RAPIC Processing API

Document Extraction

Supported: PDF, DOCX, XLSX, XLS

Always produces HTML + status JSON. If mixed-content pages are detected, page images are saved for LLM processing.

Finalize (Post-Processing)

POST JSON to /finalize with:

• run_id — from the /extract response
• llm_pages — (optional) array of {"page": N, "html": "..."}
• output_format — "html", "excel", or "both" (default: "html")

Merges LLM-extracted pages into base HTML and/or converts to Excel.

Artwork Processing

Supported: PDF (layered packaging artwork)

/health