Files

Read a file

Reads any file into Markdown ready for a model: Word, PowerPoint, Excel, PDF, .doc/.ppt/.xls, TXT, Markdown or HTML.

post/extract

Request

  • Base URL: https://api.eu.doconda.com/v1
  • URL: https://api.eu.doconda.com/v1/extract
  • Auth: one of:
    • HTTP bearer
    • HTTP bearer

Request body

Response

The text, as Markdown. Nothing is kept.

object'extraction' required
idstring required
format'docx' | 'pptx' | 'xlsx' | 'pdf' | 'doc' | 'ppt' | 'xls' | 'txt' | 'md' | 'html' | 'png' | 'jpg' | 'gif' | 'webp' required
markdownstring required

Headings, lists and tables kept; one section per slide or sheet; page markers in a PDF. Scanned pages and pictures are read with OCR.

charsinteger required

Length of the whole text, before any cut.

truncatedboolean required

true when longer than 2 000 000 characters.

pagesinteger nullable required

Pages (PDF), slides (PowerPoint) or sheets (Excel).

Changes

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