FileTag

Tag Document

Extract filing metadata (title, type, date, tags, ...) from a single PDF or image and return a suggested filename plus a set of filename patterns.

Requires API-key auth (X-API-Key header). Subject to the per-API-key burst rate limit and -- for free-tier users -- the monthly FileTag credit allowance.

post/api/v1/filetag

Request

  • Base URL: https://api.gemina.co (the document declares no server; this is the origin it was published from)
  • URL: https://api.gemina.co/api/v1/filetag
  • Auth: API key in header X-API-Key

Response

Successful Response

documentIdstring uuid required
documentExtractionIdstring uuid required
suggestedFilenamestring required

Recommended filename for the enriched file -- one of the six filename_patterns, picked as the safest default for general use. Pair this with enriched_file_url when saving the downloaded file.

enrichedFileUrlstring required

Short-lived signed URL to the input file with the extracted metadata embedded directly into the document properties (XMP for PDFs, EXIF/XMP for images). This is the canonical enriched output of the tool -- the file the user actually wants. Agents should download it within enriched_file_expires_in_seconds and save it under suggested_filename rather than embedding metadata client-side. Skip the download only if the user explicitly asked for the metadata payload alone.

enrichedFileExpiresAtstring date-time required

Absolute UTC timestamp when enriched_file_url stops resolving.

enrichedFileExpiresInSecondsinteger required

Seconds until enriched_file_url expires, captured at response time. Easier for agents to reason about than the absolute timestamp.

Changes

No recorded changes to this operation across all 1 revision of this API.