Basic Information

appmixer.ragieai.core.UpdateDocumentFromUrl

1.0.0

Public

Updates a document from a publicly accessible URL. The document goes through processing steps (pending, partitioning, partitioned, refined, chunked, indexed, summary_indexed, keyword_indexed, ready, failed) before it is ready for retrieval. PDF files over 2000 pages are not supported in hi_res mode.

Input Ports

in

FieldTypeDescription
Document Id text The id of the document to update
Url text Url of the file to download. Must be publicly accessible and HTTP or HTTPS scheme
Mode select Partition strategy for the document. Different strategies exist for textual, audio and video file types. For textual documents: 'hi_res' (extracts images and tables, ~20x slower) or 'fast' (text only, default). For audio: true/false. For video: 'audio_only', 'video_only', 'audio_video'. Use 'all' for highest quality processing of all media types

Output Ports

out

FieldTypeDescription
Status -

Full Metadata