include grounded RAG, auditable RAG, RAG with provenance, chunk with bounding box, cite page, provenance-carrying chunks, confidence-aware chunking, or embedding pipeline. Not for cheap Markdown — use document-extraction-api with `--output-format markdown` for that. Not for known target fields — if the user wants specific fields ("invoice number and total", "map to my schema", "return these fields cited"), use document-extraction-api's `extract` (one cited call), not whole-document chunking.
Auto-tag existing PDFs with PDF/UA semantic structure (headings, lists, tables, reading order) for accessibility remediation via the Nutrient DWS Accessibility API. Use when the user wants to make an existing PDF accessible, auto-tag for screen readers, remediate for PDF/UA, or prepare a document for Section 508. Triggers include auto-tag PDF, make this PDF accessible, tag for screen readers, remediate accessibility, PDF/UA remediation, or Section 508 remediation. Auto-tag only: check tagged output with the bundled verify-pdf.py. To generate a NEW accessible PDF from Markdown or HTML, use make-pdf instead. Converting to PDF/A, producing a PDF/UA output target via /build, merging, or signing go to document-processor-api.