Documents guide
Document Processing turns PDFs and office files into searchable, structured and automation-ready outputs on the same control plane as image and video. Typical pipeline: upload → OCR → extract → classify → redact → JSON/PDF. Capability is tenant-gated — check what is live before wiring production. Folder sharing, e-sign and retention are outside SialFlow.
Document pipeline (capability-gated)
POST /v1/documents/jobs
{
"source_object_id": "obj_...",
"operations": [
{ "op": "ocr", "searchable_pdf": true },
{ "op": "extract", "targets": ["text", "tables", "metadata"] },
{ "op": "classify" },
{ "op": "redact_pii" },
{ "op": "normalize_for_llm", "format": "structured_json" },
{ "op": "archive", "profile": "pdf_a" }
],
"billing": { "unit": "pages" }
}