Skip to content
SialFlow

Document Processing

Document intelligence — far beyond format conversion

Turn Office and PDF files into searchable, operable outputs: conversion, OCR, extraction, and page-async workers billed by the page. Classification, redaction, and human-review queues are part of the product direction — we call out what is still catching up. For storing and sharing sensitive files with people (not machine processing), see Secure Documents.

What you get

Convert, merge, protect

Office/PDF/image conversion plus merge, split, compress, and encrypt — production-grade document ops.

OCR & searchable PDF

Make archives searchable. Extract text, tables, and metadata for DAM, search, and downstream systems.

Privacy & compliance direction

Redaction, PII detection, PDF/A archival, and PDF/UA accessibility are on the processing roadmap — ask us what is live for your tenant.

Human review later

Review queues and e-signature provider hooks are planned operator surfaces, not the first vertical we pretend is already everywhere.

Included

  • Not just Word → PDF
  • OCR · extract · convert
  • Page-async workers
  • Honest expanding scope

Differentiation

Where SialFlow goes deeper on document processing

  • Office / PDF / image conversion
  • PDF merge, split, compress, and encrypt
  • OCR and searchable PDF
  • Thumbnail and preview generation
  • Text, table, and metadata extraction
  • Page-based quota and billing
  • Async page workers for very large documents
  • Document classification — expanding
  • Redaction and PII detection — expanding
  • PDF/A and PDF/UA — expanding
  • E-signature provider integration — Planned
  • Human-review workflow — Planned

Example

Same auth and tenancy headers as the rest of the API. Where a capability plugs into Flows today, that is called out on the product page — we do not imply every media type shares one live pipeline yet.

POST /v1/documents/jobs

{
  "source_object_id": "obj_01J8D...",
  "operations": [
    { "op": "ocr", "searchable_pdf": true },
    { "op": "extract", "targets": ["text", "tables", "metadata"] },
    { "op": "classify", "model": "contracts_v2" },
    { "op": "redact_pii" },
    { "op": "normalize_for_llm", "format": "structured_json" },
    { "op": "archive", "profile": "pdf_a" }
  ],
  "review": { "required": true, "queue": "legal_eu" },
  "billing": { "unit": "pages" }
}

Ship with Document Processing

Open the portal, follow the docs, or talk to us about rollout for your agency or commerce stack.