# From a scanned page and a recording to a searchable document

> Source: <https://loomcycle.dev/blog/from-a-scanned-page-to-a-searchable-document.html>
> Published: 2026-10-26 16:00:00+00:00

What lands on a document-based reference system is DOCX, XLSX, PPTX, PDF, scans and recordings. loomcycle v1.122 to v1.124 reads them without the model ever holding the bytes: pure-Go extraction to Markdown with bounded zip and XML parsers, PDF text layers with CMaps and Cyrillic, and an import that builds a Document tagged untrusted with pictures as image chunks by page and slide. Pages with no text layer go through OCR by a vision model, opted into by both operator and agent, with page caps, a ledger purpose and a dry-run cost estimate. Recordings go through any OpenAI-audio-shaped whisper server, cut into overlapping pieces under minute budgets. Search filters by path, document, type, status, tag and as_of act inside every retrieval leg rather than after it, chunks carry validity periods, and documents_scope keeps notes and references apart.